diff --git a/results/Alibaba-NLP__gte-Qwen2-1.5B-instruct/c6c1b92f4a3e1b92b326ad29dd3c8433457df8dd/R2MEDRetrieval.json b/results/Alibaba-NLP__gte-Qwen2-1.5B-instruct/c6c1b92f4a3e1b92b326ad29dd3c8433457df8dd/R2MEDRetrieval.json new file mode 100644 index 0000000000..ee0fabade6 --- /dev/null +++ b/results/Alibaba-NLP__gte-Qwen2-1.5B-instruct/c6c1b92f4a3e1b92b326ad29dd3c8433457df8dd/R2MEDRetrieval.json @@ -0,0 +1,1187 @@ +{ + "dataset_revision": "1.0", + "task_name": "R2MEDRetrieval", + "mteb_version": "1.38.20", + "scores": { + "test": [ + { + "ndcg_at_1": 0.15534, + "ndcg_at_3": 0.15733, + "ndcg_at_5": 0.15068, + "ndcg_at_10": 0.17158, + "ndcg_at_20": 0.20041, + "ndcg_at_100": 0.26314, + "ndcg_at_1000": 0.32761, + "map_at_1": 0.0376, + "map_at_3": 0.08401, + "map_at_5": 0.09239, + "map_at_10": 0.11209, + "map_at_20": 0.12309, + "map_at_100": 0.13613, + "map_at_1000": 0.13986, + "recall_at_1": 0.0376, + "recall_at_3": 0.12183, + "recall_at_5": 0.1426, + "recall_at_10": 0.20792, + "recall_at_20": 0.28802, + "recall_at_100": 0.52119, + "recall_at_1000": 0.88396, + "precision_at_1": 0.15534, + "precision_at_3": 0.14239, + "precision_at_5": 0.1068, + "precision_at_10": 0.08155, + "precision_at_20": 0.05534, + "precision_at_100": 0.02, + "precision_at_1000": 0.00324, + "mrr_at_1": 0.135922, + "mrr_at_3": 0.203883, + "mrr_at_5": 0.212621, + "mrr_at_10": 0.224149, + "mrr_at_20": 0.230638, + "mrr_at_100": 0.23588, + "mrr_at_1000": 0.236849, + "nauc_ndcg_at_1_max": 0.043162, + "nauc_ndcg_at_1_std": -0.197054, + "nauc_ndcg_at_1_diff1": 0.033, + "nauc_ndcg_at_3_max": 0.036832, + "nauc_ndcg_at_3_std": -0.217969, + "nauc_ndcg_at_3_diff1": 0.042707, + "nauc_ndcg_at_5_max": 0.083252, + "nauc_ndcg_at_5_std": -0.209761, + "nauc_ndcg_at_5_diff1": 0.076015, + "nauc_ndcg_at_10_max": 0.109022, + "nauc_ndcg_at_10_std": -0.179232, + "nauc_ndcg_at_10_diff1": 0.090936, + "nauc_ndcg_at_20_max": 0.055902, + "nauc_ndcg_at_20_std": -0.219545, + "nauc_ndcg_at_20_diff1": 0.056387, + "nauc_ndcg_at_100_max": 0.007695, + "nauc_ndcg_at_100_std": -0.243414, + "nauc_ndcg_at_100_diff1": 0.027337, + "nauc_ndcg_at_1000_max": 0.04756, + "nauc_ndcg_at_1000_std": -0.179507, + "nauc_ndcg_at_1000_diff1": 0.022172, + "nauc_map_at_1_max": 0.152888, + "nauc_map_at_1_std": -0.206546, + "nauc_map_at_1_diff1": 0.067181, + "nauc_map_at_3_max": 0.133551, + "nauc_map_at_3_std": -0.234395, + "nauc_map_at_3_diff1": 0.074463, + "nauc_map_at_5_max": 0.146198, + "nauc_map_at_5_std": -0.219463, + "nauc_map_at_5_diff1": 0.090968, + "nauc_map_at_10_max": 0.127698, + "nauc_map_at_10_std": -0.211415, + "nauc_map_at_10_diff1": 0.105176, + "nauc_map_at_20_max": 0.091347, + "nauc_map_at_20_std": -0.227329, + "nauc_map_at_20_diff1": 0.070797, + "nauc_map_at_100_max": 0.07235, + "nauc_map_at_100_std": -0.228508, + "nauc_map_at_100_diff1": 0.059918, + "nauc_map_at_1000_max": 0.073293, + "nauc_map_at_1000_std": -0.224687, + "nauc_map_at_1000_diff1": 0.058591, + "nauc_recall_at_1_max": 0.152888, + "nauc_recall_at_1_std": -0.206546, + "nauc_recall_at_1_diff1": 0.067181, + "nauc_recall_at_3_max": 0.158256, + "nauc_recall_at_3_std": -0.198852, + "nauc_recall_at_3_diff1": 0.135204, + "nauc_recall_at_5_max": 0.205718, + "nauc_recall_at_5_std": -0.170234, + "nauc_recall_at_5_diff1": 0.168633, + "nauc_recall_at_10_max": 0.175269, + "nauc_recall_at_10_std": -0.125935, + "nauc_recall_at_10_diff1": 0.14925, + "nauc_recall_at_20_max": 0.045362, + "nauc_recall_at_20_std": -0.209459, + "nauc_recall_at_20_diff1": 0.063763, + "nauc_recall_at_100_max": -0.093978, + "nauc_recall_at_100_std": -0.289285, + "nauc_recall_at_100_diff1": -0.012271, + "nauc_recall_at_1000_max": 0.205614, + "nauc_recall_at_1000_std": 0.315539, + "nauc_recall_at_1000_diff1": -0.052651, + "nauc_precision_at_1_max": 0.043162, + "nauc_precision_at_1_std": -0.197054, + "nauc_precision_at_1_diff1": 0.033, + "nauc_precision_at_3_max": -0.034286, + "nauc_precision_at_3_std": -0.231688, + "nauc_precision_at_3_diff1": 0.004616, + "nauc_precision_at_5_max": -0.012642, + "nauc_precision_at_5_std": -0.198358, + "nauc_precision_at_5_diff1": 0.016286, + "nauc_precision_at_10_max": -0.036443, + "nauc_precision_at_10_std": -0.174946, + "nauc_precision_at_10_diff1": 0.034214, + "nauc_precision_at_20_max": -0.125512, + "nauc_precision_at_20_std": -0.214498, + "nauc_precision_at_20_diff1": -0.051533, + "nauc_precision_at_100_max": -0.177078, + "nauc_precision_at_100_std": -0.18669, + "nauc_precision_at_100_diff1": -0.090969, + "nauc_precision_at_1000_max": -0.126668, + "nauc_precision_at_1000_std": -0.038646, + "nauc_precision_at_1000_diff1": -0.124093, + "nauc_mrr_at_1_max": 0.047079, + "nauc_mrr_at_1_std": -0.179281, + "nauc_mrr_at_1_diff1": 0.127084, + "nauc_mrr_at_3_max": 0.041883, + "nauc_mrr_at_3_std": -0.214568, + "nauc_mrr_at_3_diff1": 0.083644, + "nauc_mrr_at_5_max": 0.058587, + "nauc_mrr_at_5_std": -0.204153, + "nauc_mrr_at_5_diff1": 0.077505, + "nauc_mrr_at_10_max": 0.055233, + "nauc_mrr_at_10_std": -0.185858, + "nauc_mrr_at_10_diff1": 0.065808, + "nauc_mrr_at_20_max": 0.053161, + "nauc_mrr_at_20_std": -0.19455, + "nauc_mrr_at_20_diff1": 0.076221, + "nauc_mrr_at_100_max": 0.04739, + "nauc_mrr_at_100_std": -0.200545, + "nauc_mrr_at_100_diff1": 0.074901, + "nauc_mrr_at_1000_max": 0.047993, + "nauc_mrr_at_1000_std": -0.199493, + "nauc_mrr_at_1000_diff1": 0.074695, + "main_score": 0.17158, + "hf_subset": "Biology", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.33766, + "ndcg_at_3": 0.3315, + "ndcg_at_5": 0.38632, + "ndcg_at_10": 0.42491, + "ndcg_at_20": 0.45599, + "ndcg_at_100": 0.50643, + "ndcg_at_1000": 0.53475, + "map_at_1": 0.15813, + "map_at_3": 0.24478, + "map_at_5": 0.29691, + "map_at_10": 0.32723, + "map_at_20": 0.34036, + "map_at_100": 0.35319, + "map_at_1000": 0.35551, + "recall_at_1": 0.15813, + "recall_at_3": 0.31487, + "recall_at_5": 0.45441, + "recall_at_10": 0.56146, + "recall_at_20": 0.64712, + "recall_at_100": 0.8287, + "recall_at_1000": 0.99382, + "precision_at_1": 0.33766, + "precision_at_3": 0.22078, + "precision_at_5": 0.21039, + "precision_at_10": 0.14156, + "precision_at_20": 0.08636, + "precision_at_100": 0.02429, + "precision_at_1000": 0.00292, + "mrr_at_1": 0.337662, + "mrr_at_3": 0.422078, + "mrr_at_5": 0.448701, + "mrr_at_10": 0.459699, + "mrr_at_20": 0.464088, + "mrr_at_100": 0.467727, + "mrr_at_1000": 0.468137, + "nauc_ndcg_at_1_max": 0.107933, + "nauc_ndcg_at_1_std": -0.036251, + "nauc_ndcg_at_1_diff1": 0.20485, + "nauc_ndcg_at_3_max": 0.003896, + "nauc_ndcg_at_3_std": -0.159925, + "nauc_ndcg_at_3_diff1": 0.158787, + "nauc_ndcg_at_5_max": -0.024326, + "nauc_ndcg_at_5_std": -0.259057, + "nauc_ndcg_at_5_diff1": 0.087966, + "nauc_ndcg_at_10_max": 0.046541, + "nauc_ndcg_at_10_std": -0.216917, + "nauc_ndcg_at_10_diff1": 0.102002, + "nauc_ndcg_at_20_max": 0.08808, + "nauc_ndcg_at_20_std": -0.193759, + "nauc_ndcg_at_20_diff1": 0.123764, + "nauc_ndcg_at_100_max": 0.101127, + "nauc_ndcg_at_100_std": -0.140113, + "nauc_ndcg_at_100_diff1": 0.094295, + "nauc_ndcg_at_1000_max": 0.105675, + "nauc_ndcg_at_1000_std": -0.119119, + "nauc_ndcg_at_1000_diff1": 0.122725, + "nauc_map_at_1_max": -0.128017, + "nauc_map_at_1_std": -0.228048, + "nauc_map_at_1_diff1": 0.206813, + "nauc_map_at_3_max": -0.077104, + "nauc_map_at_3_std": -0.271212, + "nauc_map_at_3_diff1": 0.163482, + "nauc_map_at_5_max": -0.051938, + "nauc_map_at_5_std": -0.301827, + "nauc_map_at_5_diff1": 0.10682, + "nauc_map_at_10_max": 0.009518, + "nauc_map_at_10_std": -0.253407, + "nauc_map_at_10_diff1": 0.119989, + "nauc_map_at_20_max": 0.027802, + "nauc_map_at_20_std": -0.240282, + "nauc_map_at_20_diff1": 0.128026, + "nauc_map_at_100_max": 0.036107, + "nauc_map_at_100_std": -0.222729, + "nauc_map_at_100_diff1": 0.120636, + "nauc_map_at_1000_max": 0.035463, + "nauc_map_at_1000_std": -0.220357, + "nauc_map_at_1000_diff1": 0.122269, + "nauc_recall_at_1_max": -0.128017, + "nauc_recall_at_1_std": -0.228048, + "nauc_recall_at_1_diff1": 0.206813, + "nauc_recall_at_3_max": -0.092021, + "nauc_recall_at_3_std": -0.277492, + "nauc_recall_at_3_diff1": 0.137652, + "nauc_recall_at_5_max": -0.114084, + "nauc_recall_at_5_std": -0.409315, + "nauc_recall_at_5_diff1": -0.005854, + "nauc_recall_at_10_max": -0.005245, + "nauc_recall_at_10_std": -0.310963, + "nauc_recall_at_10_diff1": 0.003225, + "nauc_recall_at_20_max": 0.092056, + "nauc_recall_at_20_std": -0.296093, + "nauc_recall_at_20_diff1": 0.075963, + "nauc_recall_at_100_max": 0.087527, + "nauc_recall_at_100_std": -0.212826, + "nauc_recall_at_100_diff1": -0.104752, + "nauc_recall_at_1000_max": -0.431216, + "nauc_recall_at_1000_std": -1.730542, + "nauc_recall_at_1000_diff1": -0.013341, + "nauc_precision_at_1_max": 0.107933, + "nauc_precision_at_1_std": -0.036251, + "nauc_precision_at_1_diff1": 0.20485, + "nauc_precision_at_3_max": 0.169329, + "nauc_precision_at_3_std": -0.048836, + "nauc_precision_at_3_diff1": 0.120776, + "nauc_precision_at_5_max": 0.159786, + "nauc_precision_at_5_std": -0.050926, + "nauc_precision_at_5_diff1": -0.036858, + "nauc_precision_at_10_max": 0.274123, + "nauc_precision_at_10_std": 0.126855, + "nauc_precision_at_10_diff1": -0.026095, + "nauc_precision_at_20_max": 0.332965, + "nauc_precision_at_20_std": 0.222284, + "nauc_precision_at_20_diff1": -0.010906, + "nauc_precision_at_100_max": 0.306047, + "nauc_precision_at_100_std": 0.407784, + "nauc_precision_at_100_diff1": -0.111434, + "nauc_precision_at_1000_max": 0.310909, + "nauc_precision_at_1000_std": 0.502172, + "nauc_precision_at_1000_diff1": -0.022547, + "nauc_mrr_at_1_max": 0.107933, + "nauc_mrr_at_1_std": -0.036251, + "nauc_mrr_at_1_diff1": 0.20485, + "nauc_mrr_at_3_max": 0.133737, + "nauc_mrr_at_3_std": -0.020626, + "nauc_mrr_at_3_diff1": 0.198239, + "nauc_mrr_at_5_max": 0.118186, + "nauc_mrr_at_5_std": -0.052252, + "nauc_mrr_at_5_diff1": 0.164958, + "nauc_mrr_at_10_max": 0.123855, + "nauc_mrr_at_10_std": -0.036904, + "nauc_mrr_at_10_diff1": 0.161794, + "nauc_mrr_at_20_max": 0.132658, + "nauc_mrr_at_20_std": -0.031363, + "nauc_mrr_at_20_diff1": 0.165566, + "nauc_mrr_at_100_max": 0.129236, + "nauc_mrr_at_100_std": -0.033646, + "nauc_mrr_at_100_diff1": 0.166151, + "nauc_mrr_at_1000_max": 0.12938, + "nauc_mrr_at_1000_std": -0.03328, + "nauc_mrr_at_1000_diff1": 0.16674, + "main_score": 0.42491, + "hf_subset": "Bioinformatics", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.35227, + "ndcg_at_3": 0.36071, + "ndcg_at_5": 0.381, + "ndcg_at_10": 0.42818, + "ndcg_at_20": 0.46417, + "ndcg_at_100": 0.51092, + "ndcg_at_1000": 0.53819, + "map_at_1": 0.22217, + "map_at_3": 0.29807, + "map_at_5": 0.32109, + "map_at_10": 0.34951, + "map_at_20": 0.36535, + "map_at_100": 0.37408, + "map_at_1000": 0.37602, + "recall_at_1": 0.22217, + "recall_at_3": 0.35299, + "recall_at_5": 0.414, + "recall_at_10": 0.53144, + "recall_at_20": 0.62902, + "recall_at_100": 0.82036, + "recall_at_1000": 0.96752, + "precision_at_1": 0.35227, + "precision_at_3": 0.21212, + "precision_at_5": 0.16364, + "precision_at_10": 0.11818, + "precision_at_20": 0.07557, + "precision_at_100": 0.02114, + "precision_at_1000": 0.00268, + "mrr_at_1": 0.352273, + "mrr_at_3": 0.42803, + "mrr_at_5": 0.444508, + "mrr_at_10": 0.459952, + "mrr_at_20": 0.466378, + "mrr_at_100": 0.469637, + "mrr_at_1000": 0.469934, + "nauc_ndcg_at_1_max": 0.466956, + "nauc_ndcg_at_1_std": 0.104462, + "nauc_ndcg_at_1_diff1": 0.269119, + "nauc_ndcg_at_3_max": 0.378987, + "nauc_ndcg_at_3_std": 0.022767, + "nauc_ndcg_at_3_diff1": 0.34481, + "nauc_ndcg_at_5_max": 0.413435, + "nauc_ndcg_at_5_std": 0.028992, + "nauc_ndcg_at_5_diff1": 0.348732, + "nauc_ndcg_at_10_max": 0.422955, + "nauc_ndcg_at_10_std": 0.06409, + "nauc_ndcg_at_10_diff1": 0.328809, + "nauc_ndcg_at_20_max": 0.442583, + "nauc_ndcg_at_20_std": 0.074299, + "nauc_ndcg_at_20_diff1": 0.359118, + "nauc_ndcg_at_100_max": 0.44028, + "nauc_ndcg_at_100_std": 0.081741, + "nauc_ndcg_at_100_diff1": 0.381222, + "nauc_ndcg_at_1000_max": 0.460224, + "nauc_ndcg_at_1000_std": 0.09562, + "nauc_ndcg_at_1000_diff1": 0.36562, + "nauc_map_at_1_max": 0.258775, + "nauc_map_at_1_std": -0.074488, + "nauc_map_at_1_diff1": 0.378686, + "nauc_map_at_3_max": 0.3242, + "nauc_map_at_3_std": -0.010066, + "nauc_map_at_3_diff1": 0.350084, + "nauc_map_at_5_max": 0.364598, + "nauc_map_at_5_std": 0.011142, + "nauc_map_at_5_diff1": 0.350776, + "nauc_map_at_10_max": 0.387372, + "nauc_map_at_10_std": 0.033698, + "nauc_map_at_10_diff1": 0.34773, + "nauc_map_at_20_max": 0.40178, + "nauc_map_at_20_std": 0.039617, + "nauc_map_at_20_diff1": 0.360901, + "nauc_map_at_100_max": 0.404443, + "nauc_map_at_100_std": 0.041352, + "nauc_map_at_100_diff1": 0.365251, + "nauc_map_at_1000_max": 0.406531, + "nauc_map_at_1000_std": 0.043544, + "nauc_map_at_1000_diff1": 0.364464, + "nauc_recall_at_1_max": 0.258775, + "nauc_recall_at_1_std": -0.074488, + "nauc_recall_at_1_diff1": 0.378686, + "nauc_recall_at_3_max": 0.274339, + "nauc_recall_at_3_std": -0.051182, + "nauc_recall_at_3_diff1": 0.346018, + "nauc_recall_at_5_max": 0.366718, + "nauc_recall_at_5_std": -0.016842, + "nauc_recall_at_5_diff1": 0.341731, + "nauc_recall_at_10_max": 0.360763, + "nauc_recall_at_10_std": 0.049114, + "nauc_recall_at_10_diff1": 0.275663, + "nauc_recall_at_20_max": 0.382995, + "nauc_recall_at_20_std": 0.065099, + "nauc_recall_at_20_diff1": 0.343502, + "nauc_recall_at_100_max": 0.276467, + "nauc_recall_at_100_std": 0.07351, + "nauc_recall_at_100_diff1": 0.522068, + "nauc_recall_at_1000_max": 0.443533, + "nauc_recall_at_1000_std": 0.210116, + "nauc_recall_at_1000_diff1": 0.515783, + "nauc_precision_at_1_max": 0.466956, + "nauc_precision_at_1_std": 0.104462, + "nauc_precision_at_1_diff1": 0.269119, + "nauc_precision_at_3_max": 0.510697, + "nauc_precision_at_3_std": 0.213785, + "nauc_precision_at_3_diff1": 0.192106, + "nauc_precision_at_5_max": 0.568913, + "nauc_precision_at_5_std": 0.238838, + "nauc_precision_at_5_diff1": 0.182005, + "nauc_precision_at_10_max": 0.517725, + "nauc_precision_at_10_std": 0.311062, + "nauc_precision_at_10_diff1": 0.120102, + "nauc_precision_at_20_max": 0.476959, + "nauc_precision_at_20_std": 0.307682, + "nauc_precision_at_20_diff1": 0.157045, + "nauc_precision_at_100_max": 0.315846, + "nauc_precision_at_100_std": 0.279559, + "nauc_precision_at_100_diff1": 0.095685, + "nauc_precision_at_1000_max": 0.212281, + "nauc_precision_at_1000_std": 0.274573, + "nauc_precision_at_1000_diff1": -0.048411, + "nauc_mrr_at_1_max": 0.466956, + "nauc_mrr_at_1_std": 0.104462, + "nauc_mrr_at_1_diff1": 0.269119, + "nauc_mrr_at_3_max": 0.43493, + "nauc_mrr_at_3_std": 0.056197, + "nauc_mrr_at_3_diff1": 0.304602, + "nauc_mrr_at_5_max": 0.466773, + "nauc_mrr_at_5_std": 0.060573, + "nauc_mrr_at_5_diff1": 0.308103, + "nauc_mrr_at_10_max": 0.472314, + "nauc_mrr_at_10_std": 0.084723, + "nauc_mrr_at_10_diff1": 0.304944, + "nauc_mrr_at_20_max": 0.470816, + "nauc_mrr_at_20_std": 0.083581, + "nauc_mrr_at_20_diff1": 0.308095, + "nauc_mrr_at_100_max": 0.468242, + "nauc_mrr_at_100_std": 0.082214, + "nauc_mrr_at_100_diff1": 0.309585, + "nauc_mrr_at_1000_max": 0.468595, + "nauc_mrr_at_1000_std": 0.082018, + "nauc_mrr_at_1000_diff1": 0.30915, + "main_score": 0.42818, + "hf_subset": "Medical-Sciences", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.08247, + "ndcg_at_3": 0.06731, + "ndcg_at_5": 0.06819, + "ndcg_at_10": 0.08887, + "ndcg_at_20": 0.10327, + "ndcg_at_100": 0.13433, + "ndcg_at_1000": 0.19346, + "map_at_1": 0.03548, + "map_at_3": 0.04444, + "map_at_5": 0.04818, + "map_at_10": 0.05665, + "map_at_20": 0.06042, + "map_at_100": 0.0652, + "map_at_1000": 0.06742, + "recall_at_1": 0.03548, + "recall_at_3": 0.05733, + "recall_at_5": 0.07228, + "recall_at_10": 0.13276, + "recall_at_20": 0.17418, + "recall_at_100": 0.29999, + "recall_at_1000": 0.66381, + "precision_at_1": 0.08247, + "precision_at_3": 0.04467, + "precision_at_5": 0.03299, + "precision_at_10": 0.02784, + "precision_at_20": 0.0201, + "precision_at_100": 0.00773, + "precision_at_1000": 0.00185, + "mrr_at_1": 0.082474, + "mrr_at_3": 0.104811, + "mrr_at_5": 0.10945, + "mrr_at_10": 0.119674, + "mrr_at_20": 0.126044, + "mrr_at_100": 0.129477, + "mrr_at_1000": 0.131019, + "nauc_ndcg_at_1_max": -0.053046, + "nauc_ndcg_at_1_std": 0.074889, + "nauc_ndcg_at_1_diff1": 0.195563, + "nauc_ndcg_at_3_max": -0.081115, + "nauc_ndcg_at_3_std": -0.001036, + "nauc_ndcg_at_3_diff1": 0.325966, + "nauc_ndcg_at_5_max": -0.06461, + "nauc_ndcg_at_5_std": -0.000435, + "nauc_ndcg_at_5_diff1": 0.346635, + "nauc_ndcg_at_10_max": -0.036987, + "nauc_ndcg_at_10_std": 0.06998, + "nauc_ndcg_at_10_diff1": 0.201827, + "nauc_ndcg_at_20_max": -0.046214, + "nauc_ndcg_at_20_std": 0.058367, + "nauc_ndcg_at_20_diff1": 0.173209, + "nauc_ndcg_at_100_max": -0.079043, + "nauc_ndcg_at_100_std": 0.052391, + "nauc_ndcg_at_100_diff1": 0.172187, + "nauc_ndcg_at_1000_max": -0.00423, + "nauc_ndcg_at_1000_std": 0.115002, + "nauc_ndcg_at_1000_diff1": 0.177606, + "nauc_map_at_1_max": 0.079533, + "nauc_map_at_1_std": -0.036639, + "nauc_map_at_1_diff1": 0.488684, + "nauc_map_at_3_max": -0.007424, + "nauc_map_at_3_std": -0.03519, + "nauc_map_at_3_diff1": 0.439048, + "nauc_map_at_5_max": -0.010565, + "nauc_map_at_5_std": -0.026047, + "nauc_map_at_5_diff1": 0.431618, + "nauc_map_at_10_max": 0.005629, + "nauc_map_at_10_std": 0.015048, + "nauc_map_at_10_diff1": 0.336172, + "nauc_map_at_20_max": -6e-06, + "nauc_map_at_20_std": 0.018, + "nauc_map_at_20_diff1": 0.315877, + "nauc_map_at_100_max": -0.009186, + "nauc_map_at_100_std": 0.01868, + "nauc_map_at_100_diff1": 0.304046, + "nauc_map_at_1000_max": -0.002502, + "nauc_map_at_1000_std": 0.024117, + "nauc_map_at_1000_diff1": 0.304701, + "nauc_recall_at_1_max": 0.079533, + "nauc_recall_at_1_std": -0.036639, + "nauc_recall_at_1_diff1": 0.488684, + "nauc_recall_at_3_max": -0.083517, + "nauc_recall_at_3_std": -0.03522, + "nauc_recall_at_3_diff1": 0.358313, + "nauc_recall_at_5_max": -0.061783, + "nauc_recall_at_5_std": 0.005919, + "nauc_recall_at_5_diff1": 0.326886, + "nauc_recall_at_10_max": -0.027948, + "nauc_recall_at_10_std": 0.112751, + "nauc_recall_at_10_diff1": 0.041427, + "nauc_recall_at_20_max": -0.056244, + "nauc_recall_at_20_std": 0.070025, + "nauc_recall_at_20_diff1": -0.001759, + "nauc_recall_at_100_max": -0.125272, + "nauc_recall_at_100_std": 0.08911, + "nauc_recall_at_100_diff1": 0.029936, + "nauc_recall_at_1000_max": 0.14519, + "nauc_recall_at_1000_std": 0.356555, + "nauc_recall_at_1000_diff1": 0.037083, + "nauc_precision_at_1_max": -0.053046, + "nauc_precision_at_1_std": 0.074889, + "nauc_precision_at_1_diff1": 0.195563, + "nauc_precision_at_3_max": -0.165841, + "nauc_precision_at_3_std": 0.026957, + "nauc_precision_at_3_diff1": 0.244365, + "nauc_precision_at_5_max": -0.154372, + "nauc_precision_at_5_std": 0.016332, + "nauc_precision_at_5_diff1": 0.264705, + "nauc_precision_at_10_max": -0.093357, + "nauc_precision_at_10_std": 0.143975, + "nauc_precision_at_10_diff1": 0.029316, + "nauc_precision_at_20_max": -0.080029, + "nauc_precision_at_20_std": 0.11739, + "nauc_precision_at_20_diff1": 0.022441, + "nauc_precision_at_100_max": -0.147011, + "nauc_precision_at_100_std": 0.011758, + "nauc_precision_at_100_diff1": 0.081096, + "nauc_precision_at_1000_max": -0.00426, + "nauc_precision_at_1000_std": 0.050125, + "nauc_precision_at_1000_diff1": 0.002264, + "nauc_mrr_at_1_max": -0.053046, + "nauc_mrr_at_1_std": 0.074889, + "nauc_mrr_at_1_diff1": 0.195563, + "nauc_mrr_at_3_max": -0.114533, + "nauc_mrr_at_3_std": 0.046754, + "nauc_mrr_at_3_diff1": 0.240621, + "nauc_mrr_at_5_max": -0.106789, + "nauc_mrr_at_5_std": 0.046656, + "nauc_mrr_at_5_diff1": 0.237736, + "nauc_mrr_at_10_max": -0.100161, + "nauc_mrr_at_10_std": 0.065384, + "nauc_mrr_at_10_diff1": 0.194025, + "nauc_mrr_at_20_max": -0.098137, + "nauc_mrr_at_20_std": 0.062532, + "nauc_mrr_at_20_diff1": 0.185965, + "nauc_mrr_at_100_max": -0.100888, + "nauc_mrr_at_100_std": 0.058775, + "nauc_mrr_at_100_diff1": 0.186474, + "nauc_mrr_at_1000_max": -0.098384, + "nauc_mrr_at_1000_std": 0.061412, + "nauc_mrr_at_1000_diff1": 0.186931, + "main_score": 0.08887, + "hf_subset": "MedXpertQA-Exam", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.07627, + "ndcg_at_3": 0.08847, + "ndcg_at_5": 0.10051, + "ndcg_at_10": 0.119, + "ndcg_at_20": 0.1352, + "ndcg_at_100": 0.19084, + "ndcg_at_1000": 0.24845, + "map_at_1": 0.01923, + "map_at_3": 0.04852, + "map_at_5": 0.06613, + "map_at_10": 0.07774, + "map_at_20": 0.08344, + "map_at_100": 0.09267, + "map_at_1000": 0.09575, + "recall_at_1": 0.01923, + "recall_at_3": 0.06812, + "recall_at_5": 0.10916, + "recall_at_10": 0.15762, + "recall_at_20": 0.20107, + "recall_at_100": 0.40383, + "recall_at_1000": 0.70176, + "precision_at_1": 0.07627, + "precision_at_3": 0.08475, + "precision_at_5": 0.08136, + "precision_at_10": 0.05678, + "precision_at_20": 0.03644, + "precision_at_100": 0.01525, + "precision_at_1000": 0.00292, + "mrr_at_1": 0.076271, + "mrr_at_3": 0.120056, + "mrr_at_5": 0.134463, + "mrr_at_10": 0.14504, + "mrr_at_20": 0.149384, + "mrr_at_100": 0.157053, + "mrr_at_1000": 0.157907, + "nauc_ndcg_at_1_max": 0.329794, + "nauc_ndcg_at_1_std": 0.07435, + "nauc_ndcg_at_1_diff1": 0.329409, + "nauc_ndcg_at_3_max": 0.213967, + "nauc_ndcg_at_3_std": 0.123496, + "nauc_ndcg_at_3_diff1": 0.203749, + "nauc_ndcg_at_5_max": 0.235176, + "nauc_ndcg_at_5_std": 0.148111, + "nauc_ndcg_at_5_diff1": 0.177289, + "nauc_ndcg_at_10_max": 0.230068, + "nauc_ndcg_at_10_std": 0.231773, + "nauc_ndcg_at_10_diff1": 0.159032, + "nauc_ndcg_at_20_max": 0.212785, + "nauc_ndcg_at_20_std": 0.224056, + "nauc_ndcg_at_20_diff1": 0.135052, + "nauc_ndcg_at_100_max": 0.241107, + "nauc_ndcg_at_100_std": 0.256899, + "nauc_ndcg_at_100_diff1": 0.149691, + "nauc_ndcg_at_1000_max": 0.259561, + "nauc_ndcg_at_1000_std": 0.26709, + "nauc_ndcg_at_1000_diff1": 0.175585, + "nauc_map_at_1_max": 0.347594, + "nauc_map_at_1_std": 0.043959, + "nauc_map_at_1_diff1": 0.399534, + "nauc_map_at_3_max": 0.264503, + "nauc_map_at_3_std": 0.120048, + "nauc_map_at_3_diff1": 0.259438, + "nauc_map_at_5_max": 0.305887, + "nauc_map_at_5_std": 0.158882, + "nauc_map_at_5_diff1": 0.216812, + "nauc_map_at_10_max": 0.283553, + "nauc_map_at_10_std": 0.202707, + "nauc_map_at_10_diff1": 0.193518, + "nauc_map_at_20_max": 0.272925, + "nauc_map_at_20_std": 0.199785, + "nauc_map_at_20_diff1": 0.181677, + "nauc_map_at_100_max": 0.279139, + "nauc_map_at_100_std": 0.21617, + "nauc_map_at_100_diff1": 0.180556, + "nauc_map_at_1000_max": 0.280036, + "nauc_map_at_1000_std": 0.217717, + "nauc_map_at_1000_diff1": 0.182273, + "nauc_recall_at_1_max": 0.347594, + "nauc_recall_at_1_std": 0.043959, + "nauc_recall_at_1_diff1": 0.399534, + "nauc_recall_at_3_max": 0.155283, + "nauc_recall_at_3_std": 0.106446, + "nauc_recall_at_3_diff1": 0.156999, + "nauc_recall_at_5_max": 0.240509, + "nauc_recall_at_5_std": 0.168729, + "nauc_recall_at_5_diff1": 0.157653, + "nauc_recall_at_10_max": 0.200596, + "nauc_recall_at_10_std": 0.301042, + "nauc_recall_at_10_diff1": 0.120235, + "nauc_recall_at_20_max": 0.154829, + "nauc_recall_at_20_std": 0.259338, + "nauc_recall_at_20_diff1": 0.076032, + "nauc_recall_at_100_max": 0.185848, + "nauc_recall_at_100_std": 0.291596, + "nauc_recall_at_100_diff1": 0.080925, + "nauc_recall_at_1000_max": 0.283692, + "nauc_recall_at_1000_std": 0.448373, + "nauc_recall_at_1000_diff1": 0.160741, + "nauc_precision_at_1_max": 0.329794, + "nauc_precision_at_1_std": 0.07435, + "nauc_precision_at_1_diff1": 0.329409, + "nauc_precision_at_3_max": 0.220339, + "nauc_precision_at_3_std": 0.149346, + "nauc_precision_at_3_diff1": 0.186439, + "nauc_precision_at_5_max": 0.238345, + "nauc_precision_at_5_std": 0.175114, + "nauc_precision_at_5_diff1": 0.129217, + "nauc_precision_at_10_max": 0.179772, + "nauc_precision_at_10_std": 0.262602, + "nauc_precision_at_10_diff1": 0.085796, + "nauc_precision_at_20_max": 0.158462, + "nauc_precision_at_20_std": 0.244822, + "nauc_precision_at_20_diff1": 0.051726, + "nauc_precision_at_100_max": 0.211875, + "nauc_precision_at_100_std": 0.262885, + "nauc_precision_at_100_diff1": 0.10643, + "nauc_precision_at_1000_max": 0.167686, + "nauc_precision_at_1000_std": 0.127041, + "nauc_precision_at_1000_diff1": 0.12607, + "nauc_mrr_at_1_max": 0.329794, + "nauc_mrr_at_1_std": 0.07435, + "nauc_mrr_at_1_diff1": 0.329409, + "nauc_mrr_at_3_max": 0.191124, + "nauc_mrr_at_3_std": 0.084115, + "nauc_mrr_at_3_diff1": 0.200696, + "nauc_mrr_at_5_max": 0.221313, + "nauc_mrr_at_5_std": 0.123465, + "nauc_mrr_at_5_diff1": 0.21135, + "nauc_mrr_at_10_max": 0.205418, + "nauc_mrr_at_10_std": 0.150732, + "nauc_mrr_at_10_diff1": 0.191646, + "nauc_mrr_at_20_max": 0.205343, + "nauc_mrr_at_20_std": 0.156625, + "nauc_mrr_at_20_diff1": 0.1839, + "nauc_mrr_at_100_max": 0.211667, + "nauc_mrr_at_100_std": 0.14975, + "nauc_mrr_at_100_diff1": 0.192522, + "nauc_mrr_at_1000_max": 0.211813, + "nauc_mrr_at_1000_std": 0.14955, + "nauc_mrr_at_1000_diff1": 0.193293, + "main_score": 0.119, + "hf_subset": "MedQA-Diag", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.35333, + "ndcg_at_3": 0.31345, + "ndcg_at_5": 0.31558, + "ndcg_at_10": 0.33965, + "ndcg_at_20": 0.36024, + "ndcg_at_100": 0.39612, + "ndcg_at_1000": 0.43065, + "map_at_1": 0.20222, + "map_at_3": 0.25561, + "map_at_5": 0.26688, + "map_at_10": 0.28037, + "map_at_20": 0.28766, + "map_at_100": 0.2939, + "map_at_1000": 0.29551, + "recall_at_1": 0.20222, + "recall_at_3": 0.29589, + "recall_at_5": 0.32333, + "recall_at_10": 0.38544, + "recall_at_20": 0.44933, + "recall_at_100": 0.61111, + "recall_at_1000": 0.845, + "precision_at_1": 0.35333, + "precision_at_3": 0.19111, + "precision_at_5": 0.132, + "precision_at_10": 0.07733, + "precision_at_20": 0.04667, + "precision_at_100": 0.01273, + "precision_at_1000": 0.00175, + "mrr_at_1": 0.353333, + "mrr_at_3": 0.405556, + "mrr_at_5": 0.410222, + "mrr_at_10": 0.418198, + "mrr_at_20": 0.422168, + "mrr_at_100": 0.425655, + "mrr_at_1000": 0.426334, + "nauc_ndcg_at_1_max": 0.532606, + "nauc_ndcg_at_1_std": 0.002703, + "nauc_ndcg_at_1_diff1": 0.584681, + "nauc_ndcg_at_3_max": 0.42288, + "nauc_ndcg_at_3_std": -0.037329, + "nauc_ndcg_at_3_diff1": 0.40128, + "nauc_ndcg_at_5_max": 0.415168, + "nauc_ndcg_at_5_std": -0.035653, + "nauc_ndcg_at_5_diff1": 0.401499, + "nauc_ndcg_at_10_max": 0.404207, + "nauc_ndcg_at_10_std": -0.026365, + "nauc_ndcg_at_10_diff1": 0.384172, + "nauc_ndcg_at_20_max": 0.42023, + "nauc_ndcg_at_20_std": -0.0023, + "nauc_ndcg_at_20_diff1": 0.403236, + "nauc_ndcg_at_100_max": 0.436005, + "nauc_ndcg_at_100_std": 0.029782, + "nauc_ndcg_at_100_diff1": 0.412703, + "nauc_ndcg_at_1000_max": 0.443756, + "nauc_ndcg_at_1000_std": 0.022562, + "nauc_ndcg_at_1000_diff1": 0.414695, + "nauc_map_at_1_max": 0.351071, + "nauc_map_at_1_std": -0.086673, + "nauc_map_at_1_diff1": 0.485901, + "nauc_map_at_3_max": 0.363871, + "nauc_map_at_3_std": -0.071608, + "nauc_map_at_3_diff1": 0.392764, + "nauc_map_at_5_max": 0.381044, + "nauc_map_at_5_std": -0.060257, + "nauc_map_at_5_diff1": 0.392069, + "nauc_map_at_10_max": 0.384322, + "nauc_map_at_10_std": -0.052755, + "nauc_map_at_10_diff1": 0.384193, + "nauc_map_at_20_max": 0.392635, + "nauc_map_at_20_std": -0.04437, + "nauc_map_at_20_diff1": 0.391633, + "nauc_map_at_100_max": 0.397761, + "nauc_map_at_100_std": -0.036716, + "nauc_map_at_100_diff1": 0.395121, + "nauc_map_at_1000_max": 0.398341, + "nauc_map_at_1000_std": -0.03635, + "nauc_map_at_1000_diff1": 0.395545, + "nauc_recall_at_1_max": 0.351071, + "nauc_recall_at_1_std": -0.086673, + "nauc_recall_at_1_diff1": 0.485901, + "nauc_recall_at_3_max": 0.292287, + "nauc_recall_at_3_std": -0.079945, + "nauc_recall_at_3_diff1": 0.297014, + "nauc_recall_at_5_max": 0.316812, + "nauc_recall_at_5_std": -0.052169, + "nauc_recall_at_5_diff1": 0.291731, + "nauc_recall_at_10_max": 0.26559, + "nauc_recall_at_10_std": -0.027308, + "nauc_recall_at_10_diff1": 0.241517, + "nauc_recall_at_20_max": 0.29436, + "nauc_recall_at_20_std": 0.044672, + "nauc_recall_at_20_diff1": 0.287698, + "nauc_recall_at_100_max": 0.30619, + "nauc_recall_at_100_std": 0.193308, + "nauc_recall_at_100_diff1": 0.284309, + "nauc_recall_at_1000_max": 0.286836, + "nauc_recall_at_1000_std": 0.238493, + "nauc_recall_at_1000_diff1": 0.197999, + "nauc_precision_at_1_max": 0.532606, + "nauc_precision_at_1_std": 0.002703, + "nauc_precision_at_1_diff1": 0.584681, + "nauc_precision_at_3_max": 0.496832, + "nauc_precision_at_3_std": 0.089476, + "nauc_precision_at_3_diff1": 0.294169, + "nauc_precision_at_5_max": 0.501167, + "nauc_precision_at_5_std": 0.091588, + "nauc_precision_at_5_diff1": 0.260203, + "nauc_precision_at_10_max": 0.471686, + "nauc_precision_at_10_std": 0.104242, + "nauc_precision_at_10_diff1": 0.214886, + "nauc_precision_at_20_max": 0.479972, + "nauc_precision_at_20_std": 0.155596, + "nauc_precision_at_20_diff1": 0.237673, + "nauc_precision_at_100_max": 0.475989, + "nauc_precision_at_100_std": 0.240235, + "nauc_precision_at_100_diff1": 0.211206, + "nauc_precision_at_1000_max": 0.385255, + "nauc_precision_at_1000_std": 0.1811, + "nauc_precision_at_1000_diff1": 0.103737, + "nauc_mrr_at_1_max": 0.532606, + "nauc_mrr_at_1_std": 0.002703, + "nauc_mrr_at_1_diff1": 0.584681, + "nauc_mrr_at_3_max": 0.542744, + "nauc_mrr_at_3_std": 0.01834, + "nauc_mrr_at_3_diff1": 0.533246, + "nauc_mrr_at_5_max": 0.541765, + "nauc_mrr_at_5_std": 0.017306, + "nauc_mrr_at_5_diff1": 0.525069, + "nauc_mrr_at_10_max": 0.534061, + "nauc_mrr_at_10_std": 0.016003, + "nauc_mrr_at_10_diff1": 0.517984, + "nauc_mrr_at_20_max": 0.534788, + "nauc_mrr_at_20_std": 0.019903, + "nauc_mrr_at_20_diff1": 0.521836, + "nauc_mrr_at_100_max": 0.533807, + "nauc_mrr_at_100_std": 0.021207, + "nauc_mrr_at_100_diff1": 0.52121, + "nauc_mrr_at_1000_max": 0.533884, + "nauc_mrr_at_1000_std": 0.020682, + "nauc_mrr_at_1000_diff1": 0.521561, + "main_score": 0.33965, + "hf_subset": "PMC-Treatment", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.12281, + "ndcg_at_3": 0.12477, + "ndcg_at_5": 0.16445, + "ndcg_at_10": 0.19797, + "ndcg_at_20": 0.22294, + "ndcg_at_100": 0.27338, + "ndcg_at_1000": 0.31313, + "map_at_1": 0.05848, + "map_at_3": 0.09454, + "map_at_5": 0.12057, + "map_at_10": 0.13399, + "map_at_20": 0.14131, + "map_at_100": 0.15015, + "map_at_1000": 0.15192, + "recall_at_1": 0.05848, + "recall_at_3": 0.12719, + "recall_at_5": 0.21491, + "recall_at_10": 0.30263, + "recall_at_20": 0.38304, + "recall_at_100": 0.60161, + "recall_at_1000": 0.85892, + "precision_at_1": 0.12281, + "precision_at_3": 0.09357, + "precision_at_5": 0.08772, + "precision_at_10": 0.06053, + "precision_at_20": 0.0386, + "precision_at_100": 0.01272, + "precision_at_1000": 0.00187, + "mrr_at_1": 0.122807, + "mrr_at_3": 0.173977, + "mrr_at_5": 0.195029, + "mrr_at_10": 0.212639, + "mrr_at_20": 0.219988, + "mrr_at_100": 0.22462, + "mrr_at_1000": 0.225334, + "nauc_ndcg_at_1_max": 0.154545, + "nauc_ndcg_at_1_std": 0.067351, + "nauc_ndcg_at_1_diff1": 0.249031, + "nauc_ndcg_at_3_max": 0.175403, + "nauc_ndcg_at_3_std": 0.045531, + "nauc_ndcg_at_3_diff1": 0.075816, + "nauc_ndcg_at_5_max": 0.212487, + "nauc_ndcg_at_5_std": 0.100327, + "nauc_ndcg_at_5_diff1": 0.085731, + "nauc_ndcg_at_10_max": 0.185351, + "nauc_ndcg_at_10_std": 0.149733, + "nauc_ndcg_at_10_diff1": 0.023407, + "nauc_ndcg_at_20_max": 0.176222, + "nauc_ndcg_at_20_std": 0.118825, + "nauc_ndcg_at_20_diff1": 0.050064, + "nauc_ndcg_at_100_max": 0.211189, + "nauc_ndcg_at_100_std": 0.157688, + "nauc_ndcg_at_100_diff1": 0.040603, + "nauc_ndcg_at_1000_max": 0.204589, + "nauc_ndcg_at_1000_std": 0.140899, + "nauc_ndcg_at_1000_diff1": 0.042611, + "nauc_map_at_1_max": 0.123883, + "nauc_map_at_1_std": 0.105859, + "nauc_map_at_1_diff1": 0.262462, + "nauc_map_at_3_max": 0.16633, + "nauc_map_at_3_std": 0.039997, + "nauc_map_at_3_diff1": 0.110588, + "nauc_map_at_5_max": 0.196978, + "nauc_map_at_5_std": 0.083962, + "nauc_map_at_5_diff1": 0.107293, + "nauc_map_at_10_max": 0.18812, + "nauc_map_at_10_std": 0.109534, + "nauc_map_at_10_diff1": 0.076383, + "nauc_map_at_20_max": 0.18326, + "nauc_map_at_20_std": 0.096323, + "nauc_map_at_20_diff1": 0.0862, + "nauc_map_at_100_max": 0.190829, + "nauc_map_at_100_std": 0.106593, + "nauc_map_at_100_diff1": 0.079364, + "nauc_map_at_1000_max": 0.190985, + "nauc_map_at_1000_std": 0.105337, + "nauc_map_at_1000_diff1": 0.079274, + "nauc_recall_at_1_max": 0.123883, + "nauc_recall_at_1_std": 0.105859, + "nauc_recall_at_1_diff1": 0.262462, + "nauc_recall_at_3_max": 0.164922, + "nauc_recall_at_3_std": 0.019967, + "nauc_recall_at_3_diff1": 0.007819, + "nauc_recall_at_5_max": 0.207951, + "nauc_recall_at_5_std": 0.114358, + "nauc_recall_at_5_diff1": 0.03906, + "nauc_recall_at_10_max": 0.126646, + "nauc_recall_at_10_std": 0.209156, + "nauc_recall_at_10_diff1": -0.081549, + "nauc_recall_at_20_max": 0.094647, + "nauc_recall_at_20_std": 0.128031, + "nauc_recall_at_20_diff1": -0.008776, + "nauc_recall_at_100_max": 0.196467, + "nauc_recall_at_100_std": 0.247337, + "nauc_recall_at_100_diff1": -0.031857, + "nauc_recall_at_1000_max": 0.121849, + "nauc_recall_at_1000_std": 0.246114, + "nauc_recall_at_1000_diff1": -0.128008, + "nauc_precision_at_1_max": 0.154545, + "nauc_precision_at_1_std": 0.067351, + "nauc_precision_at_1_diff1": 0.249031, + "nauc_precision_at_3_max": 0.247684, + "nauc_precision_at_3_std": 0.021781, + "nauc_precision_at_3_diff1": 0.001076, + "nauc_precision_at_5_max": 0.259528, + "nauc_precision_at_5_std": 0.109571, + "nauc_precision_at_5_diff1": 0.007519, + "nauc_precision_at_10_max": 0.23801, + "nauc_precision_at_10_std": 0.165596, + "nauc_precision_at_10_diff1": -0.090463, + "nauc_precision_at_20_max": 0.220919, + "nauc_precision_at_20_std": 0.104084, + "nauc_precision_at_20_diff1": -0.041424, + "nauc_precision_at_100_max": 0.292023, + "nauc_precision_at_100_std": 0.173143, + "nauc_precision_at_100_diff1": -0.049696, + "nauc_precision_at_1000_max": 0.228425, + "nauc_precision_at_1000_std": 0.078727, + "nauc_precision_at_1000_diff1": -0.020921, + "nauc_mrr_at_1_max": 0.154545, + "nauc_mrr_at_1_std": 0.067351, + "nauc_mrr_at_1_diff1": 0.249031, + "nauc_mrr_at_3_max": 0.185257, + "nauc_mrr_at_3_std": 0.068213, + "nauc_mrr_at_3_diff1": 0.113716, + "nauc_mrr_at_5_max": 0.196558, + "nauc_mrr_at_5_std": 0.089205, + "nauc_mrr_at_5_diff1": 0.128505, + "nauc_mrr_at_10_max": 0.183143, + "nauc_mrr_at_10_std": 0.108583, + "nauc_mrr_at_10_diff1": 0.100643, + "nauc_mrr_at_20_max": 0.184737, + "nauc_mrr_at_20_std": 0.102859, + "nauc_mrr_at_20_diff1": 0.106083, + "nauc_mrr_at_100_max": 0.185266, + "nauc_mrr_at_100_std": 0.107388, + "nauc_mrr_at_100_diff1": 0.108241, + "nauc_mrr_at_1000_max": 0.184376, + "nauc_mrr_at_1000_std": 0.106372, + "nauc_mrr_at_1000_diff1": 0.108255, + "main_score": 0.19797, + "hf_subset": "PMC-Clinical", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.17829, + "ndcg_at_3": 0.16057, + "ndcg_at_5": 0.17393, + "ndcg_at_10": 0.20994, + "ndcg_at_20": 0.26523, + "ndcg_at_100": 0.34459, + "ndcg_at_1000": 0.39176, + "map_at_1": 0.06318, + "map_at_3": 0.09748, + "map_at_5": 0.11515, + "map_at_10": 0.13395, + "map_at_20": 0.15252, + "map_at_100": 0.17153, + "map_at_1000": 0.17486, + "recall_at_1": 0.06318, + "recall_at_3": 0.12545, + "recall_at_5": 0.17791, + "recall_at_10": 0.25917, + "recall_at_20": 0.40879, + "recall_at_100": 0.69302, + "recall_at_1000": 0.95129, + "precision_at_1": 0.17829, + "precision_at_3": 0.13437, + "precision_at_5": 0.12093, + "precision_at_10": 0.08992, + "precision_at_20": 0.07093, + "precision_at_100": 0.02527, + "precision_at_1000": 0.00339, + "mrr_at_1": 0.178295, + "mrr_at_3": 0.250646, + "mrr_at_5": 0.274677, + "mrr_at_10": 0.291584, + "mrr_at_20": 0.304723, + "mrr_at_100": 0.307817, + "mrr_at_1000": 0.308504, + "nauc_ndcg_at_1_max": 0.321138, + "nauc_ndcg_at_1_std": 0.172397, + "nauc_ndcg_at_1_diff1": 0.238424, + "nauc_ndcg_at_3_max": 0.219563, + "nauc_ndcg_at_3_std": 0.023852, + "nauc_ndcg_at_3_diff1": 0.155533, + "nauc_ndcg_at_5_max": 0.200423, + "nauc_ndcg_at_5_std": 0.070287, + "nauc_ndcg_at_5_diff1": 0.138789, + "nauc_ndcg_at_10_max": 0.214234, + "nauc_ndcg_at_10_std": 0.054603, + "nauc_ndcg_at_10_diff1": 0.094064, + "nauc_ndcg_at_20_max": 0.212209, + "nauc_ndcg_at_20_std": 0.124929, + "nauc_ndcg_at_20_diff1": 0.039628, + "nauc_ndcg_at_100_max": 0.227845, + "nauc_ndcg_at_100_std": 0.202778, + "nauc_ndcg_at_100_diff1": 0.032639, + "nauc_ndcg_at_1000_max": 0.226608, + "nauc_ndcg_at_1000_std": 0.195814, + "nauc_ndcg_at_1000_diff1": 0.059843, + "nauc_map_at_1_max": 0.156957, + "nauc_map_at_1_std": -0.008806, + "nauc_map_at_1_diff1": 0.225104, + "nauc_map_at_3_max": 0.150318, + "nauc_map_at_3_std": -0.02965, + "nauc_map_at_3_diff1": 0.191134, + "nauc_map_at_5_max": 0.166058, + "nauc_map_at_5_std": 0.02073, + "nauc_map_at_5_diff1": 0.167786, + "nauc_map_at_10_max": 0.180744, + "nauc_map_at_10_std": 0.011676, + "nauc_map_at_10_diff1": 0.133342, + "nauc_map_at_20_max": 0.17878, + "nauc_map_at_20_std": 0.046939, + "nauc_map_at_20_diff1": 0.105472, + "nauc_map_at_100_max": 0.185024, + "nauc_map_at_100_std": 0.071299, + "nauc_map_at_100_diff1": 0.098684, + "nauc_map_at_1000_max": 0.186406, + "nauc_map_at_1000_std": 0.073977, + "nauc_map_at_1000_diff1": 0.100071, + "nauc_recall_at_1_max": 0.156957, + "nauc_recall_at_1_std": -0.008806, + "nauc_recall_at_1_diff1": 0.225104, + "nauc_recall_at_3_max": 0.111739, + "nauc_recall_at_3_std": -0.061882, + "nauc_recall_at_3_diff1": 0.157353, + "nauc_recall_at_5_max": 0.139011, + "nauc_recall_at_5_std": 0.057743, + "nauc_recall_at_5_diff1": 0.100563, + "nauc_recall_at_10_max": 0.152971, + "nauc_recall_at_10_std": 0.016017, + "nauc_recall_at_10_diff1": 0.002579, + "nauc_recall_at_20_max": 0.125749, + "nauc_recall_at_20_std": 0.155026, + "nauc_recall_at_20_diff1": -0.111651, + "nauc_recall_at_100_max": 0.14173, + "nauc_recall_at_100_std": 0.33964, + "nauc_recall_at_100_diff1": -0.13978, + "nauc_recall_at_1000_max": -0.085871, + "nauc_recall_at_1000_std": 0.702237, + "nauc_recall_at_1000_diff1": -0.105675, + "nauc_precision_at_1_max": 0.321138, + "nauc_precision_at_1_std": 0.172397, + "nauc_precision_at_1_diff1": 0.238424, + "nauc_precision_at_3_max": 0.291047, + "nauc_precision_at_3_std": 0.061389, + "nauc_precision_at_3_diff1": 0.124932, + "nauc_precision_at_5_max": 0.262828, + "nauc_precision_at_5_std": 0.183084, + "nauc_precision_at_5_diff1": 0.039833, + "nauc_precision_at_10_max": 0.265454, + "nauc_precision_at_10_std": 0.166222, + "nauc_precision_at_10_diff1": -0.005732, + "nauc_precision_at_20_max": 0.23123, + "nauc_precision_at_20_std": 0.311688, + "nauc_precision_at_20_diff1": -0.126086, + "nauc_precision_at_100_max": 0.166562, + "nauc_precision_at_100_std": 0.400221, + "nauc_precision_at_100_diff1": -0.106833, + "nauc_precision_at_1000_max": 0.142796, + "nauc_precision_at_1000_std": 0.385056, + "nauc_precision_at_1000_diff1": -0.082761, + "nauc_mrr_at_1_max": 0.321138, + "nauc_mrr_at_1_std": 0.172397, + "nauc_mrr_at_1_diff1": 0.238424, + "nauc_mrr_at_3_max": 0.272688, + "nauc_mrr_at_3_std": 0.070355, + "nauc_mrr_at_3_diff1": 0.189276, + "nauc_mrr_at_5_max": 0.272814, + "nauc_mrr_at_5_std": 0.111678, + "nauc_mrr_at_5_diff1": 0.170863, + "nauc_mrr_at_10_max": 0.280972, + "nauc_mrr_at_10_std": 0.118271, + "nauc_mrr_at_10_diff1": 0.153892, + "nauc_mrr_at_20_max": 0.282802, + "nauc_mrr_at_20_std": 0.127195, + "nauc_mrr_at_20_diff1": 0.151642, + "nauc_mrr_at_100_max": 0.283355, + "nauc_mrr_at_100_std": 0.128946, + "nauc_mrr_at_100_diff1": 0.153771, + "nauc_mrr_at_1000_max": 0.282575, + "nauc_mrr_at_1000_std": 0.127868, + "nauc_mrr_at_1000_diff1": 0.154288, + "main_score": 0.20994, + "hf_subset": "IIYi-Clinical", + "languages": [ + "eng-Latn" + ] + } + ] + }, + "evaluation_time": 864.0663409233093, + "kg_co2_emissions": null +} \ No newline at end of file diff --git a/results/Alibaba-NLP__gte-Qwen2-7B-instruct/e26182b2122f4435e8b3ebecbf363990f409b45b/R2MEDRetrieval.json b/results/Alibaba-NLP__gte-Qwen2-7B-instruct/e26182b2122f4435e8b3ebecbf363990f409b45b/R2MEDRetrieval.json new file mode 100644 index 0000000000..3e47054cc5 --- /dev/null +++ b/results/Alibaba-NLP__gte-Qwen2-7B-instruct/e26182b2122f4435e8b3ebecbf363990f409b45b/R2MEDRetrieval.json @@ -0,0 +1,1187 @@ +{ + "dataset_revision": "1.0", + "task_name": "R2MEDRetrieval", + "mteb_version": "1.38.20", + "scores": { + "test": [ + { + "ndcg_at_1": 0.29126, + "ndcg_at_3": 0.27222, + "ndcg_at_5": 0.28517, + "ndcg_at_10": 0.32486, + "ndcg_at_20": 0.35614, + "ndcg_at_100": 0.41235, + "ndcg_at_1000": 0.45707, + "map_at_1": 0.08073, + "map_at_3": 0.16355, + "map_at_5": 0.19036, + "map_at_10": 0.23006, + "map_at_20": 0.24787, + "map_at_100": 0.2615, + "map_at_1000": 0.26449, + "recall_at_1": 0.08073, + "recall_at_3": 0.20764, + "recall_at_5": 0.2739, + "recall_at_10": 0.38845, + "recall_at_20": 0.47871, + "recall_at_100": 0.68293, + "recall_at_1000": 0.9377, + "precision_at_1": 0.29126, + "precision_at_3": 0.23625, + "precision_at_5": 0.19806, + "precision_at_10": 0.14757, + "precision_at_20": 0.09126, + "precision_at_100": 0.0265, + "precision_at_1000": 0.00341, + "mrr_at_1": 0.291262, + "mrr_at_3": 0.368932, + "mrr_at_5": 0.38932, + "mrr_at_10": 0.401464, + "mrr_at_20": 0.404739, + "mrr_at_100": 0.408496, + "mrr_at_1000": 0.40924, + "nauc_ndcg_at_1_max": 0.004285, + "nauc_ndcg_at_1_std": -0.220535, + "nauc_ndcg_at_1_diff1": 0.243153, + "nauc_ndcg_at_3_max": 0.045553, + "nauc_ndcg_at_3_std": -0.202856, + "nauc_ndcg_at_3_diff1": 0.220974, + "nauc_ndcg_at_5_max": -0.018513, + "nauc_ndcg_at_5_std": -0.267436, + "nauc_ndcg_at_5_diff1": 0.159335, + "nauc_ndcg_at_10_max": -0.025205, + "nauc_ndcg_at_10_std": -0.262014, + "nauc_ndcg_at_10_diff1": 0.152402, + "nauc_ndcg_at_20_max": 0.008305, + "nauc_ndcg_at_20_std": -0.279721, + "nauc_ndcg_at_20_diff1": 0.179012, + "nauc_ndcg_at_100_max": 0.025958, + "nauc_ndcg_at_100_std": -0.251004, + "nauc_ndcg_at_100_diff1": 0.188444, + "nauc_ndcg_at_1000_max": 0.025489, + "nauc_ndcg_at_1000_std": -0.23271, + "nauc_ndcg_at_1000_diff1": 0.208479, + "nauc_map_at_1_max": 0.022707, + "nauc_map_at_1_std": -0.245351, + "nauc_map_at_1_diff1": 0.253544, + "nauc_map_at_3_max": 0.087283, + "nauc_map_at_3_std": -0.184908, + "nauc_map_at_3_diff1": 0.240926, + "nauc_map_at_5_max": 0.03752, + "nauc_map_at_5_std": -0.233254, + "nauc_map_at_5_diff1": 0.209463, + "nauc_map_at_10_max": 0.007386, + "nauc_map_at_10_std": -0.238277, + "nauc_map_at_10_diff1": 0.180392, + "nauc_map_at_20_max": 0.020936, + "nauc_map_at_20_std": -0.246176, + "nauc_map_at_20_diff1": 0.180474, + "nauc_map_at_100_max": 0.017892, + "nauc_map_at_100_std": -0.237917, + "nauc_map_at_100_diff1": 0.179801, + "nauc_map_at_1000_max": 0.018831, + "nauc_map_at_1000_std": -0.236746, + "nauc_map_at_1000_diff1": 0.181491, + "nauc_recall_at_1_max": 0.022707, + "nauc_recall_at_1_std": -0.245351, + "nauc_recall_at_1_diff1": 0.253544, + "nauc_recall_at_3_max": 0.137543, + "nauc_recall_at_3_std": -0.133623, + "nauc_recall_at_3_diff1": 0.216615, + "nauc_recall_at_5_max": 0.024664, + "nauc_recall_at_5_std": -0.244359, + "nauc_recall_at_5_diff1": 0.132398, + "nauc_recall_at_10_max": -0.046368, + "nauc_recall_at_10_std": -0.259144, + "nauc_recall_at_10_diff1": 0.10291, + "nauc_recall_at_20_max": 0.011437, + "nauc_recall_at_20_std": -0.292566, + "nauc_recall_at_20_diff1": 0.151191, + "nauc_recall_at_100_max": 0.093634, + "nauc_recall_at_100_std": -0.18881, + "nauc_recall_at_100_diff1": 0.173845, + "nauc_recall_at_1000_max": 0.21901, + "nauc_recall_at_1000_std": 0.449859, + "nauc_recall_at_1000_diff1": 0.436055, + "nauc_precision_at_1_max": 0.004285, + "nauc_precision_at_1_std": -0.220535, + "nauc_precision_at_1_diff1": 0.243153, + "nauc_precision_at_3_max": 0.009451, + "nauc_precision_at_3_std": -0.206797, + "nauc_precision_at_3_diff1": 0.217706, + "nauc_precision_at_5_max": -0.106356, + "nauc_precision_at_5_std": -0.277039, + "nauc_precision_at_5_diff1": 0.077509, + "nauc_precision_at_10_max": -0.124788, + "nauc_precision_at_10_std": -0.240486, + "nauc_precision_at_10_diff1": 0.036196, + "nauc_precision_at_20_max": -0.08483, + "nauc_precision_at_20_std": -0.242388, + "nauc_precision_at_20_diff1": 0.057685, + "nauc_precision_at_100_max": -0.060875, + "nauc_precision_at_100_std": -0.142691, + "nauc_precision_at_100_diff1": 0.049748, + "nauc_precision_at_1000_max": -0.078477, + "nauc_precision_at_1000_std": -0.062572, + "nauc_precision_at_1000_diff1": 0.063605, + "nauc_mrr_at_1_max": 0.004285, + "nauc_mrr_at_1_std": -0.220535, + "nauc_mrr_at_1_diff1": 0.243153, + "nauc_mrr_at_3_max": 0.043847, + "nauc_mrr_at_3_std": -0.231428, + "nauc_mrr_at_3_diff1": 0.218515, + "nauc_mrr_at_5_max": 0.013413, + "nauc_mrr_at_5_std": -0.251321, + "nauc_mrr_at_5_diff1": 0.19073, + "nauc_mrr_at_10_max": 0.008645, + "nauc_mrr_at_10_std": -0.254792, + "nauc_mrr_at_10_diff1": 0.191223, + "nauc_mrr_at_20_max": 0.012827, + "nauc_mrr_at_20_std": -0.256161, + "nauc_mrr_at_20_diff1": 0.196706, + "nauc_mrr_at_100_max": 0.016807, + "nauc_mrr_at_100_std": -0.253888, + "nauc_mrr_at_100_diff1": 0.201208, + "nauc_mrr_at_1000_max": 0.016583, + "nauc_mrr_at_1000_std": -0.253944, + "nauc_mrr_at_1000_diff1": 0.201391, + "main_score": 0.32486, + "hf_subset": "Biology", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.36364, + "ndcg_at_3": 0.39728, + "ndcg_at_5": 0.42402, + "ndcg_at_10": 0.45788, + "ndcg_at_20": 0.50211, + "ndcg_at_100": 0.54999, + "ndcg_at_1000": 0.57107, + "map_at_1": 0.19504, + "map_at_3": 0.30169, + "map_at_5": 0.33774, + "map_at_10": 0.3691, + "map_at_20": 0.39062, + "map_at_100": 0.40535, + "map_at_1000": 0.40677, + "recall_at_1": 0.19504, + "recall_at_3": 0.37613, + "recall_at_5": 0.4742, + "recall_at_10": 0.56396, + "recall_at_20": 0.68211, + "recall_at_100": 0.85351, + "recall_at_1000": 0.98268, + "precision_at_1": 0.36364, + "precision_at_3": 0.27706, + "precision_at_5": 0.22338, + "precision_at_10": 0.15195, + "precision_at_20": 0.09805, + "precision_at_100": 0.02584, + "precision_at_1000": 0.00292, + "mrr_at_1": 0.363636, + "mrr_at_3": 0.448052, + "mrr_at_5": 0.47987, + "mrr_at_10": 0.488812, + "mrr_at_20": 0.492912, + "mrr_at_100": 0.495222, + "mrr_at_1000": 0.495731, + "nauc_ndcg_at_1_max": 0.028214, + "nauc_ndcg_at_1_std": -0.228813, + "nauc_ndcg_at_1_diff1": 0.104356, + "nauc_ndcg_at_3_max": 0.039414, + "nauc_ndcg_at_3_std": -0.252415, + "nauc_ndcg_at_3_diff1": 0.086785, + "nauc_ndcg_at_5_max": 0.050308, + "nauc_ndcg_at_5_std": -0.289127, + "nauc_ndcg_at_5_diff1": 0.088865, + "nauc_ndcg_at_10_max": 0.117327, + "nauc_ndcg_at_10_std": -0.233677, + "nauc_ndcg_at_10_diff1": 0.103755, + "nauc_ndcg_at_20_max": 0.149819, + "nauc_ndcg_at_20_std": -0.17115, + "nauc_ndcg_at_20_diff1": 0.101112, + "nauc_ndcg_at_100_max": 0.135256, + "nauc_ndcg_at_100_std": -0.140985, + "nauc_ndcg_at_100_diff1": 0.05535, + "nauc_ndcg_at_1000_max": 0.144625, + "nauc_ndcg_at_1000_std": -0.144565, + "nauc_ndcg_at_1000_diff1": 0.069304, + "nauc_map_at_1_max": -0.078693, + "nauc_map_at_1_std": -0.272647, + "nauc_map_at_1_diff1": 0.163515, + "nauc_map_at_3_max": 0.019044, + "nauc_map_at_3_std": -0.3082, + "nauc_map_at_3_diff1": 0.172194, + "nauc_map_at_5_max": 0.034913, + "nauc_map_at_5_std": -0.323475, + "nauc_map_at_5_diff1": 0.157729, + "nauc_map_at_10_max": 0.069185, + "nauc_map_at_10_std": -0.281211, + "nauc_map_at_10_diff1": 0.145572, + "nauc_map_at_20_max": 0.091616, + "nauc_map_at_20_std": -0.250217, + "nauc_map_at_20_diff1": 0.145967, + "nauc_map_at_100_max": 0.087844, + "nauc_map_at_100_std": -0.237021, + "nauc_map_at_100_diff1": 0.13399, + "nauc_map_at_1000_max": 0.088943, + "nauc_map_at_1000_std": -0.236409, + "nauc_map_at_1000_diff1": 0.134581, + "nauc_recall_at_1_max": -0.078693, + "nauc_recall_at_1_std": -0.272647, + "nauc_recall_at_1_diff1": 0.163515, + "nauc_recall_at_3_max": 0.016496, + "nauc_recall_at_3_std": -0.27221, + "nauc_recall_at_3_diff1": 0.108311, + "nauc_recall_at_5_max": 0.044705, + "nauc_recall_at_5_std": -0.30704, + "nauc_recall_at_5_diff1": 0.050417, + "nauc_recall_at_10_max": 0.160439, + "nauc_recall_at_10_std": -0.202835, + "nauc_recall_at_10_diff1": 0.049183, + "nauc_recall_at_20_max": 0.222986, + "nauc_recall_at_20_std": -0.05128, + "nauc_recall_at_20_diff1": 0.038483, + "nauc_recall_at_100_max": 0.227669, + "nauc_recall_at_100_std": 0.150757, + "nauc_recall_at_100_diff1": -0.236995, + "nauc_recall_at_1000_max": 0.500307, + "nauc_recall_at_1000_std": 0.250861, + "nauc_recall_at_1000_diff1": -0.711424, + "nauc_precision_at_1_max": 0.028214, + "nauc_precision_at_1_std": -0.228813, + "nauc_precision_at_1_diff1": 0.104356, + "nauc_precision_at_3_max": 0.193261, + "nauc_precision_at_3_std": -0.147368, + "nauc_precision_at_3_diff1": 0.008356, + "nauc_precision_at_5_max": 0.204852, + "nauc_precision_at_5_std": -0.090823, + "nauc_precision_at_5_diff1": -0.029516, + "nauc_precision_at_10_max": 0.260216, + "nauc_precision_at_10_std": 0.102081, + "nauc_precision_at_10_diff1": -0.027121, + "nauc_precision_at_20_max": 0.295144, + "nauc_precision_at_20_std": 0.27436, + "nauc_precision_at_20_diff1": -0.058562, + "nauc_precision_at_100_max": 0.178814, + "nauc_precision_at_100_std": 0.311864, + "nauc_precision_at_100_diff1": -0.162876, + "nauc_precision_at_1000_max": 0.231552, + "nauc_precision_at_1000_std": 0.38846, + "nauc_precision_at_1000_diff1": -0.169405, + "nauc_mrr_at_1_max": 0.028214, + "nauc_mrr_at_1_std": -0.228813, + "nauc_mrr_at_1_diff1": 0.104356, + "nauc_mrr_at_3_max": 0.060894, + "nauc_mrr_at_3_std": -0.213818, + "nauc_mrr_at_3_diff1": 0.046193, + "nauc_mrr_at_5_max": 0.067695, + "nauc_mrr_at_5_std": -0.204391, + "nauc_mrr_at_5_diff1": 0.03359, + "nauc_mrr_at_10_max": 0.078398, + "nauc_mrr_at_10_std": -0.192421, + "nauc_mrr_at_10_diff1": 0.043189, + "nauc_mrr_at_20_max": 0.075896, + "nauc_mrr_at_20_std": -0.186049, + "nauc_mrr_at_20_diff1": 0.044407, + "nauc_mrr_at_100_max": 0.073781, + "nauc_mrr_at_100_std": -0.18728, + "nauc_mrr_at_100_diff1": 0.042473, + "nauc_mrr_at_1000_max": 0.073774, + "nauc_mrr_at_1000_std": -0.187747, + "nauc_mrr_at_1000_diff1": 0.043216, + "main_score": 0.45788, + "hf_subset": "Bioinformatics", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.38636, + "ndcg_at_3": 0.42637, + "ndcg_at_5": 0.45282, + "ndcg_at_10": 0.50489, + "ndcg_at_20": 0.53824, + "ndcg_at_100": 0.58444, + "ndcg_at_1000": 0.60018, + "map_at_1": 0.23732, + "map_at_3": 0.34119, + "map_at_5": 0.37312, + "map_at_10": 0.40827, + "map_at_20": 0.42491, + "map_at_100": 0.43575, + "map_at_1000": 0.43684, + "recall_at_1": 0.23732, + "recall_at_3": 0.41833, + "recall_at_5": 0.50407, + "recall_at_10": 0.63845, + "recall_at_20": 0.72385, + "recall_at_100": 0.90273, + "recall_at_1000": 0.99242, + "precision_at_1": 0.38636, + "precision_at_3": 0.27652, + "precision_at_5": 0.21591, + "precision_at_10": 0.14773, + "precision_at_20": 0.09205, + "precision_at_100": 0.02443, + "precision_at_1000": 0.00275, + "mrr_at_1": 0.386364, + "mrr_at_3": 0.494318, + "mrr_at_5": 0.515341, + "mrr_at_10": 0.53254, + "mrr_at_20": 0.53474, + "mrr_at_100": 0.536756, + "mrr_at_1000": 0.536904, + "nauc_ndcg_at_1_max": 0.348351, + "nauc_ndcg_at_1_std": -0.002898, + "nauc_ndcg_at_1_diff1": 0.323335, + "nauc_ndcg_at_3_max": 0.289542, + "nauc_ndcg_at_3_std": -0.083635, + "nauc_ndcg_at_3_diff1": 0.286789, + "nauc_ndcg_at_5_max": 0.266187, + "nauc_ndcg_at_5_std": -0.124379, + "nauc_ndcg_at_5_diff1": 0.319646, + "nauc_ndcg_at_10_max": 0.290548, + "nauc_ndcg_at_10_std": -0.104636, + "nauc_ndcg_at_10_diff1": 0.337538, + "nauc_ndcg_at_20_max": 0.301292, + "nauc_ndcg_at_20_std": -0.100836, + "nauc_ndcg_at_20_diff1": 0.342397, + "nauc_ndcg_at_100_max": 0.324137, + "nauc_ndcg_at_100_std": -0.042676, + "nauc_ndcg_at_100_diff1": 0.340228, + "nauc_ndcg_at_1000_max": 0.325187, + "nauc_ndcg_at_1000_std": -0.045616, + "nauc_ndcg_at_1000_diff1": 0.339655, + "nauc_map_at_1_max": 0.138556, + "nauc_map_at_1_std": -0.196758, + "nauc_map_at_1_diff1": 0.401541, + "nauc_map_at_3_max": 0.244836, + "nauc_map_at_3_std": -0.121889, + "nauc_map_at_3_diff1": 0.332229, + "nauc_map_at_5_max": 0.242088, + "nauc_map_at_5_std": -0.134354, + "nauc_map_at_5_diff1": 0.341673, + "nauc_map_at_10_max": 0.253773, + "nauc_map_at_10_std": -0.125555, + "nauc_map_at_10_diff1": 0.347794, + "nauc_map_at_20_max": 0.258154, + "nauc_map_at_20_std": -0.126971, + "nauc_map_at_20_diff1": 0.348199, + "nauc_map_at_100_max": 0.267048, + "nauc_map_at_100_std": -0.111295, + "nauc_map_at_100_diff1": 0.349731, + "nauc_map_at_1000_max": 0.267285, + "nauc_map_at_1000_std": -0.111316, + "nauc_map_at_1000_diff1": 0.349936, + "nauc_recall_at_1_max": 0.138556, + "nauc_recall_at_1_std": -0.196758, + "nauc_recall_at_1_diff1": 0.401541, + "nauc_recall_at_3_max": 0.225271, + "nauc_recall_at_3_std": -0.129475, + "nauc_recall_at_3_diff1": 0.247682, + "nauc_recall_at_5_max": 0.213948, + "nauc_recall_at_5_std": -0.158022, + "nauc_recall_at_5_diff1": 0.283013, + "nauc_recall_at_10_max": 0.227271, + "nauc_recall_at_10_std": -0.147672, + "nauc_recall_at_10_diff1": 0.285309, + "nauc_recall_at_20_max": 0.254483, + "nauc_recall_at_20_std": -0.15851, + "nauc_recall_at_20_diff1": 0.297771, + "nauc_recall_at_100_max": 0.351926, + "nauc_recall_at_100_std": 0.092916, + "nauc_recall_at_100_diff1": 0.353585, + "nauc_recall_at_1000_max": 0.795001, + "nauc_recall_at_1000_std": 0.561718, + "nauc_recall_at_1000_diff1": 1.0, + "nauc_precision_at_1_max": 0.348351, + "nauc_precision_at_1_std": -0.002898, + "nauc_precision_at_1_diff1": 0.323335, + "nauc_precision_at_3_max": 0.387267, + "nauc_precision_at_3_std": 0.128232, + "nauc_precision_at_3_diff1": 0.069033, + "nauc_precision_at_5_max": 0.316255, + "nauc_precision_at_5_std": 0.094419, + "nauc_precision_at_5_diff1": 0.05541, + "nauc_precision_at_10_max": 0.30517, + "nauc_precision_at_10_std": 0.171075, + "nauc_precision_at_10_diff1": 0.047603, + "nauc_precision_at_20_max": 0.254509, + "nauc_precision_at_20_std": 0.16714, + "nauc_precision_at_20_diff1": 0.02674, + "nauc_precision_at_100_max": 0.211004, + "nauc_precision_at_100_std": 0.333744, + "nauc_precision_at_100_diff1": -0.09332, + "nauc_precision_at_1000_max": 0.162798, + "nauc_precision_at_1000_std": 0.316664, + "nauc_precision_at_1000_diff1": -0.135917, + "nauc_mrr_at_1_max": 0.348351, + "nauc_mrr_at_1_std": -0.002898, + "nauc_mrr_at_1_diff1": 0.323335, + "nauc_mrr_at_3_max": 0.361668, + "nauc_mrr_at_3_std": -0.011794, + "nauc_mrr_at_3_diff1": 0.29549, + "nauc_mrr_at_5_max": 0.364567, + "nauc_mrr_at_5_std": -0.021985, + "nauc_mrr_at_5_diff1": 0.312262, + "nauc_mrr_at_10_max": 0.369875, + "nauc_mrr_at_10_std": -0.015112, + "nauc_mrr_at_10_diff1": 0.313267, + "nauc_mrr_at_20_max": 0.366319, + "nauc_mrr_at_20_std": -0.016935, + "nauc_mrr_at_20_diff1": 0.312965, + "nauc_mrr_at_100_max": 0.365746, + "nauc_mrr_at_100_std": -0.014231, + "nauc_mrr_at_100_diff1": 0.312929, + "nauc_mrr_at_1000_max": 0.365592, + "nauc_mrr_at_1000_std": -0.014578, + "nauc_mrr_at_1000_diff1": 0.312746, + "main_score": 0.50489, + "hf_subset": "Medical-Sciences", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.12371, + "ndcg_at_3": 0.11247, + "ndcg_at_5": 0.1184, + "ndcg_at_10": 0.1337, + "ndcg_at_20": 0.15463, + "ndcg_at_100": 0.20126, + "ndcg_at_1000": 0.26506, + "map_at_1": 0.05895, + "map_at_3": 0.07879, + "map_at_5": 0.08507, + "map_at_10": 0.09387, + "map_at_20": 0.10014, + "map_at_100": 0.10766, + "map_at_1000": 0.11095, + "recall_at_1": 0.05895, + "recall_at_3": 0.10731, + "recall_at_5": 0.13198, + "recall_at_10": 0.17401, + "recall_at_20": 0.23382, + "recall_at_100": 0.42547, + "recall_at_1000": 0.7975, + "precision_at_1": 0.12371, + "precision_at_3": 0.0756, + "precision_at_5": 0.06186, + "precision_at_10": 0.04227, + "precision_at_20": 0.03041, + "precision_at_100": 0.01165, + "precision_at_1000": 0.00233, + "mrr_at_1": 0.123711, + "mrr_at_3": 0.149485, + "mrr_at_5": 0.162371, + "mrr_at_10": 0.170602, + "mrr_at_20": 0.177108, + "mrr_at_100": 0.182009, + "mrr_at_1000": 0.183428, + "nauc_ndcg_at_1_max": -0.000592, + "nauc_ndcg_at_1_std": -0.044585, + "nauc_ndcg_at_1_diff1": 0.037102, + "nauc_ndcg_at_3_max": 0.053644, + "nauc_ndcg_at_3_std": -0.036761, + "nauc_ndcg_at_3_diff1": 0.159608, + "nauc_ndcg_at_5_max": 0.015593, + "nauc_ndcg_at_5_std": -0.054206, + "nauc_ndcg_at_5_diff1": 0.127018, + "nauc_ndcg_at_10_max": -0.008751, + "nauc_ndcg_at_10_std": -0.056299, + "nauc_ndcg_at_10_diff1": 0.088534, + "nauc_ndcg_at_20_max": 0.034168, + "nauc_ndcg_at_20_std": 0.01201, + "nauc_ndcg_at_20_diff1": 0.068606, + "nauc_ndcg_at_100_max": 0.028857, + "nauc_ndcg_at_100_std": 0.026862, + "nauc_ndcg_at_100_diff1": 0.035501, + "nauc_ndcg_at_1000_max": 0.031267, + "nauc_ndcg_at_1000_std": 0.026604, + "nauc_ndcg_at_1000_diff1": 0.033888, + "nauc_map_at_1_max": -0.056227, + "nauc_map_at_1_std": -0.148536, + "nauc_map_at_1_diff1": 0.139526, + "nauc_map_at_3_max": 0.006578, + "nauc_map_at_3_std": -0.095599, + "nauc_map_at_3_diff1": 0.168032, + "nauc_map_at_5_max": 0.005809, + "nauc_map_at_5_std": -0.079268, + "nauc_map_at_5_diff1": 0.155526, + "nauc_map_at_10_max": -0.021878, + "nauc_map_at_10_std": -0.086645, + "nauc_map_at_10_diff1": 0.112848, + "nauc_map_at_20_max": -0.007872, + "nauc_map_at_20_std": -0.061509, + "nauc_map_at_20_diff1": 0.102537, + "nauc_map_at_100_max": -0.008809, + "nauc_map_at_100_std": -0.053762, + "nauc_map_at_100_diff1": 0.092397, + "nauc_map_at_1000_max": -0.007025, + "nauc_map_at_1000_std": -0.052651, + "nauc_map_at_1000_diff1": 0.091632, + "nauc_recall_at_1_max": -0.056227, + "nauc_recall_at_1_std": -0.148536, + "nauc_recall_at_1_diff1": 0.139526, + "nauc_recall_at_3_max": 0.053942, + "nauc_recall_at_3_std": -0.067138, + "nauc_recall_at_3_diff1": 0.189852, + "nauc_recall_at_5_max": 0.025037, + "nauc_recall_at_5_std": -0.046944, + "nauc_recall_at_5_diff1": 0.154622, + "nauc_recall_at_10_max": -0.029944, + "nauc_recall_at_10_std": -0.047831, + "nauc_recall_at_10_diff1": 0.066207, + "nauc_recall_at_20_max": 0.077494, + "nauc_recall_at_20_std": 0.099858, + "nauc_recall_at_20_diff1": 0.040352, + "nauc_recall_at_100_max": 0.077612, + "nauc_recall_at_100_std": 0.153704, + "nauc_recall_at_100_diff1": -0.032411, + "nauc_recall_at_1000_max": 0.137351, + "nauc_recall_at_1000_std": 0.276576, + "nauc_recall_at_1000_diff1": -0.108409, + "nauc_precision_at_1_max": -0.000592, + "nauc_precision_at_1_std": -0.044585, + "nauc_precision_at_1_diff1": 0.037102, + "nauc_precision_at_3_max": 0.113739, + "nauc_precision_at_3_std": 0.024855, + "nauc_precision_at_3_diff1": 0.154668, + "nauc_precision_at_5_max": 0.066282, + "nauc_precision_at_5_std": 0.034503, + "nauc_precision_at_5_diff1": 0.085211, + "nauc_precision_at_10_max": 0.020334, + "nauc_precision_at_10_std": 0.017655, + "nauc_precision_at_10_diff1": 0.000456, + "nauc_precision_at_20_max": 0.12522, + "nauc_precision_at_20_std": 0.187427, + "nauc_precision_at_20_diff1": -0.043615, + "nauc_precision_at_100_max": 0.060097, + "nauc_precision_at_100_std": 0.126306, + "nauc_precision_at_100_diff1": -0.111168, + "nauc_precision_at_1000_max": -0.009726, + "nauc_precision_at_1000_std": 0.05078, + "nauc_precision_at_1000_diff1": -0.063205, + "nauc_mrr_at_1_max": -0.000592, + "nauc_mrr_at_1_std": -0.044585, + "nauc_mrr_at_1_diff1": 0.037102, + "nauc_mrr_at_3_max": 0.044218, + "nauc_mrr_at_3_std": -0.027566, + "nauc_mrr_at_3_diff1": 0.092643, + "nauc_mrr_at_5_max": 0.024133, + "nauc_mrr_at_5_std": -0.037058, + "nauc_mrr_at_5_diff1": 0.077716, + "nauc_mrr_at_10_max": 0.021694, + "nauc_mrr_at_10_std": -0.033552, + "nauc_mrr_at_10_diff1": 0.072161, + "nauc_mrr_at_20_max": 0.02915, + "nauc_mrr_at_20_std": -0.016081, + "nauc_mrr_at_20_diff1": 0.061743, + "nauc_mrr_at_100_max": 0.02544, + "nauc_mrr_at_100_std": -0.020074, + "nauc_mrr_at_100_diff1": 0.059762, + "nauc_mrr_at_1000_max": 0.026001, + "nauc_mrr_at_1000_std": -0.020013, + "nauc_mrr_at_1000_diff1": 0.059678, + "main_score": 0.1337, + "hf_subset": "MedXpertQA-Exam", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.15254, + "ndcg_at_3": 0.14106, + "ndcg_at_5": 0.14199, + "ndcg_at_10": 0.18675, + "ndcg_at_20": 0.22052, + "ndcg_at_100": 0.27274, + "ndcg_at_1000": 0.33209, + "map_at_1": 0.04712, + "map_at_3": 0.07796, + "map_at_5": 0.09, + "map_at_10": 0.11766, + "map_at_20": 0.13082, + "map_at_100": 0.14086, + "map_at_1000": 0.14453, + "recall_at_1": 0.04712, + "recall_at_3": 0.09821, + "recall_at_5": 0.13559, + "recall_at_10": 0.24405, + "recall_at_20": 0.3299, + "recall_at_100": 0.51631, + "recall_at_1000": 0.81491, + "precision_at_1": 0.15254, + "precision_at_3": 0.12147, + "precision_at_5": 0.09831, + "precision_at_10": 0.09153, + "precision_at_20": 0.06441, + "precision_at_100": 0.02085, + "precision_at_1000": 0.00351, + "mrr_at_1": 0.152542, + "mrr_at_3": 0.214689, + "mrr_at_5": 0.232062, + "mrr_at_10": 0.250858, + "mrr_at_20": 0.257594, + "mrr_at_100": 0.262373, + "mrr_at_1000": 0.26317, + "nauc_ndcg_at_1_max": 0.249214, + "nauc_ndcg_at_1_std": -0.064296, + "nauc_ndcg_at_1_diff1": 0.153223, + "nauc_ndcg_at_3_max": 0.290835, + "nauc_ndcg_at_3_std": 0.015364, + "nauc_ndcg_at_3_diff1": 0.162022, + "nauc_ndcg_at_5_max": 0.266752, + "nauc_ndcg_at_5_std": 0.005782, + "nauc_ndcg_at_5_diff1": 0.137803, + "nauc_ndcg_at_10_max": 0.281702, + "nauc_ndcg_at_10_std": 0.070391, + "nauc_ndcg_at_10_diff1": 0.16905, + "nauc_ndcg_at_20_max": 0.281801, + "nauc_ndcg_at_20_std": 0.105867, + "nauc_ndcg_at_20_diff1": 0.166803, + "nauc_ndcg_at_100_max": 0.273037, + "nauc_ndcg_at_100_std": 0.113015, + "nauc_ndcg_at_100_diff1": 0.177517, + "nauc_ndcg_at_1000_max": 0.263129, + "nauc_ndcg_at_1000_std": 0.094248, + "nauc_ndcg_at_1000_diff1": 0.194987, + "nauc_map_at_1_max": 0.21887, + "nauc_map_at_1_std": -0.098059, + "nauc_map_at_1_diff1": 0.209216, + "nauc_map_at_3_max": 0.341197, + "nauc_map_at_3_std": 0.01663, + "nauc_map_at_3_diff1": 0.174463, + "nauc_map_at_5_max": 0.313497, + "nauc_map_at_5_std": 0.014447, + "nauc_map_at_5_diff1": 0.147676, + "nauc_map_at_10_max": 0.317491, + "nauc_map_at_10_std": 0.057702, + "nauc_map_at_10_diff1": 0.172451, + "nauc_map_at_20_max": 0.314578, + "nauc_map_at_20_std": 0.08349, + "nauc_map_at_20_diff1": 0.165265, + "nauc_map_at_100_max": 0.308794, + "nauc_map_at_100_std": 0.091332, + "nauc_map_at_100_diff1": 0.173852, + "nauc_map_at_1000_max": 0.309113, + "nauc_map_at_1000_std": 0.09144, + "nauc_map_at_1000_diff1": 0.176457, + "nauc_recall_at_1_max": 0.21887, + "nauc_recall_at_1_std": -0.098059, + "nauc_recall_at_1_diff1": 0.209216, + "nauc_recall_at_3_max": 0.333991, + "nauc_recall_at_3_std": 0.031597, + "nauc_recall_at_3_diff1": 0.162644, + "nauc_recall_at_5_max": 0.287871, + "nauc_recall_at_5_std": 0.028378, + "nauc_recall_at_5_diff1": 0.098067, + "nauc_recall_at_10_max": 0.280713, + "nauc_recall_at_10_std": 0.129099, + "nauc_recall_at_10_diff1": 0.121225, + "nauc_recall_at_20_max": 0.265371, + "nauc_recall_at_20_std": 0.185974, + "nauc_recall_at_20_diff1": 0.11183, + "nauc_recall_at_100_max": 0.240164, + "nauc_recall_at_100_std": 0.199819, + "nauc_recall_at_100_diff1": 0.121075, + "nauc_recall_at_1000_max": 0.277738, + "nauc_recall_at_1000_std": 0.290875, + "nauc_recall_at_1000_diff1": 0.214622, + "nauc_precision_at_1_max": 0.249214, + "nauc_precision_at_1_std": -0.064296, + "nauc_precision_at_1_diff1": 0.153223, + "nauc_precision_at_3_max": 0.306562, + "nauc_precision_at_3_std": 0.0592, + "nauc_precision_at_3_diff1": 0.116782, + "nauc_precision_at_5_max": 0.225649, + "nauc_precision_at_5_std": 0.046978, + "nauc_precision_at_5_diff1": 0.084644, + "nauc_precision_at_10_max": 0.161694, + "nauc_precision_at_10_std": 0.098964, + "nauc_precision_at_10_diff1": 0.177963, + "nauc_precision_at_20_max": 0.155507, + "nauc_precision_at_20_std": 0.146792, + "nauc_precision_at_20_diff1": 0.166215, + "nauc_precision_at_100_max": 0.091474, + "nauc_precision_at_100_std": 0.114401, + "nauc_precision_at_100_diff1": 0.160624, + "nauc_precision_at_1000_max": -0.067698, + "nauc_precision_at_1000_std": -0.051945, + "nauc_precision_at_1000_diff1": 0.142242, + "nauc_mrr_at_1_max": 0.249214, + "nauc_mrr_at_1_std": -0.064296, + "nauc_mrr_at_1_diff1": 0.153223, + "nauc_mrr_at_3_max": 0.234356, + "nauc_mrr_at_3_std": -0.02875, + "nauc_mrr_at_3_diff1": 0.16139, + "nauc_mrr_at_5_max": 0.221941, + "nauc_mrr_at_5_std": -0.024559, + "nauc_mrr_at_5_diff1": 0.167868, + "nauc_mrr_at_10_max": 0.219701, + "nauc_mrr_at_10_std": -0.01552, + "nauc_mrr_at_10_diff1": 0.166065, + "nauc_mrr_at_20_max": 0.221073, + "nauc_mrr_at_20_std": -0.016848, + "nauc_mrr_at_20_diff1": 0.169597, + "nauc_mrr_at_100_max": 0.219841, + "nauc_mrr_at_100_std": -0.019754, + "nauc_mrr_at_100_diff1": 0.169601, + "nauc_mrr_at_1000_max": 0.220565, + "nauc_mrr_at_1000_std": -0.019087, + "nauc_mrr_at_1000_diff1": 0.169223, + "main_score": 0.18675, + "hf_subset": "MedQA-Diag", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.49333, + "ndcg_at_3": 0.44787, + "ndcg_at_5": 0.46872, + "ndcg_at_10": 0.49597, + "ndcg_at_20": 0.51506, + "ndcg_at_100": 0.54863, + "ndcg_at_1000": 0.57265, + "map_at_1": 0.29811, + "map_at_3": 0.38269, + "map_at_5": 0.4078, + "map_at_10": 0.42492, + "map_at_20": 0.43298, + "map_at_100": 0.43916, + "map_at_1000": 0.44034, + "recall_at_1": 0.29811, + "recall_at_3": 0.419, + "recall_at_5": 0.49811, + "recall_at_10": 0.56078, + "recall_at_20": 0.61967, + "recall_at_100": 0.77267, + "recall_at_1000": 0.93011, + "precision_at_1": 0.49333, + "precision_at_3": 0.26, + "precision_at_5": 0.192, + "precision_at_10": 0.11267, + "precision_at_20": 0.06367, + "precision_at_100": 0.01587, + "precision_at_1000": 0.00195, + "mrr_at_1": 0.493333, + "mrr_at_3": 0.538889, + "mrr_at_5": 0.559556, + "mrr_at_10": 0.564019, + "mrr_at_20": 0.566709, + "mrr_at_100": 0.569308, + "mrr_at_1000": 0.569683, + "nauc_ndcg_at_1_max": 0.529502, + "nauc_ndcg_at_1_std": 0.057312, + "nauc_ndcg_at_1_diff1": 0.498901, + "nauc_ndcg_at_3_max": 0.404724, + "nauc_ndcg_at_3_std": -0.000342, + "nauc_ndcg_at_3_diff1": 0.400314, + "nauc_ndcg_at_5_max": 0.404798, + "nauc_ndcg_at_5_std": 0.039355, + "nauc_ndcg_at_5_diff1": 0.395215, + "nauc_ndcg_at_10_max": 0.420502, + "nauc_ndcg_at_10_std": 0.062635, + "nauc_ndcg_at_10_diff1": 0.378775, + "nauc_ndcg_at_20_max": 0.414957, + "nauc_ndcg_at_20_std": 0.077154, + "nauc_ndcg_at_20_diff1": 0.368994, + "nauc_ndcg_at_100_max": 0.411589, + "nauc_ndcg_at_100_std": 0.078058, + "nauc_ndcg_at_100_diff1": 0.383741, + "nauc_ndcg_at_1000_max": 0.435178, + "nauc_ndcg_at_1000_std": 0.072354, + "nauc_ndcg_at_1000_diff1": 0.391827, + "nauc_map_at_1_max": 0.239611, + "nauc_map_at_1_std": -0.046728, + "nauc_map_at_1_diff1": 0.3568, + "nauc_map_at_3_max": 0.313319, + "nauc_map_at_3_std": -0.036642, + "nauc_map_at_3_diff1": 0.364407, + "nauc_map_at_5_max": 0.345338, + "nauc_map_at_5_std": -0.005832, + "nauc_map_at_5_diff1": 0.380423, + "nauc_map_at_10_max": 0.361405, + "nauc_map_at_10_std": 0.012142, + "nauc_map_at_10_diff1": 0.372684, + "nauc_map_at_20_max": 0.363454, + "nauc_map_at_20_std": 0.020483, + "nauc_map_at_20_diff1": 0.370649, + "nauc_map_at_100_max": 0.364993, + "nauc_map_at_100_std": 0.022997, + "nauc_map_at_100_diff1": 0.37315, + "nauc_map_at_1000_max": 0.366556, + "nauc_map_at_1000_std": 0.023095, + "nauc_map_at_1000_diff1": 0.373426, + "nauc_recall_at_1_max": 0.239611, + "nauc_recall_at_1_std": -0.046728, + "nauc_recall_at_1_diff1": 0.3568, + "nauc_recall_at_3_max": 0.272358, + "nauc_recall_at_3_std": -0.0393, + "nauc_recall_at_3_diff1": 0.329187, + "nauc_recall_at_5_max": 0.329841, + "nauc_recall_at_5_std": 0.070001, + "nauc_recall_at_5_diff1": 0.307219, + "nauc_recall_at_10_max": 0.343772, + "nauc_recall_at_10_std": 0.113328, + "nauc_recall_at_10_diff1": 0.256151, + "nauc_recall_at_20_max": 0.308334, + "nauc_recall_at_20_std": 0.155832, + "nauc_recall_at_20_diff1": 0.211467, + "nauc_recall_at_100_max": 0.188737, + "nauc_recall_at_100_std": 0.158065, + "nauc_recall_at_100_diff1": 0.222962, + "nauc_recall_at_1000_max": 0.394445, + "nauc_recall_at_1000_std": 0.112978, + "nauc_recall_at_1000_diff1": 0.202796, + "nauc_precision_at_1_max": 0.529502, + "nauc_precision_at_1_std": 0.057312, + "nauc_precision_at_1_diff1": 0.498901, + "nauc_precision_at_3_max": 0.520909, + "nauc_precision_at_3_std": 0.083146, + "nauc_precision_at_3_diff1": 0.356218, + "nauc_precision_at_5_max": 0.573145, + "nauc_precision_at_5_std": 0.209481, + "nauc_precision_at_5_diff1": 0.327623, + "nauc_precision_at_10_max": 0.517453, + "nauc_precision_at_10_std": 0.244795, + "nauc_precision_at_10_diff1": 0.21701, + "nauc_precision_at_20_max": 0.46, + "nauc_precision_at_20_std": 0.26205, + "nauc_precision_at_20_diff1": 0.165212, + "nauc_precision_at_100_max": 0.373389, + "nauc_precision_at_100_std": 0.248601, + "nauc_precision_at_100_diff1": 0.137264, + "nauc_precision_at_1000_max": 0.371579, + "nauc_precision_at_1000_std": 0.214211, + "nauc_precision_at_1000_diff1": 0.092819, + "nauc_mrr_at_1_max": 0.529502, + "nauc_mrr_at_1_std": 0.057312, + "nauc_mrr_at_1_diff1": 0.498901, + "nauc_mrr_at_3_max": 0.536468, + "nauc_mrr_at_3_std": 0.037189, + "nauc_mrr_at_3_diff1": 0.50559, + "nauc_mrr_at_5_max": 0.549772, + "nauc_mrr_at_5_std": 0.075563, + "nauc_mrr_at_5_diff1": 0.489102, + "nauc_mrr_at_10_max": 0.545956, + "nauc_mrr_at_10_std": 0.074083, + "nauc_mrr_at_10_diff1": 0.485282, + "nauc_mrr_at_20_max": 0.543875, + "nauc_mrr_at_20_std": 0.074758, + "nauc_mrr_at_20_diff1": 0.483898, + "nauc_mrr_at_100_max": 0.54219, + "nauc_mrr_at_100_std": 0.073988, + "nauc_mrr_at_100_diff1": 0.48428, + "nauc_mrr_at_1000_max": 0.542333, + "nauc_mrr_at_1000_std": 0.073753, + "nauc_mrr_at_1000_diff1": 0.484294, + "main_score": 0.49597, + "hf_subset": "PMC-Treatment", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.2193, + "ndcg_at_3": 0.20928, + "ndcg_at_5": 0.2329, + "ndcg_at_10": 0.27523, + "ndcg_at_20": 0.30598, + "ndcg_at_100": 0.35584, + "ndcg_at_1000": 0.39204, + "map_at_1": 0.11257, + "map_at_3": 0.16849, + "map_at_5": 0.18417, + "map_at_10": 0.20429, + "map_at_20": 0.21381, + "map_at_100": 0.22242, + "map_at_1000": 0.22438, + "recall_at_1": 0.11257, + "recall_at_3": 0.21637, + "recall_at_5": 0.26754, + "recall_at_10": 0.375, + "recall_at_20": 0.47515, + "recall_at_100": 0.69371, + "recall_at_1000": 0.9269, + "precision_at_1": 0.2193, + "precision_at_3": 0.14327, + "precision_at_5": 0.11053, + "precision_at_10": 0.07807, + "precision_at_20": 0.04912, + "precision_at_100": 0.01482, + "precision_at_1000": 0.00198, + "mrr_at_1": 0.219298, + "mrr_at_3": 0.276316, + "mrr_at_5": 0.29386, + "mrr_at_10": 0.310815, + "mrr_at_20": 0.318633, + "mrr_at_100": 0.322745, + "mrr_at_1000": 0.323345, + "nauc_ndcg_at_1_max": 0.267365, + "nauc_ndcg_at_1_std": 0.067935, + "nauc_ndcg_at_1_diff1": 0.314253, + "nauc_ndcg_at_3_max": 0.230281, + "nauc_ndcg_at_3_std": 0.091349, + "nauc_ndcg_at_3_diff1": 0.290209, + "nauc_ndcg_at_5_max": 0.203289, + "nauc_ndcg_at_5_std": 0.088098, + "nauc_ndcg_at_5_diff1": 0.26714, + "nauc_ndcg_at_10_max": 0.222172, + "nauc_ndcg_at_10_std": 0.075081, + "nauc_ndcg_at_10_diff1": 0.280055, + "nauc_ndcg_at_20_max": 0.215514, + "nauc_ndcg_at_20_std": 0.11138, + "nauc_ndcg_at_20_diff1": 0.269804, + "nauc_ndcg_at_100_max": 0.210631, + "nauc_ndcg_at_100_std": 0.124327, + "nauc_ndcg_at_100_diff1": 0.277895, + "nauc_ndcg_at_1000_max": 0.22346, + "nauc_ndcg_at_1000_std": 0.126593, + "nauc_ndcg_at_1000_diff1": 0.278613, + "nauc_map_at_1_max": 0.18178, + "nauc_map_at_1_std": 0.147303, + "nauc_map_at_1_diff1": 0.377038, + "nauc_map_at_3_max": 0.199709, + "nauc_map_at_3_std": 0.093193, + "nauc_map_at_3_diff1": 0.314561, + "nauc_map_at_5_max": 0.179826, + "nauc_map_at_5_std": 0.079734, + "nauc_map_at_5_diff1": 0.301664, + "nauc_map_at_10_max": 0.191845, + "nauc_map_at_10_std": 0.065538, + "nauc_map_at_10_diff1": 0.304931, + "nauc_map_at_20_max": 0.194699, + "nauc_map_at_20_std": 0.08344, + "nauc_map_at_20_diff1": 0.298798, + "nauc_map_at_100_max": 0.19546, + "nauc_map_at_100_std": 0.089735, + "nauc_map_at_100_diff1": 0.299051, + "nauc_map_at_1000_max": 0.196058, + "nauc_map_at_1000_std": 0.090382, + "nauc_map_at_1000_diff1": 0.298701, + "nauc_recall_at_1_max": 0.18178, + "nauc_recall_at_1_std": 0.147303, + "nauc_recall_at_1_diff1": 0.377038, + "nauc_recall_at_3_max": 0.160587, + "nauc_recall_at_3_std": 0.069298, + "nauc_recall_at_3_diff1": 0.233508, + "nauc_recall_at_5_max": 0.112414, + "nauc_recall_at_5_std": 0.070413, + "nauc_recall_at_5_diff1": 0.197784, + "nauc_recall_at_10_max": 0.136724, + "nauc_recall_at_10_std": 0.02523, + "nauc_recall_at_10_diff1": 0.207414, + "nauc_recall_at_20_max": 0.088512, + "nauc_recall_at_20_std": 0.096341, + "nauc_recall_at_20_diff1": 0.180224, + "nauc_recall_at_100_max": 0.025693, + "nauc_recall_at_100_std": 0.132958, + "nauc_recall_at_100_diff1": 0.202687, + "nauc_recall_at_1000_max": 0.0027, + "nauc_recall_at_1000_std": 0.311638, + "nauc_recall_at_1000_diff1": 0.24551, + "nauc_precision_at_1_max": 0.267365, + "nauc_precision_at_1_std": 0.067935, + "nauc_precision_at_1_diff1": 0.314253, + "nauc_precision_at_3_max": 0.326474, + "nauc_precision_at_3_std": 0.040431, + "nauc_precision_at_3_diff1": 0.257449, + "nauc_precision_at_5_max": 0.26541, + "nauc_precision_at_5_std": 0.032238, + "nauc_precision_at_5_diff1": 0.190494, + "nauc_precision_at_10_max": 0.29902, + "nauc_precision_at_10_std": 0.036085, + "nauc_precision_at_10_diff1": 0.207301, + "nauc_precision_at_20_max": 0.278719, + "nauc_precision_at_20_std": 0.149327, + "nauc_precision_at_20_diff1": 0.135001, + "nauc_precision_at_100_max": 0.208442, + "nauc_precision_at_100_std": 0.177036, + "nauc_precision_at_100_diff1": 0.072962, + "nauc_precision_at_1000_max": 0.229736, + "nauc_precision_at_1000_std": 0.139883, + "nauc_precision_at_1000_diff1": 0.018422, + "nauc_mrr_at_1_max": 0.267365, + "nauc_mrr_at_1_std": 0.067935, + "nauc_mrr_at_1_diff1": 0.314253, + "nauc_mrr_at_3_max": 0.304825, + "nauc_mrr_at_3_std": 0.091735, + "nauc_mrr_at_3_diff1": 0.275917, + "nauc_mrr_at_5_max": 0.295403, + "nauc_mrr_at_5_std": 0.106655, + "nauc_mrr_at_5_diff1": 0.262053, + "nauc_mrr_at_10_max": 0.305712, + "nauc_mrr_at_10_std": 0.113972, + "nauc_mrr_at_10_diff1": 0.279206, + "nauc_mrr_at_20_max": 0.297866, + "nauc_mrr_at_20_std": 0.114886, + "nauc_mrr_at_20_diff1": 0.276849, + "nauc_mrr_at_100_max": 0.294525, + "nauc_mrr_at_100_std": 0.111481, + "nauc_mrr_at_100_diff1": 0.277094, + "nauc_mrr_at_1000_max": 0.294892, + "nauc_mrr_at_1000_std": 0.111218, + "nauc_mrr_at_1000_diff1": 0.277115, + "main_score": 0.27523, + "hf_subset": "PMC-Clinical", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.1938, + "ndcg_at_3": 0.15169, + "ndcg_at_5": 0.15547, + "ndcg_at_10": 0.20757, + "ndcg_at_20": 0.26168, + "ndcg_at_100": 0.35728, + "ndcg_at_1000": 0.39991, + "map_at_1": 0.05711, + "map_at_3": 0.09137, + "map_at_5": 0.10169, + "map_at_10": 0.12852, + "map_at_20": 0.14863, + "map_at_100": 0.17098, + "map_at_1000": 0.17466, + "recall_at_1": 0.05711, + "recall_at_3": 0.12248, + "recall_at_5": 0.15788, + "recall_at_10": 0.2677, + "recall_at_20": 0.42339, + "recall_at_100": 0.76873, + "recall_at_1000": 0.98811, + "precision_at_1": 0.1938, + "precision_at_3": 0.12145, + "precision_at_5": 0.10233, + "precision_at_10": 0.09535, + "precision_at_20": 0.07209, + "precision_at_100": 0.02713, + "precision_at_1000": 0.00351, + "mrr_at_1": 0.193798, + "mrr_at_3": 0.239018, + "mrr_at_5": 0.261499, + "mrr_at_10": 0.284401, + "mrr_at_20": 0.294246, + "mrr_at_100": 0.300049, + "mrr_at_1000": 0.300455, + "nauc_ndcg_at_1_max": 0.184128, + "nauc_ndcg_at_1_std": 0.118755, + "nauc_ndcg_at_1_diff1": 0.308651, + "nauc_ndcg_at_3_max": 0.083925, + "nauc_ndcg_at_3_std": 0.062066, + "nauc_ndcg_at_3_diff1": 0.218419, + "nauc_ndcg_at_5_max": 0.079221, + "nauc_ndcg_at_5_std": 0.118763, + "nauc_ndcg_at_5_diff1": 0.233345, + "nauc_ndcg_at_10_max": 0.077088, + "nauc_ndcg_at_10_std": 0.137362, + "nauc_ndcg_at_10_diff1": 0.158296, + "nauc_ndcg_at_20_max": 0.096593, + "nauc_ndcg_at_20_std": 0.12354, + "nauc_ndcg_at_20_diff1": 0.100829, + "nauc_ndcg_at_100_max": 0.113122, + "nauc_ndcg_at_100_std": 0.198506, + "nauc_ndcg_at_100_diff1": 0.105631, + "nauc_ndcg_at_1000_max": 0.112111, + "nauc_ndcg_at_1000_std": 0.190118, + "nauc_ndcg_at_1000_diff1": 0.158707, + "nauc_map_at_1_max": 0.1158, + "nauc_map_at_1_std": 0.08752, + "nauc_map_at_1_diff1": 0.364844, + "nauc_map_at_3_max": 0.044819, + "nauc_map_at_3_std": 0.02872, + "nauc_map_at_3_diff1": 0.235999, + "nauc_map_at_5_max": 0.062658, + "nauc_map_at_5_std": 0.080639, + "nauc_map_at_5_diff1": 0.256335, + "nauc_map_at_10_max": 0.051384, + "nauc_map_at_10_std": 0.109637, + "nauc_map_at_10_diff1": 0.214176, + "nauc_map_at_20_max": 0.074668, + "nauc_map_at_20_std": 0.104743, + "nauc_map_at_20_diff1": 0.176393, + "nauc_map_at_100_max": 0.080279, + "nauc_map_at_100_std": 0.134245, + "nauc_map_at_100_diff1": 0.17231, + "nauc_map_at_1000_max": 0.082281, + "nauc_map_at_1000_std": 0.135231, + "nauc_map_at_1000_diff1": 0.176939, + "nauc_recall_at_1_max": 0.1158, + "nauc_recall_at_1_std": 0.08752, + "nauc_recall_at_1_diff1": 0.364844, + "nauc_recall_at_3_max": -0.005221, + "nauc_recall_at_3_std": -0.015798, + "nauc_recall_at_3_diff1": 0.153207, + "nauc_recall_at_5_max": 0.029018, + "nauc_recall_at_5_std": 0.097376, + "nauc_recall_at_5_diff1": 0.169316, + "nauc_recall_at_10_max": 0.037348, + "nauc_recall_at_10_std": 0.13169, + "nauc_recall_at_10_diff1": 0.045336, + "nauc_recall_at_20_max": 0.051873, + "nauc_recall_at_20_std": 0.058419, + "nauc_recall_at_20_diff1": -0.056547, + "nauc_recall_at_100_max": 0.035243, + "nauc_recall_at_100_std": 0.24201, + "nauc_recall_at_100_diff1": -0.131451, + "nauc_recall_at_1000_max": -1.327355, + "nauc_recall_at_1000_std": 0.543781, + "nauc_recall_at_1000_diff1": 0.079757, + "nauc_precision_at_1_max": 0.184128, + "nauc_precision_at_1_std": 0.118755, + "nauc_precision_at_1_diff1": 0.308651, + "nauc_precision_at_3_max": 0.08263, + "nauc_precision_at_3_std": 0.095432, + "nauc_precision_at_3_diff1": 0.178564, + "nauc_precision_at_5_max": 0.123407, + "nauc_precision_at_5_std": 0.217483, + "nauc_precision_at_5_diff1": 0.210211, + "nauc_precision_at_10_max": 0.099355, + "nauc_precision_at_10_std": 0.210794, + "nauc_precision_at_10_diff1": 0.054598, + "nauc_precision_at_20_max": 0.13669, + "nauc_precision_at_20_std": 0.185158, + "nauc_precision_at_20_diff1": -0.058019, + "nauc_precision_at_100_max": 0.174784, + "nauc_precision_at_100_std": 0.324652, + "nauc_precision_at_100_diff1": -0.021574, + "nauc_precision_at_1000_max": 0.140637, + "nauc_precision_at_1000_std": 0.242144, + "nauc_precision_at_1000_diff1": 0.098315, + "nauc_mrr_at_1_max": 0.184128, + "nauc_mrr_at_1_std": 0.118755, + "nauc_mrr_at_1_diff1": 0.308651, + "nauc_mrr_at_3_max": 0.129277, + "nauc_mrr_at_3_std": 0.108208, + "nauc_mrr_at_3_diff1": 0.236484, + "nauc_mrr_at_5_max": 0.126056, + "nauc_mrr_at_5_std": 0.127837, + "nauc_mrr_at_5_diff1": 0.217906, + "nauc_mrr_at_10_max": 0.143204, + "nauc_mrr_at_10_std": 0.135496, + "nauc_mrr_at_10_diff1": 0.211368, + "nauc_mrr_at_20_max": 0.137828, + "nauc_mrr_at_20_std": 0.134903, + "nauc_mrr_at_20_diff1": 0.203024, + "nauc_mrr_at_100_max": 0.141102, + "nauc_mrr_at_100_std": 0.135753, + "nauc_mrr_at_100_diff1": 0.207332, + "nauc_mrr_at_1000_max": 0.140643, + "nauc_mrr_at_1000_std": 0.135179, + "nauc_mrr_at_1000_diff1": 0.207994, + "main_score": 0.20757, + "hf_subset": "IIYi-Clinical", + "languages": [ + "eng-Latn" + ] + } + ] + }, + "evaluation_time": 2846.2090780735016, + "kg_co2_emissions": null +} \ No newline at end of file diff --git a/results/BAAI__bge-large-en-v1.5/d4aa6901d3a41ba39fb536a557fa166f842b0e09/R2MEDRetrieval.json b/results/BAAI__bge-large-en-v1.5/d4aa6901d3a41ba39fb536a557fa166f842b0e09/R2MEDRetrieval.json new file mode 100644 index 0000000000..5598694e3e --- /dev/null +++ b/results/BAAI__bge-large-en-v1.5/d4aa6901d3a41ba39fb536a557fa166f842b0e09/R2MEDRetrieval.json @@ -0,0 +1,1187 @@ +{ + "dataset_revision": "1.0", + "task_name": "R2MEDRetrieval", + "mteb_version": "1.38.20", + "scores": { + "test": [ + { + "ndcg_at_1": 0.09709, + "ndcg_at_3": 0.09392, + "ndcg_at_5": 0.10695, + "ndcg_at_10": 0.12706, + "ndcg_at_20": 0.14837, + "ndcg_at_100": 0.19823, + "ndcg_at_1000": 0.26428, + "map_at_1": 0.0281, + "map_at_3": 0.05143, + "map_at_5": 0.06366, + "map_at_10": 0.07706, + "map_at_20": 0.08429, + "map_at_100": 0.0934, + "map_at_1000": 0.09698, + "recall_at_1": 0.0281, + "recall_at_3": 0.0704, + "recall_at_5": 0.11217, + "recall_at_10": 0.16545, + "recall_at_20": 0.22348, + "recall_at_100": 0.40968, + "recall_at_1000": 0.78227, + "precision_at_1": 0.09709, + "precision_at_3": 0.09061, + "precision_at_5": 0.08155, + "precision_at_10": 0.06311, + "precision_at_20": 0.04272, + "precision_at_100": 0.01573, + "precision_at_1000": 0.00288, + "mrr_at_1": 0.097087, + "mrr_at_3": 0.13754, + "mrr_at_5": 0.157929, + "mrr_at_10": 0.167618, + "mrr_at_20": 0.173593, + "mrr_at_100": 0.177743, + "mrr_at_1000": 0.1791, + "nauc_ndcg_at_1_max": 0.294204, + "nauc_ndcg_at_1_std": -0.03641, + "nauc_ndcg_at_1_diff1": 0.480561, + "nauc_ndcg_at_3_max": 0.133946, + "nauc_ndcg_at_3_std": -0.157467, + "nauc_ndcg_at_3_diff1": 0.402003, + "nauc_ndcg_at_5_max": 0.067075, + "nauc_ndcg_at_5_std": -0.215675, + "nauc_ndcg_at_5_diff1": 0.302267, + "nauc_ndcg_at_10_max": 0.02004, + "nauc_ndcg_at_10_std": -0.249527, + "nauc_ndcg_at_10_diff1": 0.313172, + "nauc_ndcg_at_20_max": 0.015173, + "nauc_ndcg_at_20_std": -0.266133, + "nauc_ndcg_at_20_diff1": 0.334579, + "nauc_ndcg_at_100_max": 0.036556, + "nauc_ndcg_at_100_std": -0.25781, + "nauc_ndcg_at_100_diff1": 0.357323, + "nauc_ndcg_at_1000_max": 0.034281, + "nauc_ndcg_at_1000_std": -0.235845, + "nauc_ndcg_at_1000_diff1": 0.349464, + "nauc_map_at_1_max": 0.264342, + "nauc_map_at_1_std": -0.112984, + "nauc_map_at_1_diff1": 0.489107, + "nauc_map_at_3_max": 0.183049, + "nauc_map_at_3_std": -0.165107, + "nauc_map_at_3_diff1": 0.458571, + "nauc_map_at_5_max": 0.11968, + "nauc_map_at_5_std": -0.202987, + "nauc_map_at_5_diff1": 0.36383, + "nauc_map_at_10_max": 0.055783, + "nauc_map_at_10_std": -0.235968, + "nauc_map_at_10_diff1": 0.350762, + "nauc_map_at_20_max": 0.049019, + "nauc_map_at_20_std": -0.243249, + "nauc_map_at_20_diff1": 0.365886, + "nauc_map_at_100_max": 0.047385, + "nauc_map_at_100_std": -0.250917, + "nauc_map_at_100_diff1": 0.370891, + "nauc_map_at_1000_max": 0.047199, + "nauc_map_at_1000_std": -0.248215, + "nauc_map_at_1000_diff1": 0.36799, + "nauc_recall_at_1_max": 0.264342, + "nauc_recall_at_1_std": -0.112984, + "nauc_recall_at_1_diff1": 0.489107, + "nauc_recall_at_3_max": 0.128965, + "nauc_recall_at_3_std": -0.170942, + "nauc_recall_at_3_diff1": 0.404312, + "nauc_recall_at_5_max": 0.016113, + "nauc_recall_at_5_std": -0.233644, + "nauc_recall_at_5_diff1": 0.178667, + "nauc_recall_at_10_max": -0.073116, + "nauc_recall_at_10_std": -0.293033, + "nauc_recall_at_10_diff1": 0.217982, + "nauc_recall_at_20_max": -0.040102, + "nauc_recall_at_20_std": -0.286509, + "nauc_recall_at_20_diff1": 0.281433, + "nauc_recall_at_100_max": 0.04198, + "nauc_recall_at_100_std": -0.198581, + "nauc_recall_at_100_diff1": 0.313088, + "nauc_recall_at_1000_max": 0.045433, + "nauc_recall_at_1000_std": -0.086178, + "nauc_recall_at_1000_diff1": 0.334612, + "nauc_precision_at_1_max": 0.294204, + "nauc_precision_at_1_std": -0.03641, + "nauc_precision_at_1_diff1": 0.480561, + "nauc_precision_at_3_max": 0.08678, + "nauc_precision_at_3_std": -0.170249, + "nauc_precision_at_3_diff1": 0.389842, + "nauc_precision_at_5_max": -0.015567, + "nauc_precision_at_5_std": -0.238697, + "nauc_precision_at_5_diff1": 0.251601, + "nauc_precision_at_10_max": -0.109903, + "nauc_precision_at_10_std": -0.31552, + "nauc_precision_at_10_diff1": 0.246084, + "nauc_precision_at_20_max": -0.126519, + "nauc_precision_at_20_std": -0.340761, + "nauc_precision_at_20_diff1": 0.249629, + "nauc_precision_at_100_max": -0.079848, + "nauc_precision_at_100_std": -0.279586, + "nauc_precision_at_100_diff1": 0.235352, + "nauc_precision_at_1000_max": -0.116721, + "nauc_precision_at_1000_std": -0.199638, + "nauc_precision_at_1000_diff1": 0.115002, + "nauc_mrr_at_1_max": 0.294204, + "nauc_mrr_at_1_std": -0.03641, + "nauc_mrr_at_1_diff1": 0.480561, + "nauc_mrr_at_3_max": 0.181706, + "nauc_mrr_at_3_std": -0.116683, + "nauc_mrr_at_3_diff1": 0.383959, + "nauc_mrr_at_5_max": 0.148849, + "nauc_mrr_at_5_std": -0.141983, + "nauc_mrr_at_5_diff1": 0.33836, + "nauc_mrr_at_10_max": 0.139662, + "nauc_mrr_at_10_std": -0.156451, + "nauc_mrr_at_10_diff1": 0.353751, + "nauc_mrr_at_20_max": 0.136293, + "nauc_mrr_at_20_std": -0.163988, + "nauc_mrr_at_20_diff1": 0.350167, + "nauc_mrr_at_100_max": 0.139033, + "nauc_mrr_at_100_std": -0.161858, + "nauc_mrr_at_100_diff1": 0.353242, + "nauc_mrr_at_1000_max": 0.138785, + "nauc_mrr_at_1000_std": -0.161742, + "nauc_mrr_at_1000_diff1": 0.353343, + "main_score": 0.12706, + "hf_subset": "Biology", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.16883, + "ndcg_at_3": 0.18541, + "ndcg_at_5": 0.23214, + "ndcg_at_10": 0.27039, + "ndcg_at_20": 0.29845, + "ndcg_at_100": 0.35271, + "ndcg_at_1000": 0.3971, + "map_at_1": 0.08496, + "map_at_3": 0.12459, + "map_at_5": 0.1648, + "map_at_10": 0.18608, + "map_at_20": 0.19762, + "map_at_100": 0.20859, + "map_at_1000": 0.2118, + "recall_at_1": 0.08496, + "recall_at_3": 0.17645, + "recall_at_5": 0.29215, + "recall_at_10": 0.40082, + "recall_at_20": 0.47056, + "recall_at_100": 0.69147, + "recall_at_1000": 0.94388, + "precision_at_1": 0.16883, + "precision_at_3": 0.1342, + "precision_at_5": 0.13766, + "precision_at_10": 0.0974, + "precision_at_20": 0.06429, + "precision_at_100": 0.01961, + "precision_at_1000": 0.00279, + "mrr_at_1": 0.168831, + "mrr_at_3": 0.242424, + "mrr_at_5": 0.274892, + "mrr_at_10": 0.28892, + "mrr_at_20": 0.291813, + "mrr_at_100": 0.295858, + "mrr_at_1000": 0.296725, + "nauc_ndcg_at_1_max": -0.02574, + "nauc_ndcg_at_1_std": -0.0132, + "nauc_ndcg_at_1_diff1": 0.293279, + "nauc_ndcg_at_3_max": 0.119779, + "nauc_ndcg_at_3_std": 0.066322, + "nauc_ndcg_at_3_diff1": 0.241602, + "nauc_ndcg_at_5_max": 0.19192, + "nauc_ndcg_at_5_std": 0.083306, + "nauc_ndcg_at_5_diff1": 0.229184, + "nauc_ndcg_at_10_max": 0.26077, + "nauc_ndcg_at_10_std": 0.125898, + "nauc_ndcg_at_10_diff1": 0.279474, + "nauc_ndcg_at_20_max": 0.267364, + "nauc_ndcg_at_20_std": 0.145164, + "nauc_ndcg_at_20_diff1": 0.266735, + "nauc_ndcg_at_100_max": 0.266037, + "nauc_ndcg_at_100_std": 0.161979, + "nauc_ndcg_at_100_diff1": 0.269879, + "nauc_ndcg_at_1000_max": 0.248974, + "nauc_ndcg_at_1000_std": 0.15792, + "nauc_ndcg_at_1000_diff1": 0.266128, + "nauc_map_at_1_max": 0.095205, + "nauc_map_at_1_std": 0.163319, + "nauc_map_at_1_diff1": 0.382853, + "nauc_map_at_3_max": 0.118979, + "nauc_map_at_3_std": 0.083942, + "nauc_map_at_3_diff1": 0.295581, + "nauc_map_at_5_max": 0.199051, + "nauc_map_at_5_std": 0.102713, + "nauc_map_at_5_diff1": 0.267862, + "nauc_map_at_10_max": 0.246989, + "nauc_map_at_10_std": 0.135114, + "nauc_map_at_10_diff1": 0.289731, + "nauc_map_at_20_max": 0.248542, + "nauc_map_at_20_std": 0.146198, + "nauc_map_at_20_diff1": 0.279193, + "nauc_map_at_100_max": 0.249969, + "nauc_map_at_100_std": 0.14693, + "nauc_map_at_100_diff1": 0.278685, + "nauc_map_at_1000_max": 0.249775, + "nauc_map_at_1000_std": 0.149564, + "nauc_map_at_1000_diff1": 0.278687, + "nauc_recall_at_1_max": 0.095205, + "nauc_recall_at_1_std": 0.163319, + "nauc_recall_at_1_diff1": 0.382853, + "nauc_recall_at_3_max": 0.18175, + "nauc_recall_at_3_std": 0.02363, + "nauc_recall_at_3_diff1": 0.201436, + "nauc_recall_at_5_max": 0.237489, + "nauc_recall_at_5_std": 0.042344, + "nauc_recall_at_5_diff1": 0.159362, + "nauc_recall_at_10_max": 0.336485, + "nauc_recall_at_10_std": 0.094471, + "nauc_recall_at_10_diff1": 0.255675, + "nauc_recall_at_20_max": 0.353248, + "nauc_recall_at_20_std": 0.140657, + "nauc_recall_at_20_diff1": 0.252119, + "nauc_recall_at_100_max": 0.346245, + "nauc_recall_at_100_std": 0.231145, + "nauc_recall_at_100_diff1": 0.268763, + "nauc_recall_at_1000_max": 0.207844, + "nauc_recall_at_1000_std": 0.09167, + "nauc_recall_at_1000_diff1": 0.21417, + "nauc_precision_at_1_max": -0.02574, + "nauc_precision_at_1_std": -0.0132, + "nauc_precision_at_1_diff1": 0.293279, + "nauc_precision_at_3_max": 0.157425, + "nauc_precision_at_3_std": 0.082995, + "nauc_precision_at_3_diff1": 0.132266, + "nauc_precision_at_5_max": 0.26339, + "nauc_precision_at_5_std": 0.129618, + "nauc_precision_at_5_diff1": 0.119209, + "nauc_precision_at_10_max": 0.315976, + "nauc_precision_at_10_std": 0.234277, + "nauc_precision_at_10_diff1": 0.143531, + "nauc_precision_at_20_max": 0.269692, + "nauc_precision_at_20_std": 0.215746, + "nauc_precision_at_20_diff1": 0.06244, + "nauc_precision_at_100_max": 0.165442, + "nauc_precision_at_100_std": 0.197531, + "nauc_precision_at_100_diff1": -0.004816, + "nauc_precision_at_1000_max": 0.073675, + "nauc_precision_at_1000_std": 0.166424, + "nauc_precision_at_1000_diff1": -0.042191, + "nauc_mrr_at_1_max": -0.02574, + "nauc_mrr_at_1_std": -0.0132, + "nauc_mrr_at_1_diff1": 0.293279, + "nauc_mrr_at_3_max": 0.085388, + "nauc_mrr_at_3_std": 0.029758, + "nauc_mrr_at_3_diff1": 0.213908, + "nauc_mrr_at_5_max": 0.08257, + "nauc_mrr_at_5_std": 0.041481, + "nauc_mrr_at_5_diff1": 0.215012, + "nauc_mrr_at_10_max": 0.082258, + "nauc_mrr_at_10_std": 0.049894, + "nauc_mrr_at_10_diff1": 0.226159, + "nauc_mrr_at_20_max": 0.090359, + "nauc_mrr_at_20_std": 0.053737, + "nauc_mrr_at_20_diff1": 0.230529, + "nauc_mrr_at_100_max": 0.088, + "nauc_mrr_at_100_std": 0.050337, + "nauc_mrr_at_100_diff1": 0.2304, + "nauc_mrr_at_1000_max": 0.087073, + "nauc_mrr_at_1000_std": 0.049525, + "nauc_mrr_at_1000_diff1": 0.230092, + "main_score": 0.27039, + "hf_subset": "Bioinformatics", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.07955, + "ndcg_at_3": 0.18812, + "ndcg_at_5": 0.22245, + "ndcg_at_10": 0.27762, + "ndcg_at_20": 0.32064, + "ndcg_at_100": 0.37105, + "ndcg_at_1000": 0.40055, + "map_at_1": 0.05492, + "map_at_3": 0.13927, + "map_at_5": 0.16149, + "map_at_10": 0.19061, + "map_at_20": 0.20684, + "map_at_100": 0.21693, + "map_at_1000": 0.21887, + "recall_at_1": 0.05492, + "recall_at_3": 0.2383, + "recall_at_5": 0.31351, + "recall_at_10": 0.44785, + "recall_at_20": 0.5768, + "recall_at_100": 0.77707, + "recall_at_1000": 0.94053, + "precision_at_1": 0.07955, + "precision_at_3": 0.14015, + "precision_at_5": 0.12273, + "precision_at_10": 0.1, + "precision_at_20": 0.06818, + "precision_at_100": 0.02011, + "precision_at_1000": 0.00257, + "mrr_at_1": 0.079545, + "mrr_at_3": 0.19697, + "mrr_at_5": 0.223106, + "mrr_at_10": 0.246257, + "mrr_at_20": 0.253297, + "mrr_at_100": 0.256705, + "mrr_at_1000": 0.257027, + "nauc_ndcg_at_1_max": 0.287348, + "nauc_ndcg_at_1_std": 0.180161, + "nauc_ndcg_at_1_diff1": -0.010124, + "nauc_ndcg_at_3_max": 0.346339, + "nauc_ndcg_at_3_std": 0.003951, + "nauc_ndcg_at_3_diff1": -0.103375, + "nauc_ndcg_at_5_max": 0.347161, + "nauc_ndcg_at_5_std": -0.045478, + "nauc_ndcg_at_5_diff1": -0.029208, + "nauc_ndcg_at_10_max": 0.389512, + "nauc_ndcg_at_10_std": 0.0101, + "nauc_ndcg_at_10_diff1": 0.004222, + "nauc_ndcg_at_20_max": 0.422836, + "nauc_ndcg_at_20_std": 0.034577, + "nauc_ndcg_at_20_diff1": 0.032127, + "nauc_ndcg_at_100_max": 0.396792, + "nauc_ndcg_at_100_std": 0.061344, + "nauc_ndcg_at_100_diff1": 0.017707, + "nauc_ndcg_at_1000_max": 0.392567, + "nauc_ndcg_at_1000_std": 0.074381, + "nauc_ndcg_at_1000_diff1": 0.006407, + "nauc_map_at_1_max": 0.107071, + "nauc_map_at_1_std": -0.02379, + "nauc_map_at_1_diff1": -0.012384, + "nauc_map_at_3_max": 0.295944, + "nauc_map_at_3_std": -0.020467, + "nauc_map_at_3_diff1": -0.080242, + "nauc_map_at_5_max": 0.309332, + "nauc_map_at_5_std": -0.05074, + "nauc_map_at_5_diff1": -0.044322, + "nauc_map_at_10_max": 0.355093, + "nauc_map_at_10_std": -0.005952, + "nauc_map_at_10_diff1": -0.029452, + "nauc_map_at_20_max": 0.37304, + "nauc_map_at_20_std": 0.009371, + "nauc_map_at_20_diff1": -0.021191, + "nauc_map_at_100_max": 0.369232, + "nauc_map_at_100_std": 0.015898, + "nauc_map_at_100_diff1": -0.025227, + "nauc_map_at_1000_max": 0.369485, + "nauc_map_at_1000_std": 0.019353, + "nauc_map_at_1000_diff1": -0.025651, + "nauc_recall_at_1_max": 0.107071, + "nauc_recall_at_1_std": -0.02379, + "nauc_recall_at_1_diff1": -0.012384, + "nauc_recall_at_3_max": 0.301715, + "nauc_recall_at_3_std": -0.059614, + "nauc_recall_at_3_diff1": -0.079835, + "nauc_recall_at_5_max": 0.283878, + "nauc_recall_at_5_std": -0.135942, + "nauc_recall_at_5_diff1": 0.011338, + "nauc_recall_at_10_max": 0.360481, + "nauc_recall_at_10_std": -0.063541, + "nauc_recall_at_10_diff1": 0.060153, + "nauc_recall_at_20_max": 0.429172, + "nauc_recall_at_20_std": -0.037341, + "nauc_recall_at_20_diff1": 0.148192, + "nauc_recall_at_100_max": 0.328281, + "nauc_recall_at_100_std": 0.057522, + "nauc_recall_at_100_diff1": 0.174994, + "nauc_recall_at_1000_max": 0.087055, + "nauc_recall_at_1000_std": -0.010588, + "nauc_recall_at_1000_diff1": 0.405872, + "nauc_precision_at_1_max": 0.287348, + "nauc_precision_at_1_std": 0.180161, + "nauc_precision_at_1_diff1": -0.010124, + "nauc_precision_at_3_max": 0.444123, + "nauc_precision_at_3_std": 0.06935, + "nauc_precision_at_3_diff1": -0.177278, + "nauc_precision_at_5_max": 0.442242, + "nauc_precision_at_5_std": 0.025497, + "nauc_precision_at_5_diff1": -0.067785, + "nauc_precision_at_10_max": 0.4529, + "nauc_precision_at_10_std": 0.20947, + "nauc_precision_at_10_diff1": 0.000617, + "nauc_precision_at_20_max": 0.447068, + "nauc_precision_at_20_std": 0.251292, + "nauc_precision_at_20_diff1": 0.046773, + "nauc_precision_at_100_max": 0.237726, + "nauc_precision_at_100_std": 0.2272, + "nauc_precision_at_100_diff1": 0.004548, + "nauc_precision_at_1000_max": 0.116434, + "nauc_precision_at_1000_std": 0.238579, + "nauc_precision_at_1000_diff1": -0.050018, + "nauc_mrr_at_1_max": 0.287348, + "nauc_mrr_at_1_std": 0.180161, + "nauc_mrr_at_1_diff1": -0.010124, + "nauc_mrr_at_3_max": 0.400939, + "nauc_mrr_at_3_std": 0.073962, + "nauc_mrr_at_3_diff1": -0.070791, + "nauc_mrr_at_5_max": 0.400413, + "nauc_mrr_at_5_std": 0.059777, + "nauc_mrr_at_5_diff1": -0.025093, + "nauc_mrr_at_10_max": 0.399872, + "nauc_mrr_at_10_std": 0.070222, + "nauc_mrr_at_10_diff1": -0.009845, + "nauc_mrr_at_20_max": 0.40275, + "nauc_mrr_at_20_std": 0.073778, + "nauc_mrr_at_20_diff1": -0.011279, + "nauc_mrr_at_100_max": 0.399835, + "nauc_mrr_at_100_std": 0.078748, + "nauc_mrr_at_100_diff1": -0.015194, + "nauc_mrr_at_1000_max": 0.399586, + "nauc_mrr_at_1000_std": 0.077944, + "nauc_mrr_at_1000_diff1": -0.014829, + "main_score": 0.27762, + "hf_subset": "Medical-Sciences", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.04124, + "ndcg_at_3": 0.03186, + "ndcg_at_5": 0.03739, + "ndcg_at_10": 0.04103, + "ndcg_at_20": 0.05223, + "ndcg_at_100": 0.08319, + "ndcg_at_1000": 0.13238, + "map_at_1": 0.0178, + "map_at_3": 0.0214, + "map_at_5": 0.02549, + "map_at_10": 0.02667, + "map_at_20": 0.02921, + "map_at_100": 0.03319, + "map_at_1000": 0.03485, + "recall_at_1": 0.0178, + "recall_at_3": 0.02501, + "recall_at_5": 0.03996, + "recall_at_10": 0.04941, + "recall_at_20": 0.0825, + "recall_at_100": 0.22047, + "recall_at_1000": 0.5353, + "precision_at_1": 0.04124, + "precision_at_3": 0.02062, + "precision_at_5": 0.02268, + "precision_at_10": 0.01443, + "precision_at_20": 0.01237, + "precision_at_100": 0.00577, + "precision_at_1000": 0.00144, + "mrr_at_1": 0.041237, + "mrr_at_3": 0.051546, + "mrr_at_5": 0.057732, + "mrr_at_10": 0.061524, + "mrr_at_20": 0.066214, + "mrr_at_100": 0.070862, + "mrr_at_1000": 0.072039, + "nauc_ndcg_at_1_max": 0.077675, + "nauc_ndcg_at_1_std": -0.351913, + "nauc_ndcg_at_1_diff1": 0.522806, + "nauc_ndcg_at_3_max": 0.119594, + "nauc_ndcg_at_3_std": -0.129156, + "nauc_ndcg_at_3_diff1": 0.511218, + "nauc_ndcg_at_5_max": 0.198012, + "nauc_ndcg_at_5_std": -0.089471, + "nauc_ndcg_at_5_diff1": 0.43127, + "nauc_ndcg_at_10_max": 0.166443, + "nauc_ndcg_at_10_std": -0.121818, + "nauc_ndcg_at_10_diff1": 0.413633, + "nauc_ndcg_at_20_max": 0.167956, + "nauc_ndcg_at_20_std": -0.054027, + "nauc_ndcg_at_20_diff1": 0.375731, + "nauc_ndcg_at_100_max": 0.157661, + "nauc_ndcg_at_100_std": 0.064765, + "nauc_ndcg_at_100_diff1": 0.286567, + "nauc_ndcg_at_1000_max": 0.185939, + "nauc_ndcg_at_1000_std": 0.031909, + "nauc_ndcg_at_1000_diff1": 0.266601, + "nauc_map_at_1_max": -0.060217, + "nauc_map_at_1_std": -0.400131, + "nauc_map_at_1_diff1": 0.721916, + "nauc_map_at_3_max": 0.009747, + "nauc_map_at_3_std": -0.196665, + "nauc_map_at_3_diff1": 0.607124, + "nauc_map_at_5_max": 0.09278, + "nauc_map_at_5_std": -0.168096, + "nauc_map_at_5_diff1": 0.532648, + "nauc_map_at_10_max": 0.084692, + "nauc_map_at_10_std": -0.179684, + "nauc_map_at_10_diff1": 0.5221, + "nauc_map_at_20_max": 0.094602, + "nauc_map_at_20_std": -0.153743, + "nauc_map_at_20_diff1": 0.50265, + "nauc_map_at_100_max": 0.096471, + "nauc_map_at_100_std": -0.108731, + "nauc_map_at_100_diff1": 0.46469, + "nauc_map_at_1000_max": 0.098132, + "nauc_map_at_1000_std": -0.108233, + "nauc_map_at_1000_diff1": 0.456929, + "nauc_recall_at_1_max": -0.060217, + "nauc_recall_at_1_std": -0.400131, + "nauc_recall_at_1_diff1": 0.721916, + "nauc_recall_at_3_max": 0.059524, + "nauc_recall_at_3_std": -0.051902, + "nauc_recall_at_3_diff1": 0.525451, + "nauc_recall_at_5_max": 0.247191, + "nauc_recall_at_5_std": -0.009053, + "nauc_recall_at_5_diff1": 0.376945, + "nauc_recall_at_10_max": 0.183363, + "nauc_recall_at_10_std": -0.084318, + "nauc_recall_at_10_diff1": 0.345799, + "nauc_recall_at_20_max": 0.155964, + "nauc_recall_at_20_std": 0.006487, + "nauc_recall_at_20_diff1": 0.309677, + "nauc_recall_at_100_max": 0.123296, + "nauc_recall_at_100_std": 0.21393, + "nauc_recall_at_100_diff1": 0.18302, + "nauc_recall_at_1000_max": 0.2315, + "nauc_recall_at_1000_std": 0.114028, + "nauc_recall_at_1000_diff1": 0.199094, + "nauc_precision_at_1_max": 0.077675, + "nauc_precision_at_1_std": -0.351913, + "nauc_precision_at_1_diff1": 0.522806, + "nauc_precision_at_3_max": 0.23457, + "nauc_precision_at_3_std": -0.01396, + "nauc_precision_at_3_diff1": 0.390486, + "nauc_precision_at_5_max": 0.408968, + "nauc_precision_at_5_std": 0.031134, + "nauc_precision_at_5_diff1": 0.270874, + "nauc_precision_at_10_max": 0.30621, + "nauc_precision_at_10_std": -0.06086, + "nauc_precision_at_10_diff1": 0.249591, + "nauc_precision_at_20_max": 0.279546, + "nauc_precision_at_20_std": 0.098151, + "nauc_precision_at_20_diff1": 0.20563, + "nauc_precision_at_100_max": 0.244191, + "nauc_precision_at_100_std": 0.213228, + "nauc_precision_at_100_diff1": 0.073911, + "nauc_precision_at_1000_max": 0.155961, + "nauc_precision_at_1000_std": 0.09697, + "nauc_precision_at_1000_diff1": -0.047056, + "nauc_mrr_at_1_max": 0.077675, + "nauc_mrr_at_1_std": -0.351913, + "nauc_mrr_at_1_diff1": 0.522806, + "nauc_mrr_at_3_max": 0.171812, + "nauc_mrr_at_3_std": -0.149141, + "nauc_mrr_at_3_diff1": 0.443414, + "nauc_mrr_at_5_max": 0.224636, + "nauc_mrr_at_5_std": -0.108889, + "nauc_mrr_at_5_diff1": 0.403623, + "nauc_mrr_at_10_max": 0.205471, + "nauc_mrr_at_10_std": -0.127852, + "nauc_mrr_at_10_diff1": 0.392997, + "nauc_mrr_at_20_max": 0.200125, + "nauc_mrr_at_20_std": -0.094923, + "nauc_mrr_at_20_diff1": 0.371632, + "nauc_mrr_at_100_max": 0.193392, + "nauc_mrr_at_100_std": -0.087595, + "nauc_mrr_at_100_diff1": 0.353963, + "nauc_mrr_at_1000_max": 0.193496, + "nauc_mrr_at_1000_std": -0.090826, + "nauc_mrr_at_1000_diff1": 0.354135, + "main_score": 0.04103, + "hf_subset": "MedXpertQA-Exam", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.05085, + "ndcg_at_3": 0.06133, + "ndcg_at_5": 0.06848, + "ndcg_at_10": 0.08328, + "ndcg_at_20": 0.09735, + "ndcg_at_100": 0.13299, + "ndcg_at_1000": 0.19049, + "map_at_1": 0.02182, + "map_at_3": 0.03957, + "map_at_5": 0.04901, + "map_at_10": 0.05596, + "map_at_20": 0.06113, + "map_at_100": 0.066, + "map_at_1000": 0.06863, + "recall_at_1": 0.02182, + "recall_at_3": 0.05155, + "recall_at_5": 0.07882, + "recall_at_10": 0.11153, + "recall_at_20": 0.14659, + "recall_at_100": 0.2849, + "recall_at_1000": 0.59487, + "precision_at_1": 0.05085, + "precision_at_3": 0.0565, + "precision_at_5": 0.04915, + "precision_at_10": 0.03814, + "precision_at_20": 0.02627, + "precision_at_100": 0.01025, + "precision_at_1000": 0.00236, + "mrr_at_1": 0.050847, + "mrr_at_3": 0.076271, + "mrr_at_5": 0.086017, + "mrr_at_10": 0.096297, + "mrr_at_20": 0.101767, + "mrr_at_100": 0.106471, + "mrr_at_1000": 0.107555, + "nauc_ndcg_at_1_max": -0.100071, + "nauc_ndcg_at_1_std": 0.091795, + "nauc_ndcg_at_1_diff1": 0.010268, + "nauc_ndcg_at_3_max": -0.003446, + "nauc_ndcg_at_3_std": 0.279965, + "nauc_ndcg_at_3_diff1": 0.046242, + "nauc_ndcg_at_5_max": -0.04617, + "nauc_ndcg_at_5_std": 0.23163, + "nauc_ndcg_at_5_diff1": 0.036165, + "nauc_ndcg_at_10_max": -0.023699, + "nauc_ndcg_at_10_std": 0.257379, + "nauc_ndcg_at_10_diff1": 0.010819, + "nauc_ndcg_at_20_max": -0.011913, + "nauc_ndcg_at_20_std": 0.275447, + "nauc_ndcg_at_20_diff1": 0.031717, + "nauc_ndcg_at_100_max": 0.038537, + "nauc_ndcg_at_100_std": 0.284301, + "nauc_ndcg_at_100_diff1": 0.074414, + "nauc_ndcg_at_1000_max": 0.008142, + "nauc_ndcg_at_1000_std": 0.275517, + "nauc_ndcg_at_1000_diff1": 0.060995, + "nauc_map_at_1_max": -0.164517, + "nauc_map_at_1_std": 0.015506, + "nauc_map_at_1_diff1": 0.2203, + "nauc_map_at_3_max": 0.007387, + "nauc_map_at_3_std": 0.276505, + "nauc_map_at_3_diff1": 0.114949, + "nauc_map_at_5_max": -0.04853, + "nauc_map_at_5_std": 0.25639, + "nauc_map_at_5_diff1": 0.061755, + "nauc_map_at_10_max": -0.009374, + "nauc_map_at_10_std": 0.277454, + "nauc_map_at_10_diff1": 0.038945, + "nauc_map_at_20_max": -0.005881, + "nauc_map_at_20_std": 0.288362, + "nauc_map_at_20_diff1": 0.047893, + "nauc_map_at_100_max": 0.00105, + "nauc_map_at_100_std": 0.28651, + "nauc_map_at_100_diff1": 0.052707, + "nauc_map_at_1000_max": -0.001143, + "nauc_map_at_1000_std": 0.287538, + "nauc_map_at_1000_diff1": 0.052773, + "nauc_recall_at_1_max": -0.164517, + "nauc_recall_at_1_std": 0.015506, + "nauc_recall_at_1_diff1": 0.2203, + "nauc_recall_at_3_max": 0.03942, + "nauc_recall_at_3_std": 0.310013, + "nauc_recall_at_3_diff1": 0.111591, + "nauc_recall_at_5_max": -0.049656, + "nauc_recall_at_5_std": 0.224695, + "nauc_recall_at_5_diff1": 0.007308, + "nauc_recall_at_10_max": -0.025313, + "nauc_recall_at_10_std": 0.249369, + "nauc_recall_at_10_diff1": -0.020143, + "nauc_recall_at_20_max": -0.003255, + "nauc_recall_at_20_std": 0.276793, + "nauc_recall_at_20_diff1": 0.021214, + "nauc_recall_at_100_max": 0.113267, + "nauc_recall_at_100_std": 0.264728, + "nauc_recall_at_100_diff1": 0.115333, + "nauc_recall_at_1000_max": 0.02392, + "nauc_recall_at_1000_std": 0.283106, + "nauc_recall_at_1000_diff1": 0.062154, + "nauc_precision_at_1_max": -0.100071, + "nauc_precision_at_1_std": 0.091795, + "nauc_precision_at_1_diff1": 0.010268, + "nauc_precision_at_3_max": 0.060546, + "nauc_precision_at_3_std": 0.382219, + "nauc_precision_at_3_diff1": -0.00736, + "nauc_precision_at_5_max": -0.024047, + "nauc_precision_at_5_std": 0.327698, + "nauc_precision_at_5_diff1": -0.010395, + "nauc_precision_at_10_max": 0.010653, + "nauc_precision_at_10_std": 0.305836, + "nauc_precision_at_10_diff1": -0.022619, + "nauc_precision_at_20_max": 0.039069, + "nauc_precision_at_20_std": 0.335776, + "nauc_precision_at_20_diff1": 0.041108, + "nauc_precision_at_100_max": 0.119184, + "nauc_precision_at_100_std": 0.306533, + "nauc_precision_at_100_diff1": 0.14764, + "nauc_precision_at_1000_max": 0.011696, + "nauc_precision_at_1000_std": 0.141472, + "nauc_precision_at_1000_diff1": 0.0808, + "nauc_mrr_at_1_max": -0.100071, + "nauc_mrr_at_1_std": 0.091795, + "nauc_mrr_at_1_diff1": 0.010268, + "nauc_mrr_at_3_max": -0.05062, + "nauc_mrr_at_3_std": 0.208925, + "nauc_mrr_at_3_diff1": 0.023277, + "nauc_mrr_at_5_max": -0.050874, + "nauc_mrr_at_5_std": 0.184086, + "nauc_mrr_at_5_diff1": 0.016455, + "nauc_mrr_at_10_max": -0.06787, + "nauc_mrr_at_10_std": 0.184928, + "nauc_mrr_at_10_diff1": 0.003418, + "nauc_mrr_at_20_max": -0.064705, + "nauc_mrr_at_20_std": 0.193776, + "nauc_mrr_at_20_diff1": 0.008189, + "nauc_mrr_at_100_max": -0.054413, + "nauc_mrr_at_100_std": 0.196752, + "nauc_mrr_at_100_diff1": 0.011395, + "nauc_mrr_at_1000_max": -0.054946, + "nauc_mrr_at_1000_std": 0.195173, + "nauc_mrr_at_1000_diff1": 0.011828, + "main_score": 0.08328, + "hf_subset": "MedQA-Diag", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.24667, + "ndcg_at_3": 0.22876, + "ndcg_at_5": 0.24339, + "ndcg_at_10": 0.26454, + "ndcg_at_20": 0.2858, + "ndcg_at_100": 0.31291, + "ndcg_at_1000": 0.35104, + "map_at_1": 0.14789, + "map_at_3": 0.18717, + "map_at_5": 0.20297, + "map_at_10": 0.2123, + "map_at_20": 0.21847, + "map_at_100": 0.22245, + "map_at_1000": 0.22388, + "recall_at_1": 0.14789, + "recall_at_3": 0.22367, + "recall_at_5": 0.27267, + "recall_at_10": 0.328, + "recall_at_20": 0.398, + "recall_at_100": 0.51878, + "recall_at_1000": 0.77833, + "precision_at_1": 0.24667, + "precision_at_3": 0.13333, + "precision_at_5": 0.09867, + "precision_at_10": 0.06067, + "precision_at_20": 0.03767, + "precision_at_100": 0.0104, + "precision_at_1000": 0.00159, + "mrr_at_1": 0.246667, + "mrr_at_3": 0.293333, + "mrr_at_5": 0.304333, + "mrr_at_10": 0.313056, + "mrr_at_20": 0.31935, + "mrr_at_100": 0.321777, + "mrr_at_1000": 0.322683, + "nauc_ndcg_at_1_max": 0.310046, + "nauc_ndcg_at_1_std": 0.083436, + "nauc_ndcg_at_1_diff1": 0.421916, + "nauc_ndcg_at_3_max": 0.309142, + "nauc_ndcg_at_3_std": 0.032129, + "nauc_ndcg_at_3_diff1": 0.393846, + "nauc_ndcg_at_5_max": 0.277557, + "nauc_ndcg_at_5_std": 0.011467, + "nauc_ndcg_at_5_diff1": 0.359271, + "nauc_ndcg_at_10_max": 0.259913, + "nauc_ndcg_at_10_std": 0.002158, + "nauc_ndcg_at_10_diff1": 0.348938, + "nauc_ndcg_at_20_max": 0.249408, + "nauc_ndcg_at_20_std": -0.005678, + "nauc_ndcg_at_20_diff1": 0.330695, + "nauc_ndcg_at_100_max": 0.249253, + "nauc_ndcg_at_100_std": 0.001126, + "nauc_ndcg_at_100_diff1": 0.345938, + "nauc_ndcg_at_1000_max": 0.265565, + "nauc_ndcg_at_1000_std": 0.03331, + "nauc_ndcg_at_1000_diff1": 0.34594, + "nauc_map_at_1_max": 0.213057, + "nauc_map_at_1_std": -0.025276, + "nauc_map_at_1_diff1": 0.382369, + "nauc_map_at_3_max": 0.274731, + "nauc_map_at_3_std": 0.005206, + "nauc_map_at_3_diff1": 0.394045, + "nauc_map_at_5_max": 0.271023, + "nauc_map_at_5_std": 0.003999, + "nauc_map_at_5_diff1": 0.367824, + "nauc_map_at_10_max": 0.263136, + "nauc_map_at_10_std": 0.000991, + "nauc_map_at_10_diff1": 0.363097, + "nauc_map_at_20_max": 0.259976, + "nauc_map_at_20_std": -0.002667, + "nauc_map_at_20_diff1": 0.356963, + "nauc_map_at_100_max": 0.261864, + "nauc_map_at_100_std": -0.000715, + "nauc_map_at_100_diff1": 0.359448, + "nauc_map_at_1000_max": 0.262304, + "nauc_map_at_1000_std": 0.000487, + "nauc_map_at_1000_diff1": 0.359377, + "nauc_recall_at_1_max": 0.213057, + "nauc_recall_at_1_std": -0.025276, + "nauc_recall_at_1_diff1": 0.382369, + "nauc_recall_at_3_max": 0.272482, + "nauc_recall_at_3_std": -0.017191, + "nauc_recall_at_3_diff1": 0.354329, + "nauc_recall_at_5_max": 0.201679, + "nauc_recall_at_5_std": -0.049069, + "nauc_recall_at_5_diff1": 0.256193, + "nauc_recall_at_10_max": 0.151208, + "nauc_recall_at_10_std": -0.075767, + "nauc_recall_at_10_diff1": 0.230121, + "nauc_recall_at_20_max": 0.102334, + "nauc_recall_at_20_std": -0.098053, + "nauc_recall_at_20_diff1": 0.165529, + "nauc_recall_at_100_max": 0.070369, + "nauc_recall_at_100_std": -0.079278, + "nauc_recall_at_100_diff1": 0.202389, + "nauc_recall_at_1000_max": 0.116282, + "nauc_recall_at_1000_std": 0.190824, + "nauc_recall_at_1000_diff1": 0.133682, + "nauc_precision_at_1_max": 0.310046, + "nauc_precision_at_1_std": 0.083436, + "nauc_precision_at_1_diff1": 0.421916, + "nauc_precision_at_3_max": 0.446795, + "nauc_precision_at_3_std": 0.152027, + "nauc_precision_at_3_diff1": 0.437043, + "nauc_precision_at_5_max": 0.379951, + "nauc_precision_at_5_std": 0.113158, + "nauc_precision_at_5_diff1": 0.311873, + "nauc_precision_at_10_max": 0.332736, + "nauc_precision_at_10_std": 0.097546, + "nauc_precision_at_10_diff1": 0.276701, + "nauc_precision_at_20_max": 0.301012, + "nauc_precision_at_20_std": 0.070076, + "nauc_precision_at_20_diff1": 0.209121, + "nauc_precision_at_100_max": 0.236746, + "nauc_precision_at_100_std": 0.094699, + "nauc_precision_at_100_diff1": 0.196729, + "nauc_precision_at_1000_max": 0.226786, + "nauc_precision_at_1000_std": 0.183996, + "nauc_precision_at_1000_diff1": 0.072713, + "nauc_mrr_at_1_max": 0.310046, + "nauc_mrr_at_1_std": 0.083436, + "nauc_mrr_at_1_diff1": 0.421916, + "nauc_mrr_at_3_max": 0.342955, + "nauc_mrr_at_3_std": 0.0886, + "nauc_mrr_at_3_diff1": 0.420311, + "nauc_mrr_at_5_max": 0.327538, + "nauc_mrr_at_5_std": 0.079371, + "nauc_mrr_at_5_diff1": 0.403886, + "nauc_mrr_at_10_max": 0.321901, + "nauc_mrr_at_10_std": 0.074193, + "nauc_mrr_at_10_diff1": 0.395747, + "nauc_mrr_at_20_max": 0.319885, + "nauc_mrr_at_20_std": 0.073051, + "nauc_mrr_at_20_diff1": 0.392084, + "nauc_mrr_at_100_max": 0.318688, + "nauc_mrr_at_100_std": 0.071825, + "nauc_mrr_at_100_diff1": 0.393435, + "nauc_mrr_at_1000_max": 0.318722, + "nauc_mrr_at_1000_std": 0.072573, + "nauc_mrr_at_1000_diff1": 0.393347, + "main_score": 0.26454, + "hf_subset": "PMC-Treatment", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.12281, + "ndcg_at_3": 0.09895, + "ndcg_at_5": 0.11843, + "ndcg_at_10": 0.1506, + "ndcg_at_20": 0.18159, + "ndcg_at_100": 0.23508, + "ndcg_at_1000": 0.27562, + "map_at_1": 0.05409, + "map_at_3": 0.07481, + "map_at_5": 0.08767, + "map_at_10": 0.10289, + "map_at_20": 0.11148, + "map_at_100": 0.11984, + "map_at_1000": 0.12159, + "recall_at_1": 0.05409, + "recall_at_3": 0.09503, + "recall_at_5": 0.13523, + "recall_at_10": 0.22295, + "recall_at_20": 0.32529, + "recall_at_100": 0.55848, + "recall_at_1000": 0.8326, + "precision_at_1": 0.12281, + "precision_at_3": 0.0731, + "precision_at_5": 0.0614, + "precision_at_10": 0.04649, + "precision_at_20": 0.03377, + "precision_at_100": 0.01228, + "precision_at_1000": 0.00179, + "mrr_at_1": 0.122807, + "mrr_at_3": 0.149123, + "mrr_at_5": 0.160965, + "mrr_at_10": 0.172111, + "mrr_at_20": 0.182288, + "mrr_at_100": 0.187814, + "mrr_at_1000": 0.188582, + "nauc_ndcg_at_1_max": 0.199914, + "nauc_ndcg_at_1_std": 0.185059, + "nauc_ndcg_at_1_diff1": 0.152689, + "nauc_ndcg_at_3_max": 0.189381, + "nauc_ndcg_at_3_std": 0.109652, + "nauc_ndcg_at_3_diff1": 0.076431, + "nauc_ndcg_at_5_max": 0.189853, + "nauc_ndcg_at_5_std": 0.10017, + "nauc_ndcg_at_5_diff1": 0.041215, + "nauc_ndcg_at_10_max": 0.174871, + "nauc_ndcg_at_10_std": 0.033682, + "nauc_ndcg_at_10_diff1": 0.060933, + "nauc_ndcg_at_20_max": 0.15497, + "nauc_ndcg_at_20_std": 0.039224, + "nauc_ndcg_at_20_diff1": 0.034031, + "nauc_ndcg_at_100_max": 0.172357, + "nauc_ndcg_at_100_std": 0.117314, + "nauc_ndcg_at_100_diff1": 0.042975, + "nauc_ndcg_at_1000_max": 0.171378, + "nauc_ndcg_at_1000_std": 0.126879, + "nauc_ndcg_at_1000_diff1": 0.050057, + "nauc_map_at_1_max": 0.270081, + "nauc_map_at_1_std": 0.147137, + "nauc_map_at_1_diff1": 0.111149, + "nauc_map_at_3_max": 0.232538, + "nauc_map_at_3_std": 0.086961, + "nauc_map_at_3_diff1": 0.075427, + "nauc_map_at_5_max": 0.225935, + "nauc_map_at_5_std": 0.089326, + "nauc_map_at_5_diff1": 0.050528, + "nauc_map_at_10_max": 0.224388, + "nauc_map_at_10_std": 0.045178, + "nauc_map_at_10_diff1": 0.06427, + "nauc_map_at_20_max": 0.208354, + "nauc_map_at_20_std": 0.053262, + "nauc_map_at_20_diff1": 0.058905, + "nauc_map_at_100_max": 0.210579, + "nauc_map_at_100_std": 0.071257, + "nauc_map_at_100_diff1": 0.057502, + "nauc_map_at_1000_max": 0.210053, + "nauc_map_at_1000_std": 0.073256, + "nauc_map_at_1000_diff1": 0.056375, + "nauc_recall_at_1_max": 0.270081, + "nauc_recall_at_1_std": 0.147137, + "nauc_recall_at_1_diff1": 0.111149, + "nauc_recall_at_3_max": 0.176792, + "nauc_recall_at_3_std": 0.088018, + "nauc_recall_at_3_diff1": 0.054862, + "nauc_recall_at_5_max": 0.156924, + "nauc_recall_at_5_std": 0.070782, + "nauc_recall_at_5_diff1": 0.014389, + "nauc_recall_at_10_max": 0.124067, + "nauc_recall_at_10_std": -0.054107, + "nauc_recall_at_10_diff1": 0.040051, + "nauc_recall_at_20_max": 0.086909, + "nauc_recall_at_20_std": -0.042019, + "nauc_recall_at_20_diff1": -0.022951, + "nauc_recall_at_100_max": 0.139032, + "nauc_recall_at_100_std": 0.186512, + "nauc_recall_at_100_diff1": 0.015863, + "nauc_recall_at_1000_max": 0.12546, + "nauc_recall_at_1000_std": 0.313623, + "nauc_recall_at_1000_diff1": 0.160287, + "nauc_precision_at_1_max": 0.199914, + "nauc_precision_at_1_std": 0.185059, + "nauc_precision_at_1_diff1": 0.152689, + "nauc_precision_at_3_max": 0.14366, + "nauc_precision_at_3_std": 0.065439, + "nauc_precision_at_3_diff1": 0.031258, + "nauc_precision_at_5_max": 0.131404, + "nauc_precision_at_5_std": 0.06975, + "nauc_precision_at_5_diff1": -0.032718, + "nauc_precision_at_10_max": 0.101198, + "nauc_precision_at_10_std": -0.032879, + "nauc_precision_at_10_diff1": 0.029621, + "nauc_precision_at_20_max": 0.049783, + "nauc_precision_at_20_std": 0.009561, + "nauc_precision_at_20_diff1": -0.020431, + "nauc_precision_at_100_max": 0.098356, + "nauc_precision_at_100_std": 0.179364, + "nauc_precision_at_100_diff1": 0.01142, + "nauc_precision_at_1000_max": 0.046529, + "nauc_precision_at_1000_std": 0.162368, + "nauc_precision_at_1000_diff1": -0.016424, + "nauc_mrr_at_1_max": 0.199914, + "nauc_mrr_at_1_std": 0.185059, + "nauc_mrr_at_1_diff1": 0.152689, + "nauc_mrr_at_3_max": 0.161563, + "nauc_mrr_at_3_std": 0.166677, + "nauc_mrr_at_3_diff1": 0.09304, + "nauc_mrr_at_5_max": 0.157982, + "nauc_mrr_at_5_std": 0.157442, + "nauc_mrr_at_5_diff1": 0.083123, + "nauc_mrr_at_10_max": 0.148694, + "nauc_mrr_at_10_std": 0.133885, + "nauc_mrr_at_10_diff1": 0.094968, + "nauc_mrr_at_20_max": 0.150691, + "nauc_mrr_at_20_std": 0.131725, + "nauc_mrr_at_20_diff1": 0.084599, + "nauc_mrr_at_100_max": 0.150701, + "nauc_mrr_at_100_std": 0.140264, + "nauc_mrr_at_100_diff1": 0.084653, + "nauc_mrr_at_1000_max": 0.150501, + "nauc_mrr_at_1000_std": 0.140164, + "nauc_mrr_at_1000_diff1": 0.084641, + "main_score": 0.1506, + "hf_subset": "PMC-Clinical", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.13178, + "ndcg_at_3": 0.13093, + "ndcg_at_5": 0.12478, + "ndcg_at_10": 0.14724, + "ndcg_at_20": 0.18695, + "ndcg_at_100": 0.26939, + "ndcg_at_1000": 0.33236, + "map_at_1": 0.03824, + "map_at_3": 0.07155, + "map_at_5": 0.08008, + "map_at_10": 0.09057, + "map_at_20": 0.10474, + "map_at_100": 0.12018, + "map_at_1000": 0.12461, + "recall_at_1": 0.03824, + "recall_at_3": 0.0978, + "recall_at_5": 0.11809, + "recall_at_10": 0.17106, + "recall_at_20": 0.27519, + "recall_at_100": 0.59044, + "recall_at_1000": 0.92778, + "precision_at_1": 0.13178, + "precision_at_3": 0.12403, + "precision_at_5": 0.09302, + "precision_at_10": 0.06589, + "precision_at_20": 0.05233, + "precision_at_100": 0.02078, + "precision_at_1000": 0.00331, + "mrr_at_1": 0.131783, + "mrr_at_3": 0.200258, + "mrr_at_5": 0.210724, + "mrr_at_10": 0.223625, + "mrr_at_20": 0.233613, + "mrr_at_100": 0.241536, + "mrr_at_1000": 0.242146, + "nauc_ndcg_at_1_max": 0.218237, + "nauc_ndcg_at_1_std": 0.186456, + "nauc_ndcg_at_1_diff1": 0.260002, + "nauc_ndcg_at_3_max": 0.196314, + "nauc_ndcg_at_3_std": 0.269788, + "nauc_ndcg_at_3_diff1": 0.169106, + "nauc_ndcg_at_5_max": 0.181259, + "nauc_ndcg_at_5_std": 0.222246, + "nauc_ndcg_at_5_diff1": 0.158088, + "nauc_ndcg_at_10_max": 0.190101, + "nauc_ndcg_at_10_std": 0.23343, + "nauc_ndcg_at_10_diff1": 0.179822, + "nauc_ndcg_at_20_max": 0.206842, + "nauc_ndcg_at_20_std": 0.249199, + "nauc_ndcg_at_20_diff1": 0.146479, + "nauc_ndcg_at_100_max": 0.212909, + "nauc_ndcg_at_100_std": 0.301491, + "nauc_ndcg_at_100_diff1": 0.078615, + "nauc_ndcg_at_1000_max": 0.21065, + "nauc_ndcg_at_1000_std": 0.33384, + "nauc_ndcg_at_1000_diff1": 0.088486, + "nauc_map_at_1_max": 0.161708, + "nauc_map_at_1_std": 0.070594, + "nauc_map_at_1_diff1": 0.243503, + "nauc_map_at_3_max": 0.188976, + "nauc_map_at_3_std": 0.189445, + "nauc_map_at_3_diff1": 0.186129, + "nauc_map_at_5_max": 0.170869, + "nauc_map_at_5_std": 0.190713, + "nauc_map_at_5_diff1": 0.1847, + "nauc_map_at_10_max": 0.162349, + "nauc_map_at_10_std": 0.196922, + "nauc_map_at_10_diff1": 0.19904, + "nauc_map_at_20_max": 0.17088, + "nauc_map_at_20_std": 0.2127, + "nauc_map_at_20_diff1": 0.172209, + "nauc_map_at_100_max": 0.175634, + "nauc_map_at_100_std": 0.229565, + "nauc_map_at_100_diff1": 0.157851, + "nauc_map_at_1000_max": 0.176224, + "nauc_map_at_1000_std": 0.235182, + "nauc_map_at_1000_diff1": 0.157033, + "nauc_recall_at_1_max": 0.161708, + "nauc_recall_at_1_std": 0.070594, + "nauc_recall_at_1_diff1": 0.243503, + "nauc_recall_at_3_max": 0.202446, + "nauc_recall_at_3_std": 0.24153, + "nauc_recall_at_3_diff1": 0.131608, + "nauc_recall_at_5_max": 0.168247, + "nauc_recall_at_5_std": 0.212398, + "nauc_recall_at_5_diff1": 0.112438, + "nauc_recall_at_10_max": 0.158768, + "nauc_recall_at_10_std": 0.210992, + "nauc_recall_at_10_diff1": 0.163085, + "nauc_recall_at_20_max": 0.177854, + "nauc_recall_at_20_std": 0.212057, + "nauc_recall_at_20_diff1": 0.081268, + "nauc_recall_at_100_max": 0.136479, + "nauc_recall_at_100_std": 0.260289, + "nauc_recall_at_100_diff1": -0.129332, + "nauc_recall_at_1000_max": -0.032929, + "nauc_recall_at_1000_std": 0.643086, + "nauc_recall_at_1000_diff1": -0.499284, + "nauc_precision_at_1_max": 0.218237, + "nauc_precision_at_1_std": 0.186456, + "nauc_precision_at_1_diff1": 0.260002, + "nauc_precision_at_3_max": 0.190504, + "nauc_precision_at_3_std": 0.312205, + "nauc_precision_at_3_diff1": 0.140362, + "nauc_precision_at_5_max": 0.136219, + "nauc_precision_at_5_std": 0.273161, + "nauc_precision_at_5_diff1": 0.102825, + "nauc_precision_at_10_max": 0.181272, + "nauc_precision_at_10_std": 0.329945, + "nauc_precision_at_10_diff1": 0.155696, + "nauc_precision_at_20_max": 0.212204, + "nauc_precision_at_20_std": 0.338196, + "nauc_precision_at_20_diff1": 0.087766, + "nauc_precision_at_100_max": 0.208458, + "nauc_precision_at_100_std": 0.447727, + "nauc_precision_at_100_diff1": -0.047314, + "nauc_precision_at_1000_max": 0.177066, + "nauc_precision_at_1000_std": 0.433088, + "nauc_precision_at_1000_diff1": -0.006448, + "nauc_mrr_at_1_max": 0.218237, + "nauc_mrr_at_1_std": 0.186456, + "nauc_mrr_at_1_diff1": 0.260002, + "nauc_mrr_at_3_max": 0.251511, + "nauc_mrr_at_3_std": 0.252604, + "nauc_mrr_at_3_diff1": 0.17881, + "nauc_mrr_at_5_max": 0.233058, + "nauc_mrr_at_5_std": 0.241839, + "nauc_mrr_at_5_diff1": 0.149832, + "nauc_mrr_at_10_max": 0.245582, + "nauc_mrr_at_10_std": 0.259405, + "nauc_mrr_at_10_diff1": 0.166836, + "nauc_mrr_at_20_max": 0.245552, + "nauc_mrr_at_20_std": 0.259417, + "nauc_mrr_at_20_diff1": 0.168501, + "nauc_mrr_at_100_max": 0.242888, + "nauc_mrr_at_100_std": 0.258351, + "nauc_mrr_at_100_diff1": 0.161608, + "nauc_mrr_at_1000_max": 0.242375, + "nauc_mrr_at_1000_std": 0.258173, + "nauc_mrr_at_1000_diff1": 0.162245, + "main_score": 0.14724, + "hf_subset": "IIYi-Clinical", + "languages": [ + "eng-Latn" + ] + } + ] + }, + "evaluation_time": 849.7474474906921, + "kg_co2_emissions": null +} \ No newline at end of file diff --git a/results/BAAI__bge-m3/5617a9f61b028005a4858fdac845db406aefb181/R2MEDRetrieval.json b/results/BAAI__bge-m3/5617a9f61b028005a4858fdac845db406aefb181/R2MEDRetrieval.json new file mode 100644 index 0000000000..e03b219829 --- /dev/null +++ b/results/BAAI__bge-m3/5617a9f61b028005a4858fdac845db406aefb181/R2MEDRetrieval.json @@ -0,0 +1,1187 @@ +{ + "dataset_revision": "1.0", + "task_name": "R2MEDRetrieval", + "mteb_version": "1.38.20", + "scores": { + "test": [ + { + "ndcg_at_1": 0.08738, + "ndcg_at_3": 0.07888, + "ndcg_at_5": 0.07816, + "ndcg_at_10": 0.09467, + "ndcg_at_20": 0.10858, + "ndcg_at_100": 0.14795, + "ndcg_at_1000": 0.21763, + "map_at_1": 0.0294, + "map_at_3": 0.04787, + "map_at_5": 0.05174, + "map_at_10": 0.06084, + "map_at_20": 0.06501, + "map_at_100": 0.07181, + "map_at_1000": 0.07496, + "recall_at_1": 0.0294, + "recall_at_3": 0.06052, + "recall_at_5": 0.06985, + "recall_at_10": 0.11242, + "recall_at_20": 0.15257, + "recall_at_100": 0.29764, + "recall_at_1000": 0.6997, + "precision_at_1": 0.08738, + "precision_at_3": 0.06796, + "precision_at_5": 0.05049, + "precision_at_10": 0.04175, + "precision_at_20": 0.02718, + "precision_at_100": 0.01117, + "precision_at_1000": 0.00255, + "mrr_at_1": 0.087379, + "mrr_at_3": 0.122977, + "mrr_at_5": 0.127832, + "mrr_at_10": 0.139197, + "mrr_at_20": 0.142956, + "mrr_at_100": 0.14712, + "mrr_at_1000": 0.148556, + "nauc_ndcg_at_1_max": 0.135072, + "nauc_ndcg_at_1_std": -0.162223, + "nauc_ndcg_at_1_diff1": 0.356229, + "nauc_ndcg_at_3_max": 0.055247, + "nauc_ndcg_at_3_std": -0.183744, + "nauc_ndcg_at_3_diff1": 0.248425, + "nauc_ndcg_at_5_max": 0.038237, + "nauc_ndcg_at_5_std": -0.19755, + "nauc_ndcg_at_5_diff1": 0.214113, + "nauc_ndcg_at_10_max": 0.05504, + "nauc_ndcg_at_10_std": -0.149417, + "nauc_ndcg_at_10_diff1": 0.206467, + "nauc_ndcg_at_20_max": 0.074254, + "nauc_ndcg_at_20_std": -0.127021, + "nauc_ndcg_at_20_diff1": 0.230028, + "nauc_ndcg_at_100_max": 0.018336, + "nauc_ndcg_at_100_std": -0.175408, + "nauc_ndcg_at_100_diff1": 0.231847, + "nauc_ndcg_at_1000_max": 0.007304, + "nauc_ndcg_at_1000_std": -0.147677, + "nauc_ndcg_at_1000_diff1": 0.24179, + "nauc_map_at_1_max": 0.07112, + "nauc_map_at_1_std": -0.115706, + "nauc_map_at_1_diff1": 0.271705, + "nauc_map_at_3_max": 0.038612, + "nauc_map_at_3_std": -0.188851, + "nauc_map_at_3_diff1": 0.214668, + "nauc_map_at_5_max": 0.031492, + "nauc_map_at_5_std": -0.202552, + "nauc_map_at_5_diff1": 0.196339, + "nauc_map_at_10_max": 0.059874, + "nauc_map_at_10_std": -0.174446, + "nauc_map_at_10_diff1": 0.220231, + "nauc_map_at_20_max": 0.068905, + "nauc_map_at_20_std": -0.159228, + "nauc_map_at_20_diff1": 0.225965, + "nauc_map_at_100_max": 0.050929, + "nauc_map_at_100_std": -0.1735, + "nauc_map_at_100_diff1": 0.225871, + "nauc_map_at_1000_max": 0.048044, + "nauc_map_at_1000_std": -0.171283, + "nauc_map_at_1000_diff1": 0.225052, + "nauc_recall_at_1_max": 0.07112, + "nauc_recall_at_1_std": -0.115706, + "nauc_recall_at_1_diff1": 0.271705, + "nauc_recall_at_3_max": 0.040553, + "nauc_recall_at_3_std": -0.182696, + "nauc_recall_at_3_diff1": 0.162461, + "nauc_recall_at_5_max": 0.01917, + "nauc_recall_at_5_std": -0.20137, + "nauc_recall_at_5_diff1": 0.117948, + "nauc_recall_at_10_max": 0.081368, + "nauc_recall_at_10_std": -0.112043, + "nauc_recall_at_10_diff1": 0.158149, + "nauc_recall_at_20_max": 0.134943, + "nauc_recall_at_20_std": -0.054405, + "nauc_recall_at_20_diff1": 0.233571, + "nauc_recall_at_100_max": 0.001078, + "nauc_recall_at_100_std": -0.173921, + "nauc_recall_at_100_diff1": 0.240887, + "nauc_recall_at_1000_max": -0.003642, + "nauc_recall_at_1000_std": -0.067691, + "nauc_recall_at_1000_diff1": 0.33018, + "nauc_precision_at_1_max": 0.135072, + "nauc_precision_at_1_std": -0.162223, + "nauc_precision_at_1_diff1": 0.356229, + "nauc_precision_at_3_max": 0.069949, + "nauc_precision_at_3_std": -0.180865, + "nauc_precision_at_3_diff1": 0.263183, + "nauc_precision_at_5_max": 0.028906, + "nauc_precision_at_5_std": -0.217717, + "nauc_precision_at_5_diff1": 0.224285, + "nauc_precision_at_10_max": 0.002097, + "nauc_precision_at_10_std": -0.16027, + "nauc_precision_at_10_diff1": 0.203186, + "nauc_precision_at_20_max": 0.020096, + "nauc_precision_at_20_std": -0.13425, + "nauc_precision_at_20_diff1": 0.219108, + "nauc_precision_at_100_max": -0.092095, + "nauc_precision_at_100_std": -0.213138, + "nauc_precision_at_100_diff1": 0.203892, + "nauc_precision_at_1000_max": -0.148978, + "nauc_precision_at_1000_std": -0.108611, + "nauc_precision_at_1000_diff1": 0.10482, + "nauc_mrr_at_1_max": 0.135072, + "nauc_mrr_at_1_std": -0.162223, + "nauc_mrr_at_1_diff1": 0.356229, + "nauc_mrr_at_3_max": 0.07824, + "nauc_mrr_at_3_std": -0.137855, + "nauc_mrr_at_3_diff1": 0.265768, + "nauc_mrr_at_5_max": 0.065134, + "nauc_mrr_at_5_std": -0.139822, + "nauc_mrr_at_5_diff1": 0.26175, + "nauc_mrr_at_10_max": 0.057653, + "nauc_mrr_at_10_std": -0.137991, + "nauc_mrr_at_10_diff1": 0.244958, + "nauc_mrr_at_20_max": 0.060109, + "nauc_mrr_at_20_std": -0.141369, + "nauc_mrr_at_20_diff1": 0.25005, + "nauc_mrr_at_100_max": 0.055092, + "nauc_mrr_at_100_std": -0.145213, + "nauc_mrr_at_100_diff1": 0.249328, + "nauc_mrr_at_1000_max": 0.055707, + "nauc_mrr_at_1000_std": -0.145231, + "nauc_mrr_at_1000_diff1": 0.249559, + "main_score": 0.09467, + "hf_subset": "Biology", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.20779, + "ndcg_at_3": 0.24807, + "ndcg_at_5": 0.26978, + "ndcg_at_10": 0.30159, + "ndcg_at_20": 0.33401, + "ndcg_at_100": 0.38615, + "ndcg_at_1000": 0.42303, + "map_at_1": 0.13961, + "map_at_3": 0.19285, + "map_at_5": 0.21203, + "map_at_10": 0.23323, + "map_at_20": 0.24418, + "map_at_100": 0.2544, + "map_at_1000": 0.25665, + "recall_at_1": 0.13961, + "recall_at_3": 0.24007, + "recall_at_5": 0.30328, + "recall_at_10": 0.3823, + "recall_at_20": 0.48114, + "recall_at_100": 0.68681, + "recall_at_1000": 0.90096, + "precision_at_1": 0.20779, + "precision_at_3": 0.1645, + "precision_at_5": 0.13506, + "precision_at_10": 0.09481, + "precision_at_20": 0.06039, + "precision_at_100": 0.01896, + "precision_at_1000": 0.00261, + "mrr_at_1": 0.207792, + "mrr_at_3": 0.292208, + "mrr_at_5": 0.322727, + "mrr_at_10": 0.32886, + "mrr_at_20": 0.337277, + "mrr_at_100": 0.340636, + "mrr_at_1000": 0.341075, + "nauc_ndcg_at_1_max": 0.115421, + "nauc_ndcg_at_1_std": 0.179988, + "nauc_ndcg_at_1_diff1": 0.150565, + "nauc_ndcg_at_3_max": 0.077802, + "nauc_ndcg_at_3_std": 0.152034, + "nauc_ndcg_at_3_diff1": 0.097364, + "nauc_ndcg_at_5_max": 0.12716, + "nauc_ndcg_at_5_std": 0.156195, + "nauc_ndcg_at_5_diff1": 0.078397, + "nauc_ndcg_at_10_max": 0.168675, + "nauc_ndcg_at_10_std": 0.198204, + "nauc_ndcg_at_10_diff1": 0.058909, + "nauc_ndcg_at_20_max": 0.1883, + "nauc_ndcg_at_20_std": 0.230585, + "nauc_ndcg_at_20_diff1": 0.068684, + "nauc_ndcg_at_100_max": 0.165093, + "nauc_ndcg_at_100_std": 0.248919, + "nauc_ndcg_at_100_diff1": 0.036563, + "nauc_ndcg_at_1000_max": 0.152006, + "nauc_ndcg_at_1000_std": 0.237983, + "nauc_ndcg_at_1000_diff1": 0.030711, + "nauc_map_at_1_max": 0.157008, + "nauc_map_at_1_std": 0.209285, + "nauc_map_at_1_diff1": 0.217708, + "nauc_map_at_3_max": 0.093092, + "nauc_map_at_3_std": 0.144685, + "nauc_map_at_3_diff1": 0.12849, + "nauc_map_at_5_max": 0.122427, + "nauc_map_at_5_std": 0.152053, + "nauc_map_at_5_diff1": 0.107377, + "nauc_map_at_10_max": 0.133374, + "nauc_map_at_10_std": 0.169312, + "nauc_map_at_10_diff1": 0.080218, + "nauc_map_at_20_max": 0.139639, + "nauc_map_at_20_std": 0.184108, + "nauc_map_at_20_diff1": 0.078675, + "nauc_map_at_100_max": 0.137966, + "nauc_map_at_100_std": 0.188821, + "nauc_map_at_100_diff1": 0.071069, + "nauc_map_at_1000_max": 0.137098, + "nauc_map_at_1000_std": 0.188898, + "nauc_map_at_1000_diff1": 0.071099, + "nauc_recall_at_1_max": 0.157008, + "nauc_recall_at_1_std": 0.209285, + "nauc_recall_at_1_diff1": 0.217708, + "nauc_recall_at_3_max": 0.07547, + "nauc_recall_at_3_std": 0.116881, + "nauc_recall_at_3_diff1": 0.067781, + "nauc_recall_at_5_max": 0.161619, + "nauc_recall_at_5_std": 0.126233, + "nauc_recall_at_5_diff1": 0.046021, + "nauc_recall_at_10_max": 0.247698, + "nauc_recall_at_10_std": 0.218314, + "nauc_recall_at_10_diff1": 0.035252, + "nauc_recall_at_20_max": 0.320275, + "nauc_recall_at_20_std": 0.315578, + "nauc_recall_at_20_diff1": 0.083058, + "nauc_recall_at_100_max": 0.177878, + "nauc_recall_at_100_std": 0.385289, + "nauc_recall_at_100_diff1": -0.091347, + "nauc_recall_at_1000_max": 0.0161, + "nauc_recall_at_1000_std": 0.432681, + "nauc_recall_at_1000_diff1": -0.418888, + "nauc_precision_at_1_max": 0.115421, + "nauc_precision_at_1_std": 0.179988, + "nauc_precision_at_1_diff1": 0.150565, + "nauc_precision_at_3_max": 0.003082, + "nauc_precision_at_3_std": 0.121573, + "nauc_precision_at_3_diff1": 0.018808, + "nauc_precision_at_5_max": 0.043634, + "nauc_precision_at_5_std": 0.106032, + "nauc_precision_at_5_diff1": -0.095991, + "nauc_precision_at_10_max": 0.122354, + "nauc_precision_at_10_std": 0.19528, + "nauc_precision_at_10_diff1": -0.151171, + "nauc_precision_at_20_max": 0.130465, + "nauc_precision_at_20_std": 0.239967, + "nauc_precision_at_20_diff1": -0.143404, + "nauc_precision_at_100_max": 0.089287, + "nauc_precision_at_100_std": 0.240317, + "nauc_precision_at_100_diff1": -0.145062, + "nauc_precision_at_1000_max": 0.013514, + "nauc_precision_at_1000_std": 0.118245, + "nauc_precision_at_1000_diff1": -0.132481, + "nauc_mrr_at_1_max": 0.115421, + "nauc_mrr_at_1_std": 0.179988, + "nauc_mrr_at_1_diff1": 0.150565, + "nauc_mrr_at_3_max": 0.110556, + "nauc_mrr_at_3_std": 0.17689, + "nauc_mrr_at_3_diff1": 0.101302, + "nauc_mrr_at_5_max": 0.121672, + "nauc_mrr_at_5_std": 0.177491, + "nauc_mrr_at_5_diff1": 0.082515, + "nauc_mrr_at_10_max": 0.135242, + "nauc_mrr_at_10_std": 0.188875, + "nauc_mrr_at_10_diff1": 0.087348, + "nauc_mrr_at_20_max": 0.13163, + "nauc_mrr_at_20_std": 0.185438, + "nauc_mrr_at_20_diff1": 0.094457, + "nauc_mrr_at_100_max": 0.128701, + "nauc_mrr_at_100_std": 0.185942, + "nauc_mrr_at_100_diff1": 0.091521, + "nauc_mrr_at_1000_max": 0.129108, + "nauc_mrr_at_1000_std": 0.186071, + "nauc_mrr_at_1000_diff1": 0.092046, + "main_score": 0.30159, + "hf_subset": "Bioinformatics", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.14773, + "ndcg_at_3": 0.21099, + "ndcg_at_5": 0.23364, + "ndcg_at_10": 0.2697, + "ndcg_at_20": 0.29006, + "ndcg_at_100": 0.34586, + "ndcg_at_1000": 0.38214, + "map_at_1": 0.09348, + "map_at_3": 0.15551, + "map_at_5": 0.17752, + "map_at_10": 0.19977, + "map_at_20": 0.20649, + "map_at_100": 0.21626, + "map_at_1000": 0.21848, + "recall_at_1": 0.09348, + "recall_at_3": 0.22505, + "recall_at_5": 0.29808, + "recall_at_10": 0.38506, + "recall_at_20": 0.44892, + "recall_at_100": 0.66978, + "recall_at_1000": 0.87831, + "precision_at_1": 0.14773, + "precision_at_3": 0.14773, + "precision_at_5": 0.11364, + "precision_at_10": 0.08409, + "precision_at_20": 0.05, + "precision_at_100": 0.01693, + "precision_at_1000": 0.00233, + "mrr_at_1": 0.147727, + "mrr_at_3": 0.248106, + "mrr_at_5": 0.264583, + "mrr_at_10": 0.272678, + "mrr_at_20": 0.278522, + "mrr_at_100": 0.284961, + "mrr_at_1000": 0.285653, + "nauc_ndcg_at_1_max": 0.24504, + "nauc_ndcg_at_1_std": -0.022277, + "nauc_ndcg_at_1_diff1": 0.139059, + "nauc_ndcg_at_3_max": 0.190231, + "nauc_ndcg_at_3_std": -0.089593, + "nauc_ndcg_at_3_diff1": 0.118833, + "nauc_ndcg_at_5_max": 0.208674, + "nauc_ndcg_at_5_std": -0.096427, + "nauc_ndcg_at_5_diff1": 0.146187, + "nauc_ndcg_at_10_max": 0.239338, + "nauc_ndcg_at_10_std": -0.050609, + "nauc_ndcg_at_10_diff1": 0.158925, + "nauc_ndcg_at_20_max": 0.246969, + "nauc_ndcg_at_20_std": -0.074475, + "nauc_ndcg_at_20_diff1": 0.154949, + "nauc_ndcg_at_100_max": 0.269243, + "nauc_ndcg_at_100_std": -0.028874, + "nauc_ndcg_at_100_diff1": 0.143036, + "nauc_ndcg_at_1000_max": 0.24353, + "nauc_ndcg_at_1000_std": -0.032361, + "nauc_ndcg_at_1000_diff1": 0.125075, + "nauc_map_at_1_max": 0.090035, + "nauc_map_at_1_std": -0.238247, + "nauc_map_at_1_diff1": 0.203416, + "nauc_map_at_3_max": 0.136613, + "nauc_map_at_3_std": -0.166927, + "nauc_map_at_3_diff1": 0.149006, + "nauc_map_at_5_max": 0.171557, + "nauc_map_at_5_std": -0.143982, + "nauc_map_at_5_diff1": 0.159702, + "nauc_map_at_10_max": 0.197312, + "nauc_map_at_10_std": -0.1063, + "nauc_map_at_10_diff1": 0.161507, + "nauc_map_at_20_max": 0.201674, + "nauc_map_at_20_std": -0.113916, + "nauc_map_at_20_diff1": 0.160612, + "nauc_map_at_100_max": 0.20488, + "nauc_map_at_100_std": -0.107842, + "nauc_map_at_100_diff1": 0.156476, + "nauc_map_at_1000_max": 0.202626, + "nauc_map_at_1000_std": -0.108116, + "nauc_map_at_1000_diff1": 0.15364, + "nauc_recall_at_1_max": 0.090035, + "nauc_recall_at_1_std": -0.238247, + "nauc_recall_at_1_diff1": 0.203416, + "nauc_recall_at_3_max": 0.132575, + "nauc_recall_at_3_std": -0.128862, + "nauc_recall_at_3_diff1": 0.102296, + "nauc_recall_at_5_max": 0.179663, + "nauc_recall_at_5_std": -0.099701, + "nauc_recall_at_5_diff1": 0.133066, + "nauc_recall_at_10_max": 0.232369, + "nauc_recall_at_10_std": -0.022442, + "nauc_recall_at_10_diff1": 0.142244, + "nauc_recall_at_20_max": 0.248215, + "nauc_recall_at_20_std": -0.087558, + "nauc_recall_at_20_diff1": 0.133533, + "nauc_recall_at_100_max": 0.339964, + "nauc_recall_at_100_std": 0.099153, + "nauc_recall_at_100_diff1": 0.112591, + "nauc_recall_at_1000_max": 0.113611, + "nauc_recall_at_1000_std": 0.118757, + "nauc_recall_at_1000_diff1": 0.113729, + "nauc_precision_at_1_max": 0.24504, + "nauc_precision_at_1_std": -0.022277, + "nauc_precision_at_1_diff1": 0.139059, + "nauc_precision_at_3_max": 0.302367, + "nauc_precision_at_3_std": 0.082871, + "nauc_precision_at_3_diff1": 0.067006, + "nauc_precision_at_5_max": 0.310875, + "nauc_precision_at_5_std": 0.079331, + "nauc_precision_at_5_diff1": 0.069493, + "nauc_precision_at_10_max": 0.309961, + "nauc_precision_at_10_std": 0.143662, + "nauc_precision_at_10_diff1": 0.064855, + "nauc_precision_at_20_max": 0.307687, + "nauc_precision_at_20_std": 0.088192, + "nauc_precision_at_20_diff1": 0.033171, + "nauc_precision_at_100_max": 0.279703, + "nauc_precision_at_100_std": 0.195077, + "nauc_precision_at_100_diff1": -0.046278, + "nauc_precision_at_1000_max": 0.13141, + "nauc_precision_at_1000_std": 0.207767, + "nauc_precision_at_1000_diff1": -0.170294, + "nauc_mrr_at_1_max": 0.24504, + "nauc_mrr_at_1_std": -0.022277, + "nauc_mrr_at_1_diff1": 0.139059, + "nauc_mrr_at_3_max": 0.264865, + "nauc_mrr_at_3_std": 0.004808, + "nauc_mrr_at_3_diff1": 0.130137, + "nauc_mrr_at_5_max": 0.275508, + "nauc_mrr_at_5_std": 0.003096, + "nauc_mrr_at_5_diff1": 0.142466, + "nauc_mrr_at_10_max": 0.269205, + "nauc_mrr_at_10_std": -0.004667, + "nauc_mrr_at_10_diff1": 0.148103, + "nauc_mrr_at_20_max": 0.27206, + "nauc_mrr_at_20_std": -0.008811, + "nauc_mrr_at_20_diff1": 0.147855, + "nauc_mrr_at_100_max": 0.274183, + "nauc_mrr_at_100_std": -0.003836, + "nauc_mrr_at_100_diff1": 0.144619, + "nauc_mrr_at_1000_max": 0.273388, + "nauc_mrr_at_1000_std": -0.004583, + "nauc_mrr_at_1000_diff1": 0.144275, + "main_score": 0.2697, + "hf_subset": "Medical-Sciences", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.01031, + "ndcg_at_3": 0.01883, + "ndcg_at_5": 0.0187, + "ndcg_at_10": 0.01971, + "ndcg_at_20": 0.02616, + "ndcg_at_100": 0.04429, + "ndcg_at_1000": 0.08067, + "map_at_1": 0.01031, + "map_at_3": 0.01352, + "map_at_5": 0.01403, + "map_at_10": 0.01444, + "map_at_20": 0.01613, + "map_at_100": 0.01875, + "map_at_1000": 0.01983, + "recall_at_1": 0.01031, + "recall_at_3": 0.01787, + "recall_at_5": 0.02045, + "recall_at_10": 0.02251, + "recall_at_20": 0.03866, + "recall_at_100": 0.10868, + "recall_at_1000": 0.33887, + "precision_at_1": 0.01031, + "precision_at_3": 0.01375, + "precision_at_5": 0.01031, + "precision_at_10": 0.00619, + "precision_at_20": 0.00619, + "precision_at_100": 0.0033, + "precision_at_1000": 0.00099, + "mrr_at_1": 0.010309, + "mrr_at_3": 0.024055, + "mrr_at_5": 0.026117, + "mrr_at_10": 0.026117, + "mrr_at_20": 0.029243, + "mrr_at_100": 0.032989, + "mrr_at_1000": 0.034186, + "nauc_ndcg_at_1_max": -0.577278, + "nauc_ndcg_at_1_std": -0.577278, + "nauc_ndcg_at_1_diff1": -0.072193, + "nauc_ndcg_at_3_max": -0.105502, + "nauc_ndcg_at_3_std": -0.355506, + "nauc_ndcg_at_3_diff1": 0.060128, + "nauc_ndcg_at_5_max": -0.147014, + "nauc_ndcg_at_5_std": -0.37025, + "nauc_ndcg_at_5_diff1": 0.033875, + "nauc_ndcg_at_10_max": -0.105082, + "nauc_ndcg_at_10_std": -0.372653, + "nauc_ndcg_at_10_diff1": 0.006416, + "nauc_ndcg_at_20_max": -0.097491, + "nauc_ndcg_at_20_std": -0.269936, + "nauc_ndcg_at_20_diff1": 0.00544, + "nauc_ndcg_at_100_max": -0.101925, + "nauc_ndcg_at_100_std": -0.199441, + "nauc_ndcg_at_100_diff1": 0.105354, + "nauc_ndcg_at_1000_max": -0.062503, + "nauc_ndcg_at_1000_std": -0.13701, + "nauc_ndcg_at_1000_diff1": 0.064677, + "nauc_map_at_1_max": -0.577278, + "nauc_map_at_1_std": -0.577278, + "nauc_map_at_1_diff1": -0.072193, + "nauc_map_at_3_max": -0.32494, + "nauc_map_at_3_std": -0.456535, + "nauc_map_at_3_diff1": 0.016132, + "nauc_map_at_5_max": -0.315655, + "nauc_map_at_5_std": -0.451528, + "nauc_map_at_5_diff1": 0.000218, + "nauc_map_at_10_max": -0.287498, + "nauc_map_at_10_std": -0.450545, + "nauc_map_at_10_diff1": -0.014107, + "nauc_map_at_20_max": -0.26082, + "nauc_map_at_20_std": -0.401053, + "nauc_map_at_20_diff1": -0.002336, + "nauc_map_at_100_max": -0.245544, + "nauc_map_at_100_std": -0.364915, + "nauc_map_at_100_diff1": 0.033692, + "nauc_map_at_1000_max": -0.234211, + "nauc_map_at_1000_std": -0.35286, + "nauc_map_at_1000_diff1": 0.037395, + "nauc_recall_at_1_max": -0.577278, + "nauc_recall_at_1_std": -0.577278, + "nauc_recall_at_1_diff1": -0.072193, + "nauc_recall_at_3_max": -0.115542, + "nauc_recall_at_3_std": -0.35141, + "nauc_recall_at_3_diff1": 0.130158, + "nauc_recall_at_5_max": -0.110078, + "nauc_recall_at_5_std": -0.347479, + "nauc_recall_at_5_diff1": 0.061176, + "nauc_recall_at_10_max": -0.038565, + "nauc_recall_at_10_std": -0.353856, + "nauc_recall_at_10_diff1": 0.009628, + "nauc_recall_at_20_max": -0.053943, + "nauc_recall_at_20_std": -0.172758, + "nauc_recall_at_20_diff1": -0.001653, + "nauc_recall_at_100_max": -0.085507, + "nauc_recall_at_100_std": -0.101724, + "nauc_recall_at_100_diff1": 0.171849, + "nauc_recall_at_1000_max": -0.028745, + "nauc_recall_at_1000_std": -0.031253, + "nauc_recall_at_1000_diff1": 0.059789, + "nauc_precision_at_1_max": -0.577278, + "nauc_precision_at_1_std": -0.577278, + "nauc_precision_at_1_diff1": -0.072193, + "nauc_precision_at_3_max": 0.215168, + "nauc_precision_at_3_std": -0.200232, + "nauc_precision_at_3_diff1": 0.187535, + "nauc_precision_at_5_max": 0.157695, + "nauc_precision_at_5_std": -0.22423, + "nauc_precision_at_5_diff1": 0.066608, + "nauc_precision_at_10_max": 0.243181, + "nauc_precision_at_10_std": -0.256374, + "nauc_precision_at_10_diff1": -0.028086, + "nauc_precision_at_20_max": 0.088506, + "nauc_precision_at_20_std": -0.097227, + "nauc_precision_at_20_diff1": -0.009267, + "nauc_precision_at_100_max": 3.7e-05, + "nauc_precision_at_100_std": -0.069614, + "nauc_precision_at_100_diff1": 0.135145, + "nauc_precision_at_1000_max": 0.030699, + "nauc_precision_at_1000_std": -3.6e-05, + "nauc_precision_at_1000_diff1": -0.017653, + "nauc_mrr_at_1_max": -0.577278, + "nauc_mrr_at_1_std": -0.577278, + "nauc_mrr_at_1_diff1": -0.072193, + "nauc_mrr_at_3_max": 0.012826, + "nauc_mrr_at_3_std": -0.302239, + "nauc_mrr_at_3_diff1": 0.073845, + "nauc_mrr_at_5_max": 0.006114, + "nauc_mrr_at_5_std": -0.303658, + "nauc_mrr_at_5_diff1": 0.035087, + "nauc_mrr_at_10_max": 0.006114, + "nauc_mrr_at_10_std": -0.303658, + "nauc_mrr_at_10_diff1": 0.035087, + "nauc_mrr_at_20_max": -0.010894, + "nauc_mrr_at_20_std": -0.277046, + "nauc_mrr_at_20_diff1": 0.019357, + "nauc_mrr_at_100_max": -0.023947, + "nauc_mrr_at_100_std": -0.262046, + "nauc_mrr_at_100_diff1": 0.038758, + "nauc_mrr_at_1000_max": -0.024492, + "nauc_mrr_at_1000_std": -0.259002, + "nauc_mrr_at_1000_diff1": 0.037648, + "main_score": 0.01971, + "hf_subset": "MedXpertQA-Exam", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.01695, + "ndcg_at_3": 0.02905, + "ndcg_at_5": 0.03251, + "ndcg_at_10": 0.03667, + "ndcg_at_20": 0.04853, + "ndcg_at_100": 0.06614, + "ndcg_at_1000": 0.11312, + "map_at_1": 0.00381, + "map_at_3": 0.01545, + "map_at_5": 0.01887, + "map_at_10": 0.02018, + "map_at_20": 0.02403, + "map_at_100": 0.02702, + "map_at_1000": 0.02877, + "recall_at_1": 0.00381, + "recall_at_3": 0.02422, + "recall_at_5": 0.03709, + "recall_at_10": 0.04832, + "recall_at_20": 0.0765, + "recall_at_100": 0.14008, + "recall_at_1000": 0.40192, + "precision_at_1": 0.01695, + "precision_at_3": 0.02825, + "precision_at_5": 0.02542, + "precision_at_10": 0.01695, + "precision_at_20": 0.01568, + "precision_at_100": 0.00534, + "precision_at_1000": 0.00157, + "mrr_at_1": 0.016949, + "mrr_at_3": 0.04096, + "mrr_at_5": 0.048164, + "mrr_at_10": 0.052953, + "mrr_at_20": 0.056998, + "mrr_at_100": 0.060298, + "mrr_at_1000": 0.061549, + "nauc_ndcg_at_1_max": -0.19627, + "nauc_ndcg_at_1_std": 0.329587, + "nauc_ndcg_at_1_diff1": -0.044221, + "nauc_ndcg_at_3_max": -0.03312, + "nauc_ndcg_at_3_std": 0.208545, + "nauc_ndcg_at_3_diff1": 0.080705, + "nauc_ndcg_at_5_max": -0.069252, + "nauc_ndcg_at_5_std": 0.229556, + "nauc_ndcg_at_5_diff1": -0.018167, + "nauc_ndcg_at_10_max": -0.093499, + "nauc_ndcg_at_10_std": 0.188692, + "nauc_ndcg_at_10_diff1": -0.034639, + "nauc_ndcg_at_20_max": -0.036764, + "nauc_ndcg_at_20_std": 0.269893, + "nauc_ndcg_at_20_diff1": 0.039766, + "nauc_ndcg_at_100_max": -0.024554, + "nauc_ndcg_at_100_std": 0.333138, + "nauc_ndcg_at_100_diff1": 0.012407, + "nauc_ndcg_at_1000_max": -0.058492, + "nauc_ndcg_at_1000_std": 0.236584, + "nauc_ndcg_at_1000_diff1": -0.001888, + "nauc_map_at_1_max": -0.21014, + "nauc_map_at_1_std": 0.329587, + "nauc_map_at_1_diff1": -0.085755, + "nauc_map_at_3_max": -0.13819, + "nauc_map_at_3_std": 0.181256, + "nauc_map_at_3_diff1": 0.006778, + "nauc_map_at_5_max": -0.105587, + "nauc_map_at_5_std": 0.245462, + "nauc_map_at_5_diff1": -0.039588, + "nauc_map_at_10_max": -0.106435, + "nauc_map_at_10_std": 0.218002, + "nauc_map_at_10_diff1": -0.041285, + "nauc_map_at_20_max": -0.074653, + "nauc_map_at_20_std": 0.268084, + "nauc_map_at_20_diff1": -0.01024, + "nauc_map_at_100_max": -0.067636, + "nauc_map_at_100_std": 0.297499, + "nauc_map_at_100_diff1": -0.0228, + "nauc_map_at_1000_max": -0.062254, + "nauc_map_at_1000_std": 0.293293, + "nauc_map_at_1000_diff1": -0.017634, + "nauc_recall_at_1_max": -0.21014, + "nauc_recall_at_1_std": 0.329587, + "nauc_recall_at_1_diff1": -0.085755, + "nauc_recall_at_3_max": -0.084321, + "nauc_recall_at_3_std": 0.166378, + "nauc_recall_at_3_diff1": 0.023168, + "nauc_recall_at_5_max": -0.11235, + "nauc_recall_at_5_std": 0.260526, + "nauc_recall_at_5_diff1": -0.081665, + "nauc_recall_at_10_max": -0.128136, + "nauc_recall_at_10_std": 0.150931, + "nauc_recall_at_10_diff1": -0.083368, + "nauc_recall_at_20_max": -0.034074, + "nauc_recall_at_20_std": 0.292199, + "nauc_recall_at_20_diff1": 0.042674, + "nauc_recall_at_100_max": -0.023981, + "nauc_recall_at_100_std": 0.388932, + "nauc_recall_at_100_diff1": -0.013975, + "nauc_recall_at_1000_max": -0.118459, + "nauc_recall_at_1000_std": 0.114335, + "nauc_recall_at_1000_diff1": -0.049331, + "nauc_precision_at_1_max": -0.19627, + "nauc_precision_at_1_std": 0.329587, + "nauc_precision_at_1_diff1": -0.044221, + "nauc_precision_at_3_max": 0.029298, + "nauc_precision_at_3_std": 0.25185, + "nauc_precision_at_3_diff1": 0.088196, + "nauc_precision_at_5_max": -1.1e-05, + "nauc_precision_at_5_std": 0.257462, + "nauc_precision_at_5_diff1": -0.013856, + "nauc_precision_at_10_max": -0.04818, + "nauc_precision_at_10_std": 0.167878, + "nauc_precision_at_10_diff1": -0.015113, + "nauc_precision_at_20_max": 0.030205, + "nauc_precision_at_20_std": 0.299599, + "nauc_precision_at_20_diff1": 0.123795, + "nauc_precision_at_100_max": 0.065439, + "nauc_precision_at_100_std": 0.376788, + "nauc_precision_at_100_diff1": 0.084631, + "nauc_precision_at_1000_max": -0.018557, + "nauc_precision_at_1000_std": 0.154654, + "nauc_precision_at_1000_diff1": 0.031051, + "nauc_mrr_at_1_max": -0.19627, + "nauc_mrr_at_1_std": 0.329587, + "nauc_mrr_at_1_diff1": -0.044221, + "nauc_mrr_at_3_max": 0.007384, + "nauc_mrr_at_3_std": 0.226052, + "nauc_mrr_at_3_diff1": 0.10231, + "nauc_mrr_at_5_max": -0.042052, + "nauc_mrr_at_5_std": 0.207229, + "nauc_mrr_at_5_diff1": 0.047494, + "nauc_mrr_at_10_max": -0.050615, + "nauc_mrr_at_10_std": 0.180573, + "nauc_mrr_at_10_diff1": 0.044952, + "nauc_mrr_at_20_max": -0.021424, + "nauc_mrr_at_20_std": 0.207933, + "nauc_mrr_at_20_diff1": 0.074177, + "nauc_mrr_at_100_max": -0.022422, + "nauc_mrr_at_100_std": 0.215087, + "nauc_mrr_at_100_diff1": 0.066524, + "nauc_mrr_at_1000_max": -0.025393, + "nauc_mrr_at_1000_std": 0.211387, + "nauc_mrr_at_1000_diff1": 0.065948, + "main_score": 0.03667, + "hf_subset": "MedQA-Diag", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.18, + "ndcg_at_3": 0.16267, + "ndcg_at_5": 0.16682, + "ndcg_at_10": 0.17853, + "ndcg_at_20": 0.2022, + "ndcg_at_100": 0.2219, + "ndcg_at_1000": 0.26155, + "map_at_1": 0.10511, + "map_at_3": 0.13252, + "map_at_5": 0.1383, + "map_at_10": 0.14462, + "map_at_20": 0.1512, + "map_at_100": 0.15364, + "map_at_1000": 0.15533, + "recall_at_1": 0.10511, + "recall_at_3": 0.15667, + "recall_at_5": 0.17656, + "recall_at_10": 0.20356, + "recall_at_20": 0.28478, + "recall_at_100": 0.37744, + "recall_at_1000": 0.63944, + "precision_at_1": 0.18, + "precision_at_3": 0.09778, + "precision_at_5": 0.06667, + "precision_at_10": 0.04067, + "precision_at_20": 0.027, + "precision_at_100": 0.0074, + "precision_at_1000": 0.00129, + "mrr_at_1": 0.18, + "mrr_at_3": 0.213333, + "mrr_at_5": 0.219667, + "mrr_at_10": 0.224627, + "mrr_at_20": 0.232954, + "mrr_at_100": 0.235436, + "mrr_at_1000": 0.236428, + "nauc_ndcg_at_1_max": 0.289081, + "nauc_ndcg_at_1_std": -0.048042, + "nauc_ndcg_at_1_diff1": 0.467495, + "nauc_ndcg_at_3_max": 0.284421, + "nauc_ndcg_at_3_std": -0.10885, + "nauc_ndcg_at_3_diff1": 0.398937, + "nauc_ndcg_at_5_max": 0.266373, + "nauc_ndcg_at_5_std": -0.102849, + "nauc_ndcg_at_5_diff1": 0.375366, + "nauc_ndcg_at_10_max": 0.284233, + "nauc_ndcg_at_10_std": -0.091236, + "nauc_ndcg_at_10_diff1": 0.365073, + "nauc_ndcg_at_20_max": 0.294015, + "nauc_ndcg_at_20_std": -0.038156, + "nauc_ndcg_at_20_diff1": 0.378397, + "nauc_ndcg_at_100_max": 0.292878, + "nauc_ndcg_at_100_std": -0.017708, + "nauc_ndcg_at_100_diff1": 0.350166, + "nauc_ndcg_at_1000_max": 0.304381, + "nauc_ndcg_at_1000_std": -0.025854, + "nauc_ndcg_at_1000_diff1": 0.375981, + "nauc_map_at_1_max": 0.253298, + "nauc_map_at_1_std": -0.08305, + "nauc_map_at_1_diff1": 0.463589, + "nauc_map_at_3_max": 0.26004, + "nauc_map_at_3_std": -0.112802, + "nauc_map_at_3_diff1": 0.414238, + "nauc_map_at_5_max": 0.255712, + "nauc_map_at_5_std": -0.107548, + "nauc_map_at_5_diff1": 0.398083, + "nauc_map_at_10_max": 0.270467, + "nauc_map_at_10_std": -0.103278, + "nauc_map_at_10_diff1": 0.387296, + "nauc_map_at_20_max": 0.276113, + "nauc_map_at_20_std": -0.083925, + "nauc_map_at_20_diff1": 0.391465, + "nauc_map_at_100_max": 0.276882, + "nauc_map_at_100_std": -0.080661, + "nauc_map_at_100_diff1": 0.387097, + "nauc_map_at_1000_max": 0.27782, + "nauc_map_at_1000_std": -0.080198, + "nauc_map_at_1000_diff1": 0.388478, + "nauc_recall_at_1_max": 0.253298, + "nauc_recall_at_1_std": -0.08305, + "nauc_recall_at_1_diff1": 0.463589, + "nauc_recall_at_3_max": 0.259439, + "nauc_recall_at_3_std": -0.128447, + "nauc_recall_at_3_diff1": 0.373939, + "nauc_recall_at_5_max": 0.217537, + "nauc_recall_at_5_std": -0.12135, + "nauc_recall_at_5_diff1": 0.305656, + "nauc_recall_at_10_max": 0.266604, + "nauc_recall_at_10_std": -0.083432, + "nauc_recall_at_10_diff1": 0.29288, + "nauc_recall_at_20_max": 0.254768, + "nauc_recall_at_20_std": 0.072301, + "nauc_recall_at_20_diff1": 0.297687, + "nauc_recall_at_100_max": 0.223858, + "nauc_recall_at_100_std": 0.133306, + "nauc_recall_at_100_diff1": 0.183797, + "nauc_recall_at_1000_max": 0.238169, + "nauc_recall_at_1000_std": 0.114059, + "nauc_recall_at_1000_diff1": 0.257236, + "nauc_precision_at_1_max": 0.289081, + "nauc_precision_at_1_std": -0.048042, + "nauc_precision_at_1_diff1": 0.467495, + "nauc_precision_at_3_max": 0.347502, + "nauc_precision_at_3_std": -0.105206, + "nauc_precision_at_3_diff1": 0.353547, + "nauc_precision_at_5_max": 0.344539, + "nauc_precision_at_5_std": -0.080511, + "nauc_precision_at_5_diff1": 0.292813, + "nauc_precision_at_10_max": 0.37707, + "nauc_precision_at_10_std": -0.074455, + "nauc_precision_at_10_diff1": 0.265198, + "nauc_precision_at_20_max": 0.419259, + "nauc_precision_at_20_std": 0.040752, + "nauc_precision_at_20_diff1": 0.317519, + "nauc_precision_at_100_max": 0.377649, + "nauc_precision_at_100_std": 0.114407, + "nauc_precision_at_100_diff1": 0.164713, + "nauc_precision_at_1000_max": 0.333071, + "nauc_precision_at_1000_std": 0.051956, + "nauc_precision_at_1000_diff1": 0.204611, + "nauc_mrr_at_1_max": 0.289081, + "nauc_mrr_at_1_std": -0.048042, + "nauc_mrr_at_1_diff1": 0.467495, + "nauc_mrr_at_3_max": 0.31816, + "nauc_mrr_at_3_std": -0.069595, + "nauc_mrr_at_3_diff1": 0.419291, + "nauc_mrr_at_5_max": 0.304633, + "nauc_mrr_at_5_std": -0.069949, + "nauc_mrr_at_5_diff1": 0.398333, + "nauc_mrr_at_10_max": 0.300095, + "nauc_mrr_at_10_std": -0.069324, + "nauc_mrr_at_10_diff1": 0.394195, + "nauc_mrr_at_20_max": 0.30247, + "nauc_mrr_at_20_std": -0.056349, + "nauc_mrr_at_20_diff1": 0.400932, + "nauc_mrr_at_100_max": 0.302705, + "nauc_mrr_at_100_std": -0.053671, + "nauc_mrr_at_100_diff1": 0.398324, + "nauc_mrr_at_1000_max": 0.302747, + "nauc_mrr_at_1000_std": -0.054481, + "nauc_mrr_at_1000_diff1": 0.398997, + "main_score": 0.17853, + "hf_subset": "PMC-Treatment", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.08772, + "ndcg_at_3": 0.0777, + "ndcg_at_5": 0.08726, + "ndcg_at_10": 0.11361, + "ndcg_at_20": 0.13119, + "ndcg_at_100": 0.17201, + "ndcg_at_1000": 0.21464, + "map_at_1": 0.03655, + "map_at_3": 0.05251, + "map_at_5": 0.05828, + "map_at_10": 0.06916, + "map_at_20": 0.07417, + "map_at_100": 0.07973, + "map_at_1000": 0.08174, + "recall_at_1": 0.03655, + "recall_at_3": 0.07749, + "recall_at_5": 0.09942, + "recall_at_10": 0.16886, + "recall_at_20": 0.22661, + "recall_at_100": 0.41813, + "recall_at_1000": 0.68787, + "precision_at_1": 0.08772, + "precision_at_3": 0.05848, + "precision_at_5": 0.04737, + "precision_at_10": 0.03596, + "precision_at_20": 0.02412, + "precision_at_100": 0.0086, + "precision_at_1000": 0.00148, + "mrr_at_1": 0.087719, + "mrr_at_3": 0.124269, + "mrr_at_5": 0.136988, + "mrr_at_10": 0.150118, + "mrr_at_20": 0.154737, + "mrr_at_100": 0.15959, + "mrr_at_1000": 0.160561, + "nauc_ndcg_at_1_max": 0.036054, + "nauc_ndcg_at_1_std": -0.237006, + "nauc_ndcg_at_1_diff1": 0.427545, + "nauc_ndcg_at_3_max": 0.078228, + "nauc_ndcg_at_3_std": -0.243034, + "nauc_ndcg_at_3_diff1": 0.285055, + "nauc_ndcg_at_5_max": 0.052606, + "nauc_ndcg_at_5_std": -0.214385, + "nauc_ndcg_at_5_diff1": 0.251495, + "nauc_ndcg_at_10_max": 0.005953, + "nauc_ndcg_at_10_std": -0.183081, + "nauc_ndcg_at_10_diff1": 0.196586, + "nauc_ndcg_at_20_max": 0.058744, + "nauc_ndcg_at_20_std": -0.109258, + "nauc_ndcg_at_20_diff1": 0.20474, + "nauc_ndcg_at_100_max": 0.105439, + "nauc_ndcg_at_100_std": -0.040028, + "nauc_ndcg_at_100_diff1": 0.222633, + "nauc_ndcg_at_1000_max": 0.15136, + "nauc_ndcg_at_1000_std": -0.017048, + "nauc_ndcg_at_1000_diff1": 0.245766, + "nauc_map_at_1_max": 0.001222, + "nauc_map_at_1_std": -0.265079, + "nauc_map_at_1_diff1": 0.342635, + "nauc_map_at_3_max": 0.062746, + "nauc_map_at_3_std": -0.249005, + "nauc_map_at_3_diff1": 0.282876, + "nauc_map_at_5_max": 0.045667, + "nauc_map_at_5_std": -0.228798, + "nauc_map_at_5_diff1": 0.257871, + "nauc_map_at_10_max": 0.023357, + "nauc_map_at_10_std": -0.215852, + "nauc_map_at_10_diff1": 0.230645, + "nauc_map_at_20_max": 0.049613, + "nauc_map_at_20_std": -0.183023, + "nauc_map_at_20_diff1": 0.237014, + "nauc_map_at_100_max": 0.057866, + "nauc_map_at_100_std": -0.168805, + "nauc_map_at_100_diff1": 0.236524, + "nauc_map_at_1000_max": 0.06401, + "nauc_map_at_1000_std": -0.163608, + "nauc_map_at_1000_diff1": 0.237261, + "nauc_recall_at_1_max": 0.001222, + "nauc_recall_at_1_std": -0.265079, + "nauc_recall_at_1_diff1": 0.342635, + "nauc_recall_at_3_max": 0.092787, + "nauc_recall_at_3_std": -0.23021, + "nauc_recall_at_3_diff1": 0.213547, + "nauc_recall_at_5_max": 0.034715, + "nauc_recall_at_5_std": -0.18321, + "nauc_recall_at_5_diff1": 0.16169, + "nauc_recall_at_10_max": -0.061343, + "nauc_recall_at_10_std": -0.121525, + "nauc_recall_at_10_diff1": 0.066581, + "nauc_recall_at_20_max": 0.04933, + "nauc_recall_at_20_std": 0.029746, + "nauc_recall_at_20_diff1": 0.090495, + "nauc_recall_at_100_max": 0.118512, + "nauc_recall_at_100_std": 0.187715, + "nauc_recall_at_100_diff1": 0.111188, + "nauc_recall_at_1000_max": 0.266983, + "nauc_recall_at_1000_std": 0.313689, + "nauc_recall_at_1000_diff1": 0.18503, + "nauc_precision_at_1_max": 0.036054, + "nauc_precision_at_1_std": -0.237006, + "nauc_precision_at_1_diff1": 0.427545, + "nauc_precision_at_3_max": 0.119912, + "nauc_precision_at_3_std": -0.244759, + "nauc_precision_at_3_diff1": 0.272339, + "nauc_precision_at_5_max": 0.052059, + "nauc_precision_at_5_std": -0.188066, + "nauc_precision_at_5_diff1": 0.195397, + "nauc_precision_at_10_max": 0.003422, + "nauc_precision_at_10_std": -0.125321, + "nauc_precision_at_10_diff1": 0.133827, + "nauc_precision_at_20_max": 0.126156, + "nauc_precision_at_20_std": 0.041408, + "nauc_precision_at_20_diff1": 0.135306, + "nauc_precision_at_100_max": 0.257087, + "nauc_precision_at_100_std": 0.196166, + "nauc_precision_at_100_diff1": 0.18132, + "nauc_precision_at_1000_max": 0.32458, + "nauc_precision_at_1000_std": 0.193448, + "nauc_precision_at_1000_diff1": 0.224822, + "nauc_mrr_at_1_max": 0.036054, + "nauc_mrr_at_1_std": -0.237006, + "nauc_mrr_at_1_diff1": 0.427545, + "nauc_mrr_at_3_max": 0.087892, + "nauc_mrr_at_3_std": -0.233813, + "nauc_mrr_at_3_diff1": 0.342442, + "nauc_mrr_at_5_max": 0.061915, + "nauc_mrr_at_5_std": -0.218535, + "nauc_mrr_at_5_diff1": 0.322582, + "nauc_mrr_at_10_max": 0.041904, + "nauc_mrr_at_10_std": -0.197887, + "nauc_mrr_at_10_diff1": 0.29248, + "nauc_mrr_at_20_max": 0.048132, + "nauc_mrr_at_20_std": -0.18956, + "nauc_mrr_at_20_diff1": 0.293634, + "nauc_mrr_at_100_max": 0.056784, + "nauc_mrr_at_100_std": -0.184989, + "nauc_mrr_at_100_diff1": 0.299667, + "nauc_mrr_at_1000_max": 0.057465, + "nauc_mrr_at_1000_std": -0.185305, + "nauc_mrr_at_1000_diff1": 0.300178, + "main_score": 0.11361, + "hf_subset": "PMC-Clinical", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.13178, + "ndcg_at_3": 0.11921, + "ndcg_at_5": 0.13667, + "ndcg_at_10": 0.17731, + "ndcg_at_20": 0.21274, + "ndcg_at_100": 0.28619, + "ndcg_at_1000": 0.34572, + "map_at_1": 0.04832, + "map_at_3": 0.0742, + "map_at_5": 0.08756, + "map_at_10": 0.10504, + "map_at_20": 0.11669, + "map_at_100": 0.13216, + "map_at_1000": 0.13635, + "recall_at_1": 0.04832, + "recall_at_3": 0.09729, + "recall_at_5": 0.14716, + "recall_at_10": 0.23786, + "recall_at_20": 0.33243, + "recall_at_100": 0.60517, + "recall_at_1000": 0.92196, + "precision_at_1": 0.13178, + "precision_at_3": 0.09302, + "precision_at_5": 0.09147, + "precision_at_10": 0.07829, + "precision_at_20": 0.05698, + "precision_at_100": 0.0214, + "precision_at_1000": 0.00329, + "mrr_at_1": 0.131783, + "mrr_at_3": 0.189922, + "mrr_at_5": 0.219767, + "mrr_at_10": 0.241227, + "mrr_at_20": 0.248944, + "mrr_at_100": 0.253129, + "mrr_at_1000": 0.253684, + "nauc_ndcg_at_1_max": 0.194956, + "nauc_ndcg_at_1_std": 0.086475, + "nauc_ndcg_at_1_diff1": 0.267662, + "nauc_ndcg_at_3_max": 0.209941, + "nauc_ndcg_at_3_std": 0.057238, + "nauc_ndcg_at_3_diff1": 0.225255, + "nauc_ndcg_at_5_max": 0.236859, + "nauc_ndcg_at_5_std": 0.125792, + "nauc_ndcg_at_5_diff1": 0.184741, + "nauc_ndcg_at_10_max": 0.244152, + "nauc_ndcg_at_10_std": 0.116749, + "nauc_ndcg_at_10_diff1": 0.197372, + "nauc_ndcg_at_20_max": 0.275686, + "nauc_ndcg_at_20_std": 0.154919, + "nauc_ndcg_at_20_diff1": 0.18055, + "nauc_ndcg_at_100_max": 0.319915, + "nauc_ndcg_at_100_std": 0.250688, + "nauc_ndcg_at_100_diff1": 0.158488, + "nauc_ndcg_at_1000_max": 0.287919, + "nauc_ndcg_at_1000_std": 0.267516, + "nauc_ndcg_at_1000_diff1": 0.104086, + "nauc_map_at_1_max": 0.167326, + "nauc_map_at_1_std": 0.064305, + "nauc_map_at_1_diff1": 0.360022, + "nauc_map_at_3_max": 0.193431, + "nauc_map_at_3_std": 0.000588, + "nauc_map_at_3_diff1": 0.33454, + "nauc_map_at_5_max": 0.211337, + "nauc_map_at_5_std": 0.064575, + "nauc_map_at_5_diff1": 0.275748, + "nauc_map_at_10_max": 0.215188, + "nauc_map_at_10_std": 0.065173, + "nauc_map_at_10_diff1": 0.264469, + "nauc_map_at_20_max": 0.236029, + "nauc_map_at_20_std": 0.078896, + "nauc_map_at_20_diff1": 0.258658, + "nauc_map_at_100_max": 0.248641, + "nauc_map_at_100_std": 0.111824, + "nauc_map_at_100_diff1": 0.241338, + "nauc_map_at_1000_max": 0.24693, + "nauc_map_at_1000_std": 0.118427, + "nauc_map_at_1000_diff1": 0.234747, + "nauc_recall_at_1_max": 0.167326, + "nauc_recall_at_1_std": 0.064305, + "nauc_recall_at_1_diff1": 0.360022, + "nauc_recall_at_3_max": 0.187635, + "nauc_recall_at_3_std": -0.022215, + "nauc_recall_at_3_diff1": 0.292545, + "nauc_recall_at_5_max": 0.227403, + "nauc_recall_at_5_std": 0.122441, + "nauc_recall_at_5_diff1": 0.151977, + "nauc_recall_at_10_max": 0.209952, + "nauc_recall_at_10_std": 0.086517, + "nauc_recall_at_10_diff1": 0.171548, + "nauc_recall_at_20_max": 0.259496, + "nauc_recall_at_20_std": 0.144378, + "nauc_recall_at_20_diff1": 0.13624, + "nauc_recall_at_100_max": 0.343687, + "nauc_recall_at_100_std": 0.334882, + "nauc_recall_at_100_diff1": 0.09742, + "nauc_recall_at_1000_max": 0.305175, + "nauc_recall_at_1000_std": 0.683177, + "nauc_recall_at_1000_diff1": -0.380327, + "nauc_precision_at_1_max": 0.194956, + "nauc_precision_at_1_std": 0.086475, + "nauc_precision_at_1_diff1": 0.267662, + "nauc_precision_at_3_max": 0.2493, + "nauc_precision_at_3_std": 0.09074, + "nauc_precision_at_3_diff1": 0.112373, + "nauc_precision_at_5_max": 0.295304, + "nauc_precision_at_5_std": 0.285611, + "nauc_precision_at_5_diff1": -0.038051, + "nauc_precision_at_10_max": 0.26108, + "nauc_precision_at_10_std": 0.248536, + "nauc_precision_at_10_diff1": -0.032416, + "nauc_precision_at_20_max": 0.294808, + "nauc_precision_at_20_std": 0.302854, + "nauc_precision_at_20_diff1": -0.064893, + "nauc_precision_at_100_max": 0.279629, + "nauc_precision_at_100_std": 0.430729, + "nauc_precision_at_100_diff1": -0.112314, + "nauc_precision_at_1000_max": 0.095935, + "nauc_precision_at_1000_std": 0.397652, + "nauc_precision_at_1000_diff1": -0.313301, + "nauc_mrr_at_1_max": 0.194956, + "nauc_mrr_at_1_std": 0.086475, + "nauc_mrr_at_1_diff1": 0.267662, + "nauc_mrr_at_3_max": 0.21438, + "nauc_mrr_at_3_std": 0.086857, + "nauc_mrr_at_3_diff1": 0.17974, + "nauc_mrr_at_5_max": 0.242515, + "nauc_mrr_at_5_std": 0.144233, + "nauc_mrr_at_5_diff1": 0.143314, + "nauc_mrr_at_10_max": 0.248117, + "nauc_mrr_at_10_std": 0.143695, + "nauc_mrr_at_10_diff1": 0.163723, + "nauc_mrr_at_20_max": 0.245828, + "nauc_mrr_at_20_std": 0.15581, + "nauc_mrr_at_20_diff1": 0.156202, + "nauc_mrr_at_100_max": 0.245142, + "nauc_mrr_at_100_std": 0.154745, + "nauc_mrr_at_100_diff1": 0.157639, + "nauc_mrr_at_1000_max": 0.244331, + "nauc_mrr_at_1000_std": 0.153832, + "nauc_mrr_at_1000_diff1": 0.157567, + "main_score": 0.17731, + "hf_subset": "IIYi-Clinical", + "languages": [ + "eng-Latn" + ] + } + ] + }, + "evaluation_time": 1297.7114157676697, + "kg_co2_emissions": null +} \ No newline at end of file diff --git a/results/BAAI__bge-small-en-v1.5/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/R2MEDRetrieval.json b/results/BAAI__bge-small-en-v1.5/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/R2MEDRetrieval.json new file mode 100644 index 0000000000..8537ed48be --- /dev/null +++ b/results/BAAI__bge-small-en-v1.5/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/R2MEDRetrieval.json @@ -0,0 +1,1187 @@ +{ + "dataset_revision": "1.0", + "task_name": "R2MEDRetrieval", + "mteb_version": "1.38.20", + "scores": { + "test": [ + { + "ndcg_at_1": 0.1165, + "ndcg_at_3": 0.10668, + "ndcg_at_5": 0.11514, + "ndcg_at_10": 0.12879, + "ndcg_at_20": 0.1462, + "ndcg_at_100": 0.20607, + "ndcg_at_1000": 0.27707, + "map_at_1": 0.03104, + "map_at_3": 0.0596, + "map_at_5": 0.07259, + "map_at_10": 0.08238, + "map_at_20": 0.08807, + "map_at_100": 0.09902, + "map_at_1000": 0.10295, + "recall_at_1": 0.03104, + "recall_at_3": 0.08237, + "recall_at_5": 0.11265, + "recall_at_10": 0.15355, + "recall_at_20": 0.19924, + "recall_at_100": 0.42606, + "recall_at_1000": 0.82627, + "precision_at_1": 0.1165, + "precision_at_3": 0.09385, + "precision_at_5": 0.0835, + "precision_at_10": 0.06019, + "precision_at_20": 0.03981, + "precision_at_100": 0.01592, + "precision_at_1000": 0.00304, + "mrr_at_1": 0.116505, + "mrr_at_3": 0.160194, + "mrr_at_5": 0.169417, + "mrr_at_10": 0.181646, + "mrr_at_20": 0.187611, + "mrr_at_100": 0.194038, + "mrr_at_1000": 0.194822, + "nauc_ndcg_at_1_max": 0.095711, + "nauc_ndcg_at_1_std": -0.189807, + "nauc_ndcg_at_1_diff1": 0.427797, + "nauc_ndcg_at_3_max": 0.149902, + "nauc_ndcg_at_3_std": -0.255171, + "nauc_ndcg_at_3_diff1": 0.323042, + "nauc_ndcg_at_5_max": 0.106452, + "nauc_ndcg_at_5_std": -0.285079, + "nauc_ndcg_at_5_diff1": 0.314957, + "nauc_ndcg_at_10_max": 0.0844, + "nauc_ndcg_at_10_std": -0.285624, + "nauc_ndcg_at_10_diff1": 0.267854, + "nauc_ndcg_at_20_max": 0.062739, + "nauc_ndcg_at_20_std": -0.312777, + "nauc_ndcg_at_20_diff1": 0.286416, + "nauc_ndcg_at_100_max": 0.075373, + "nauc_ndcg_at_100_std": -0.352553, + "nauc_ndcg_at_100_diff1": 0.256448, + "nauc_ndcg_at_1000_max": 0.071082, + "nauc_ndcg_at_1000_std": -0.290044, + "nauc_ndcg_at_1000_diff1": 0.281982, + "nauc_map_at_1_max": 0.172328, + "nauc_map_at_1_std": -0.228461, + "nauc_map_at_1_diff1": 0.48639, + "nauc_map_at_3_max": 0.19997, + "nauc_map_at_3_std": -0.267589, + "nauc_map_at_3_diff1": 0.404496, + "nauc_map_at_5_max": 0.140056, + "nauc_map_at_5_std": -0.291581, + "nauc_map_at_5_diff1": 0.376855, + "nauc_map_at_10_max": 0.111435, + "nauc_map_at_10_std": -0.30349, + "nauc_map_at_10_diff1": 0.339553, + "nauc_map_at_20_max": 0.097441, + "nauc_map_at_20_std": -0.312056, + "nauc_map_at_20_diff1": 0.344439, + "nauc_map_at_100_max": 0.097499, + "nauc_map_at_100_std": -0.325905, + "nauc_map_at_100_diff1": 0.330735, + "nauc_map_at_1000_max": 0.097931, + "nauc_map_at_1000_std": -0.319251, + "nauc_map_at_1000_diff1": 0.33359, + "nauc_recall_at_1_max": 0.172328, + "nauc_recall_at_1_std": -0.228461, + "nauc_recall_at_1_diff1": 0.48639, + "nauc_recall_at_3_max": 0.228042, + "nauc_recall_at_3_std": -0.251633, + "nauc_recall_at_3_diff1": 0.281991, + "nauc_recall_at_5_max": 0.121422, + "nauc_recall_at_5_std": -0.282833, + "nauc_recall_at_5_diff1": 0.249007, + "nauc_recall_at_10_max": 0.050553, + "nauc_recall_at_10_std": -0.287911, + "nauc_recall_at_10_diff1": 0.173016, + "nauc_recall_at_20_max": -0.001205, + "nauc_recall_at_20_std": -0.327039, + "nauc_recall_at_20_diff1": 0.205665, + "nauc_recall_at_100_max": 0.064894, + "nauc_recall_at_100_std": -0.345426, + "nauc_recall_at_100_diff1": 0.140699, + "nauc_recall_at_1000_max": 0.013185, + "nauc_recall_at_1000_std": -0.03555, + "nauc_recall_at_1000_diff1": 0.262111, + "nauc_precision_at_1_max": 0.095711, + "nauc_precision_at_1_std": -0.189807, + "nauc_precision_at_1_diff1": 0.427797, + "nauc_precision_at_3_max": 0.197935, + "nauc_precision_at_3_std": -0.254856, + "nauc_precision_at_3_diff1": 0.309466, + "nauc_precision_at_5_max": 0.075184, + "nauc_precision_at_5_std": -0.293668, + "nauc_precision_at_5_diff1": 0.280979, + "nauc_precision_at_10_max": -0.003586, + "nauc_precision_at_10_std": -0.304766, + "nauc_precision_at_10_diff1": 0.185816, + "nauc_precision_at_20_max": -0.05092, + "nauc_precision_at_20_std": -0.341665, + "nauc_precision_at_20_diff1": 0.216411, + "nauc_precision_at_100_max": -0.027082, + "nauc_precision_at_100_std": -0.357476, + "nauc_precision_at_100_diff1": 0.100085, + "nauc_precision_at_1000_max": -0.088321, + "nauc_precision_at_1000_std": -0.156035, + "nauc_precision_at_1000_diff1": 0.054834, + "nauc_mrr_at_1_max": 0.095711, + "nauc_mrr_at_1_std": -0.189807, + "nauc_mrr_at_1_diff1": 0.427797, + "nauc_mrr_at_3_max": 0.127788, + "nauc_mrr_at_3_std": -0.226291, + "nauc_mrr_at_3_diff1": 0.308776, + "nauc_mrr_at_5_max": 0.104675, + "nauc_mrr_at_5_std": -0.223473, + "nauc_mrr_at_5_diff1": 0.295649, + "nauc_mrr_at_10_max": 0.091046, + "nauc_mrr_at_10_std": -0.225333, + "nauc_mrr_at_10_diff1": 0.269808, + "nauc_mrr_at_20_max": 0.090403, + "nauc_mrr_at_20_std": -0.235175, + "nauc_mrr_at_20_diff1": 0.272211, + "nauc_mrr_at_100_max": 0.087548, + "nauc_mrr_at_100_std": -0.238229, + "nauc_mrr_at_100_diff1": 0.268487, + "nauc_mrr_at_1000_max": 0.087734, + "nauc_mrr_at_1000_std": -0.237075, + "nauc_mrr_at_1000_diff1": 0.269919, + "main_score": 0.12879, + "hf_subset": "Biology", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.14286, + "ndcg_at_3": 0.1797, + "ndcg_at_5": 0.21871, + "ndcg_at_10": 0.25896, + "ndcg_at_20": 0.2965, + "ndcg_at_100": 0.34341, + "ndcg_at_1000": 0.38814, + "map_at_1": 0.07522, + "map_at_3": 0.12515, + "map_at_5": 0.15597, + "map_at_10": 0.17795, + "map_at_20": 0.19192, + "map_at_100": 0.20133, + "map_at_1000": 0.20412, + "recall_at_1": 0.07522, + "recall_at_3": 0.17534, + "recall_at_5": 0.28411, + "recall_at_10": 0.38004, + "recall_at_20": 0.48525, + "recall_at_100": 0.66082, + "recall_at_1000": 0.93228, + "precision_at_1": 0.14286, + "precision_at_3": 0.12987, + "precision_at_5": 0.11688, + "precision_at_10": 0.08831, + "precision_at_20": 0.06299, + "precision_at_100": 0.01974, + "precision_at_1000": 0.00278, + "mrr_at_1": 0.142857, + "mrr_at_3": 0.238095, + "mrr_at_5": 0.264719, + "mrr_at_10": 0.28122, + "mrr_at_20": 0.287338, + "mrr_at_100": 0.289867, + "mrr_at_1000": 0.290516, + "nauc_ndcg_at_1_max": 0.046194, + "nauc_ndcg_at_1_std": 0.053346, + "nauc_ndcg_at_1_diff1": 0.321392, + "nauc_ndcg_at_3_max": 0.183664, + "nauc_ndcg_at_3_std": 0.074323, + "nauc_ndcg_at_3_diff1": 0.234692, + "nauc_ndcg_at_5_max": 0.194661, + "nauc_ndcg_at_5_std": 0.072092, + "nauc_ndcg_at_5_diff1": 0.280619, + "nauc_ndcg_at_10_max": 0.19119, + "nauc_ndcg_at_10_std": 0.070315, + "nauc_ndcg_at_10_diff1": 0.205548, + "nauc_ndcg_at_20_max": 0.166767, + "nauc_ndcg_at_20_std": 0.073464, + "nauc_ndcg_at_20_diff1": 0.154122, + "nauc_ndcg_at_100_max": 0.197523, + "nauc_ndcg_at_100_std": 0.113978, + "nauc_ndcg_at_100_diff1": 0.139116, + "nauc_ndcg_at_1000_max": 0.190923, + "nauc_ndcg_at_1000_std": 0.109744, + "nauc_ndcg_at_1000_diff1": 0.177259, + "nauc_map_at_1_max": 0.083721, + "nauc_map_at_1_std": 0.221995, + "nauc_map_at_1_diff1": 0.537145, + "nauc_map_at_3_max": 0.187784, + "nauc_map_at_3_std": 0.133219, + "nauc_map_at_3_diff1": 0.334315, + "nauc_map_at_5_max": 0.189685, + "nauc_map_at_5_std": 0.113935, + "nauc_map_at_5_diff1": 0.340799, + "nauc_map_at_10_max": 0.188199, + "nauc_map_at_10_std": 0.100221, + "nauc_map_at_10_diff1": 0.282479, + "nauc_map_at_20_max": 0.177989, + "nauc_map_at_20_std": 0.102094, + "nauc_map_at_20_diff1": 0.25912, + "nauc_map_at_100_max": 0.18608, + "nauc_map_at_100_std": 0.112468, + "nauc_map_at_100_diff1": 0.258235, + "nauc_map_at_1000_max": 0.186527, + "nauc_map_at_1000_std": 0.113188, + "nauc_map_at_1000_diff1": 0.259097, + "nauc_recall_at_1_max": 0.083721, + "nauc_recall_at_1_std": 0.221995, + "nauc_recall_at_1_diff1": 0.537145, + "nauc_recall_at_3_max": 0.264793, + "nauc_recall_at_3_std": 0.126743, + "nauc_recall_at_3_diff1": 0.228365, + "nauc_recall_at_5_max": 0.214226, + "nauc_recall_at_5_std": 0.064718, + "nauc_recall_at_5_diff1": 0.245499, + "nauc_recall_at_10_max": 0.210559, + "nauc_recall_at_10_std": 0.043039, + "nauc_recall_at_10_diff1": 0.121407, + "nauc_recall_at_20_max": 0.121275, + "nauc_recall_at_20_std": 0.037086, + "nauc_recall_at_20_diff1": -0.009026, + "nauc_recall_at_100_max": 0.190008, + "nauc_recall_at_100_std": 0.151306, + "nauc_recall_at_100_diff1": -0.115283, + "nauc_recall_at_1000_max": -0.095882, + "nauc_recall_at_1000_std": 0.128468, + "nauc_recall_at_1000_diff1": -0.019714, + "nauc_precision_at_1_max": 0.046194, + "nauc_precision_at_1_std": 0.053346, + "nauc_precision_at_1_diff1": 0.321392, + "nauc_precision_at_3_max": 0.171654, + "nauc_precision_at_3_std": -0.006971, + "nauc_precision_at_3_diff1": 0.0625, + "nauc_precision_at_5_max": 0.141243, + "nauc_precision_at_5_std": -0.003925, + "nauc_precision_at_5_diff1": 0.073672, + "nauc_precision_at_10_max": 0.134723, + "nauc_precision_at_10_std": 0.014734, + "nauc_precision_at_10_diff1": -0.097735, + "nauc_precision_at_20_max": 0.066347, + "nauc_precision_at_20_std": 0.009655, + "nauc_precision_at_20_diff1": -0.176129, + "nauc_precision_at_100_max": 0.115906, + "nauc_precision_at_100_std": 0.104949, + "nauc_precision_at_100_diff1": -0.153175, + "nauc_precision_at_1000_max": 0.080564, + "nauc_precision_at_1000_std": 0.063172, + "nauc_precision_at_1000_diff1": -0.07188, + "nauc_mrr_at_1_max": 0.046194, + "nauc_mrr_at_1_std": 0.053346, + "nauc_mrr_at_1_diff1": 0.321392, + "nauc_mrr_at_3_max": 0.145444, + "nauc_mrr_at_3_std": 0.032417, + "nauc_mrr_at_3_diff1": 0.205451, + "nauc_mrr_at_5_max": 0.14751, + "nauc_mrr_at_5_std": 0.02022, + "nauc_mrr_at_5_diff1": 0.217053, + "nauc_mrr_at_10_max": 0.14632, + "nauc_mrr_at_10_std": 0.045443, + "nauc_mrr_at_10_diff1": 0.192679, + "nauc_mrr_at_20_max": 0.146717, + "nauc_mrr_at_20_std": 0.042378, + "nauc_mrr_at_20_diff1": 0.18848, + "nauc_mrr_at_100_max": 0.147547, + "nauc_mrr_at_100_std": 0.041941, + "nauc_mrr_at_100_diff1": 0.188278, + "nauc_mrr_at_1000_max": 0.147304, + "nauc_mrr_at_1000_std": 0.041736, + "nauc_mrr_at_1000_diff1": 0.189095, + "main_score": 0.25896, + "hf_subset": "Bioinformatics", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.15909, + "ndcg_at_3": 0.22829, + "ndcg_at_5": 0.24948, + "ndcg_at_10": 0.2823, + "ndcg_at_20": 0.31959, + "ndcg_at_100": 0.38063, + "ndcg_at_1000": 0.41182, + "map_at_1": 0.08969, + "map_at_3": 0.17121, + "map_at_5": 0.1921, + "map_at_10": 0.2085, + "map_at_20": 0.22215, + "map_at_100": 0.23541, + "map_at_1000": 0.23744, + "recall_at_1": 0.08969, + "recall_at_3": 0.25308, + "recall_at_5": 0.31495, + "recall_at_10": 0.39765, + "recall_at_20": 0.50946, + "recall_at_100": 0.7436, + "recall_at_1000": 0.91861, + "precision_at_1": 0.15909, + "precision_at_3": 0.16667, + "precision_at_5": 0.12727, + "precision_at_10": 0.08636, + "precision_at_20": 0.05909, + "precision_at_100": 0.01932, + "precision_at_1000": 0.00253, + "mrr_at_1": 0.159091, + "mrr_at_3": 0.261364, + "mrr_at_5": 0.277273, + "mrr_at_10": 0.295373, + "mrr_at_20": 0.301952, + "mrr_at_100": 0.306458, + "mrr_at_1000": 0.306862, + "nauc_ndcg_at_1_max": 0.505962, + "nauc_ndcg_at_1_std": 0.266374, + "nauc_ndcg_at_1_diff1": -0.188923, + "nauc_ndcg_at_3_max": 0.437296, + "nauc_ndcg_at_3_std": 0.134415, + "nauc_ndcg_at_3_diff1": -0.049215, + "nauc_ndcg_at_5_max": 0.421466, + "nauc_ndcg_at_5_std": 0.097479, + "nauc_ndcg_at_5_diff1": -0.068055, + "nauc_ndcg_at_10_max": 0.41591, + "nauc_ndcg_at_10_std": 0.096663, + "nauc_ndcg_at_10_diff1": -0.039041, + "nauc_ndcg_at_20_max": 0.472773, + "nauc_ndcg_at_20_std": 0.148327, + "nauc_ndcg_at_20_diff1": -0.015534, + "nauc_ndcg_at_100_max": 0.515046, + "nauc_ndcg_at_100_std": 0.217756, + "nauc_ndcg_at_100_diff1": -0.029949, + "nauc_ndcg_at_1000_max": 0.495375, + "nauc_ndcg_at_1000_std": 0.199629, + "nauc_ndcg_at_1000_diff1": -0.061271, + "nauc_map_at_1_max": 0.526441, + "nauc_map_at_1_std": 0.208813, + "nauc_map_at_1_diff1": -0.005131, + "nauc_map_at_3_max": 0.426838, + "nauc_map_at_3_std": 0.116723, + "nauc_map_at_3_diff1": -0.005979, + "nauc_map_at_5_max": 0.42344, + "nauc_map_at_5_std": 0.109067, + "nauc_map_at_5_diff1": -0.034218, + "nauc_map_at_10_max": 0.436316, + "nauc_map_at_10_std": 0.121612, + "nauc_map_at_10_diff1": -0.026205, + "nauc_map_at_20_max": 0.468573, + "nauc_map_at_20_std": 0.145807, + "nauc_map_at_20_diff1": -0.019985, + "nauc_map_at_100_max": 0.478161, + "nauc_map_at_100_std": 0.159137, + "nauc_map_at_100_diff1": -0.024625, + "nauc_map_at_1000_max": 0.477878, + "nauc_map_at_1000_std": 0.158807, + "nauc_map_at_1000_diff1": -0.026126, + "nauc_recall_at_1_max": 0.526441, + "nauc_recall_at_1_std": 0.208813, + "nauc_recall_at_1_diff1": -0.005131, + "nauc_recall_at_3_max": 0.301146, + "nauc_recall_at_3_std": 0.009152, + "nauc_recall_at_3_diff1": 0.001401, + "nauc_recall_at_5_max": 0.29063, + "nauc_recall_at_5_std": -0.025496, + "nauc_recall_at_5_diff1": -0.050994, + "nauc_recall_at_10_max": 0.2859, + "nauc_recall_at_10_std": -0.020987, + "nauc_recall_at_10_diff1": 0.001438, + "nauc_recall_at_20_max": 0.394052, + "nauc_recall_at_20_std": 0.088623, + "nauc_recall_at_20_diff1": 0.092143, + "nauc_recall_at_100_max": 0.528056, + "nauc_recall_at_100_std": 0.336885, + "nauc_recall_at_100_diff1": 0.076275, + "nauc_recall_at_1000_max": 0.305806, + "nauc_recall_at_1000_std": 0.160555, + "nauc_recall_at_1000_diff1": -0.218133, + "nauc_precision_at_1_max": 0.505962, + "nauc_precision_at_1_std": 0.266374, + "nauc_precision_at_1_diff1": -0.188923, + "nauc_precision_at_3_max": 0.467718, + "nauc_precision_at_3_std": 0.198747, + "nauc_precision_at_3_diff1": -0.103985, + "nauc_precision_at_5_max": 0.445501, + "nauc_precision_at_5_std": 0.145136, + "nauc_precision_at_5_diff1": -0.1593, + "nauc_precision_at_10_max": 0.431436, + "nauc_precision_at_10_std": 0.152871, + "nauc_precision_at_10_diff1": -0.118104, + "nauc_precision_at_20_max": 0.516714, + "nauc_precision_at_20_std": 0.277527, + "nauc_precision_at_20_diff1": -0.089866, + "nauc_precision_at_100_max": 0.422646, + "nauc_precision_at_100_std": 0.36073, + "nauc_precision_at_100_diff1": -0.069517, + "nauc_precision_at_1000_max": 0.189225, + "nauc_precision_at_1000_std": 0.2239, + "nauc_precision_at_1000_diff1": -0.140414, + "nauc_mrr_at_1_max": 0.505962, + "nauc_mrr_at_1_std": 0.266374, + "nauc_mrr_at_1_diff1": -0.188923, + "nauc_mrr_at_3_max": 0.481803, + "nauc_mrr_at_3_std": 0.21299, + "nauc_mrr_at_3_diff1": -0.117778, + "nauc_mrr_at_5_max": 0.482065, + "nauc_mrr_at_5_std": 0.191876, + "nauc_mrr_at_5_diff1": -0.124474, + "nauc_mrr_at_10_max": 0.461172, + "nauc_mrr_at_10_std": 0.175474, + "nauc_mrr_at_10_diff1": -0.117258, + "nauc_mrr_at_20_max": 0.467017, + "nauc_mrr_at_20_std": 0.184069, + "nauc_mrr_at_20_diff1": -0.115706, + "nauc_mrr_at_100_max": 0.471265, + "nauc_mrr_at_100_std": 0.19097, + "nauc_mrr_at_100_diff1": -0.116426, + "nauc_mrr_at_1000_max": 0.470779, + "nauc_mrr_at_1000_std": 0.190767, + "nauc_mrr_at_1000_diff1": -0.117342, + "main_score": 0.2823, + "hf_subset": "Medical-Sciences", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.03093, + "ndcg_at_3": 0.03164, + "ndcg_at_5": 0.03598, + "ndcg_at_10": 0.03974, + "ndcg_at_20": 0.04967, + "ndcg_at_100": 0.07508, + "ndcg_at_1000": 0.12263, + "map_at_1": 0.00835, + "map_at_3": 0.01937, + "map_at_5": 0.02259, + "map_at_10": 0.02383, + "map_at_20": 0.02645, + "map_at_100": 0.02965, + "map_at_1000": 0.03119, + "recall_at_1": 0.00835, + "recall_at_3": 0.03498, + "recall_at_5": 0.04529, + "recall_at_10": 0.05508, + "recall_at_20": 0.08173, + "recall_at_100": 0.19385, + "recall_at_1000": 0.49553, + "precision_at_1": 0.03093, + "precision_at_3": 0.02405, + "precision_at_5": 0.02062, + "precision_at_10": 0.0134, + "precision_at_20": 0.01186, + "precision_at_100": 0.00526, + "precision_at_1000": 0.00141, + "mrr_at_1": 0.030928, + "mrr_at_3": 0.04811, + "mrr_at_5": 0.053265, + "mrr_at_10": 0.057486, + "mrr_at_20": 0.061313, + "mrr_at_100": 0.064246, + "mrr_at_1000": 0.065388, + "nauc_ndcg_at_1_max": 0.147046, + "nauc_ndcg_at_1_std": 0.007047, + "nauc_ndcg_at_1_diff1": -0.184249, + "nauc_ndcg_at_3_max": -0.066457, + "nauc_ndcg_at_3_std": -0.218315, + "nauc_ndcg_at_3_diff1": -0.152184, + "nauc_ndcg_at_5_max": 0.011077, + "nauc_ndcg_at_5_std": -0.108913, + "nauc_ndcg_at_5_diff1": -0.074139, + "nauc_ndcg_at_10_max": -0.030452, + "nauc_ndcg_at_10_std": -0.150971, + "nauc_ndcg_at_10_diff1": -0.092203, + "nauc_ndcg_at_20_max": -0.01915, + "nauc_ndcg_at_20_std": -0.16008, + "nauc_ndcg_at_20_diff1": -0.125488, + "nauc_ndcg_at_100_max": 0.009898, + "nauc_ndcg_at_100_std": -0.030086, + "nauc_ndcg_at_100_diff1": -0.074625, + "nauc_ndcg_at_1000_max": 0.030068, + "nauc_ndcg_at_1000_std": -0.012554, + "nauc_ndcg_at_1000_diff1": -0.148675, + "nauc_map_at_1_max": 0.230266, + "nauc_map_at_1_std": 0.025692, + "nauc_map_at_1_diff1": -0.25036, + "nauc_map_at_3_max": -0.050164, + "nauc_map_at_3_std": -0.230167, + "nauc_map_at_3_diff1": -0.156419, + "nauc_map_at_5_max": -0.014282, + "nauc_map_at_5_std": -0.149334, + "nauc_map_at_5_diff1": -0.102924, + "nauc_map_at_10_max": -0.034666, + "nauc_map_at_10_std": -0.166647, + "nauc_map_at_10_diff1": -0.110274, + "nauc_map_at_20_max": -0.022103, + "nauc_map_at_20_std": -0.183253, + "nauc_map_at_20_diff1": -0.117725, + "nauc_map_at_100_max": -0.016429, + "nauc_map_at_100_std": -0.146681, + "nauc_map_at_100_diff1": -0.099027, + "nauc_map_at_1000_max": -0.013396, + "nauc_map_at_1000_std": -0.138438, + "nauc_map_at_1000_diff1": -0.106315, + "nauc_recall_at_1_max": 0.230266, + "nauc_recall_at_1_std": 0.025692, + "nauc_recall_at_1_diff1": -0.25036, + "nauc_recall_at_3_max": -0.119959, + "nauc_recall_at_3_std": -0.297789, + "nauc_recall_at_3_diff1": -0.13618, + "nauc_recall_at_5_max": -0.017099, + "nauc_recall_at_5_std": -0.11597, + "nauc_recall_at_5_diff1": -0.014398, + "nauc_recall_at_10_max": -0.089049, + "nauc_recall_at_10_std": -0.183856, + "nauc_recall_at_10_diff1": -0.058374, + "nauc_recall_at_20_max": -0.044183, + "nauc_recall_at_20_std": -0.187495, + "nauc_recall_at_20_diff1": -0.121863, + "nauc_recall_at_100_max": 0.043392, + "nauc_recall_at_100_std": 0.09974, + "nauc_recall_at_100_diff1": -0.006824, + "nauc_recall_at_1000_max": 0.1037, + "nauc_recall_at_1000_std": 0.072228, + "nauc_recall_at_1000_diff1": -0.159312, + "nauc_precision_at_1_max": 0.147046, + "nauc_precision_at_1_std": 0.007047, + "nauc_precision_at_1_diff1": -0.184249, + "nauc_precision_at_3_max": -0.062938, + "nauc_precision_at_3_std": -0.226364, + "nauc_precision_at_3_diff1": -0.17663, + "nauc_precision_at_5_max": 0.05631, + "nauc_precision_at_5_std": -0.058088, + "nauc_precision_at_5_diff1": -0.064124, + "nauc_precision_at_10_max": -0.041503, + "nauc_precision_at_10_std": -0.153589, + "nauc_precision_at_10_diff1": -0.078902, + "nauc_precision_at_20_max": -0.028586, + "nauc_precision_at_20_std": -0.165134, + "nauc_precision_at_20_diff1": -0.160886, + "nauc_precision_at_100_max": 0.030834, + "nauc_precision_at_100_std": 0.083021, + "nauc_precision_at_100_diff1": -0.116812, + "nauc_precision_at_1000_max": -0.003197, + "nauc_precision_at_1000_std": 0.088059, + "nauc_precision_at_1000_diff1": -0.22799, + "nauc_mrr_at_1_max": 0.147046, + "nauc_mrr_at_1_std": 0.007047, + "nauc_mrr_at_1_diff1": -0.184249, + "nauc_mrr_at_3_max": 0.005218, + "nauc_mrr_at_3_std": -0.142215, + "nauc_mrr_at_3_diff1": -0.181737, + "nauc_mrr_at_5_max": 0.068772, + "nauc_mrr_at_5_std": -0.064394, + "nauc_mrr_at_5_diff1": -0.111082, + "nauc_mrr_at_10_max": 0.038438, + "nauc_mrr_at_10_std": -0.091588, + "nauc_mrr_at_10_diff1": -0.111327, + "nauc_mrr_at_20_max": 0.028691, + "nauc_mrr_at_20_std": -0.086505, + "nauc_mrr_at_20_diff1": -0.131128, + "nauc_mrr_at_100_max": 0.024989, + "nauc_mrr_at_100_std": -0.079517, + "nauc_mrr_at_100_diff1": -0.123598, + "nauc_mrr_at_1000_max": 0.025714, + "nauc_mrr_at_1000_std": -0.079922, + "nauc_mrr_at_1000_diff1": -0.123962, + "main_score": 0.03974, + "hf_subset": "MedXpertQA-Exam", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.0339, + "ndcg_at_3": 0.03191, + "ndcg_at_5": 0.04202, + "ndcg_at_10": 0.05001, + "ndcg_at_20": 0.06315, + "ndcg_at_100": 0.09839, + "ndcg_at_1000": 0.14587, + "map_at_1": 0.00636, + "map_at_3": 0.01487, + "map_at_5": 0.02396, + "map_at_10": 0.02755, + "map_at_20": 0.03104, + "map_at_100": 0.0364, + "map_at_1000": 0.03856, + "recall_at_1": 0.00636, + "recall_at_3": 0.019, + "recall_at_5": 0.05035, + "recall_at_10": 0.07092, + "recall_at_20": 0.10936, + "recall_at_100": 0.24264, + "recall_at_1000": 0.49398, + "precision_at_1": 0.0339, + "precision_at_3": 0.03107, + "precision_at_5": 0.03559, + "precision_at_10": 0.02627, + "precision_at_20": 0.01907, + "precision_at_100": 0.00873, + "precision_at_1000": 0.00201, + "mrr_at_1": 0.033898, + "mrr_at_3": 0.049435, + "mrr_at_5": 0.064689, + "mrr_at_10": 0.072622, + "mrr_at_20": 0.077531, + "mrr_at_100": 0.08222, + "mrr_at_1000": 0.083149, + "nauc_ndcg_at_1_max": 0.142683, + "nauc_ndcg_at_1_std": -0.003211, + "nauc_ndcg_at_1_diff1": -0.122442, + "nauc_ndcg_at_3_max": 0.079118, + "nauc_ndcg_at_3_std": 0.100445, + "nauc_ndcg_at_3_diff1": -0.132483, + "nauc_ndcg_at_5_max": 0.055695, + "nauc_ndcg_at_5_std": 0.307864, + "nauc_ndcg_at_5_diff1": -0.262335, + "nauc_ndcg_at_10_max": 0.023465, + "nauc_ndcg_at_10_std": 0.340426, + "nauc_ndcg_at_10_diff1": -0.222489, + "nauc_ndcg_at_20_max": 0.071775, + "nauc_ndcg_at_20_std": 0.306852, + "nauc_ndcg_at_20_diff1": -0.221446, + "nauc_ndcg_at_100_max": 0.101632, + "nauc_ndcg_at_100_std": 0.28736, + "nauc_ndcg_at_100_diff1": -0.159416, + "nauc_ndcg_at_1000_max": 0.113288, + "nauc_ndcg_at_1000_std": 0.294069, + "nauc_ndcg_at_1000_diff1": -0.135494, + "nauc_map_at_1_max": 0.204985, + "nauc_map_at_1_std": 0.163589, + "nauc_map_at_1_diff1": -0.262148, + "nauc_map_at_3_max": 0.159609, + "nauc_map_at_3_std": 0.310832, + "nauc_map_at_3_diff1": -0.325372, + "nauc_map_at_5_max": 0.105847, + "nauc_map_at_5_std": 0.432054, + "nauc_map_at_5_diff1": -0.377408, + "nauc_map_at_10_max": 0.059385, + "nauc_map_at_10_std": 0.412395, + "nauc_map_at_10_diff1": -0.33364, + "nauc_map_at_20_max": 0.088619, + "nauc_map_at_20_std": 0.398162, + "nauc_map_at_20_diff1": -0.323281, + "nauc_map_at_100_max": 0.097193, + "nauc_map_at_100_std": 0.3804, + "nauc_map_at_100_diff1": -0.29737, + "nauc_map_at_1000_max": 0.103955, + "nauc_map_at_1000_std": 0.380364, + "nauc_map_at_1000_diff1": -0.285607, + "nauc_recall_at_1_max": 0.204985, + "nauc_recall_at_1_std": 0.163589, + "nauc_recall_at_1_diff1": -0.262148, + "nauc_recall_at_3_max": 0.098414, + "nauc_recall_at_3_std": 0.261655, + "nauc_recall_at_3_diff1": -0.253766, + "nauc_recall_at_5_max": 0.037672, + "nauc_recall_at_5_std": 0.461431, + "nauc_recall_at_5_diff1": -0.353098, + "nauc_recall_at_10_max": -0.01694, + "nauc_recall_at_10_std": 0.41262, + "nauc_recall_at_10_diff1": -0.210757, + "nauc_recall_at_20_max": 0.080421, + "nauc_recall_at_20_std": 0.315837, + "nauc_recall_at_20_diff1": -0.197837, + "nauc_recall_at_100_max": 0.117594, + "nauc_recall_at_100_std": 0.250516, + "nauc_recall_at_100_diff1": -0.10268, + "nauc_recall_at_1000_max": 0.101614, + "nauc_recall_at_1000_std": 0.251628, + "nauc_recall_at_1000_diff1": -0.067379, + "nauc_precision_at_1_max": 0.142683, + "nauc_precision_at_1_std": -0.003211, + "nauc_precision_at_1_diff1": -0.122442, + "nauc_precision_at_3_max": 0.075436, + "nauc_precision_at_3_std": 0.129511, + "nauc_precision_at_3_diff1": -0.135013, + "nauc_precision_at_5_max": 0.052657, + "nauc_precision_at_5_std": 0.310308, + "nauc_precision_at_5_diff1": -0.258865, + "nauc_precision_at_10_max": 0.011073, + "nauc_precision_at_10_std": 0.304448, + "nauc_precision_at_10_diff1": -0.165244, + "nauc_precision_at_20_max": 0.071198, + "nauc_precision_at_20_std": 0.255855, + "nauc_precision_at_20_diff1": -0.1873, + "nauc_precision_at_100_max": 0.106999, + "nauc_precision_at_100_std": 0.224454, + "nauc_precision_at_100_diff1": -0.052988, + "nauc_precision_at_1000_max": 0.118912, + "nauc_precision_at_1000_std": 0.182184, + "nauc_precision_at_1000_diff1": -0.012955, + "nauc_mrr_at_1_max": 0.142683, + "nauc_mrr_at_1_std": -0.003211, + "nauc_mrr_at_1_diff1": -0.122442, + "nauc_mrr_at_3_max": 0.032445, + "nauc_mrr_at_3_std": -0.012032, + "nauc_mrr_at_3_diff1": -0.045761, + "nauc_mrr_at_5_max": 0.035383, + "nauc_mrr_at_5_std": 0.084114, + "nauc_mrr_at_5_diff1": -0.108556, + "nauc_mrr_at_10_max": 0.043294, + "nauc_mrr_at_10_std": 0.113296, + "nauc_mrr_at_10_diff1": -0.081415, + "nauc_mrr_at_20_max": 0.05076, + "nauc_mrr_at_20_std": 0.10513, + "nauc_mrr_at_20_diff1": -0.086133, + "nauc_mrr_at_100_max": 0.057175, + "nauc_mrr_at_100_std": 0.117209, + "nauc_mrr_at_100_diff1": -0.079316, + "nauc_mrr_at_1000_max": 0.056347, + "nauc_mrr_at_1000_std": 0.116753, + "nauc_mrr_at_1000_diff1": -0.080001, + "main_score": 0.05001, + "hf_subset": "MedQA-Diag", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.17333, + "ndcg_at_3": 0.16726, + "ndcg_at_5": 0.17645, + "ndcg_at_10": 0.19668, + "ndcg_at_20": 0.21185, + "ndcg_at_100": 0.24484, + "ndcg_at_1000": 0.2811, + "map_at_1": 0.096, + "map_at_3": 0.13281, + "map_at_5": 0.14295, + "map_at_10": 0.15117, + "map_at_20": 0.15534, + "map_at_100": 0.16027, + "map_at_1000": 0.16163, + "recall_at_1": 0.096, + "recall_at_3": 0.16522, + "recall_at_5": 0.19889, + "recall_at_10": 0.25078, + "recall_at_20": 0.29944, + "recall_at_100": 0.44956, + "recall_at_1000": 0.70233, + "precision_at_1": 0.17333, + "precision_at_3": 0.10667, + "precision_at_5": 0.07733, + "precision_at_10": 0.048, + "precision_at_20": 0.02933, + "precision_at_100": 0.0092, + "precision_at_1000": 0.00143, + "mrr_at_1": 0.173333, + "mrr_at_3": 0.217778, + "mrr_at_5": 0.226778, + "mrr_at_10": 0.238423, + "mrr_at_20": 0.243344, + "mrr_at_100": 0.246842, + "mrr_at_1000": 0.247628, + "nauc_ndcg_at_1_max": 0.443426, + "nauc_ndcg_at_1_std": 0.057658, + "nauc_ndcg_at_1_diff1": 0.433034, + "nauc_ndcg_at_3_max": 0.329881, + "nauc_ndcg_at_3_std": -0.014051, + "nauc_ndcg_at_3_diff1": 0.329118, + "nauc_ndcg_at_5_max": 0.317913, + "nauc_ndcg_at_5_std": -0.031328, + "nauc_ndcg_at_5_diff1": 0.331803, + "nauc_ndcg_at_10_max": 0.275334, + "nauc_ndcg_at_10_std": -0.048576, + "nauc_ndcg_at_10_diff1": 0.324386, + "nauc_ndcg_at_20_max": 0.292479, + "nauc_ndcg_at_20_std": -0.012281, + "nauc_ndcg_at_20_diff1": 0.337989, + "nauc_ndcg_at_100_max": 0.290275, + "nauc_ndcg_at_100_std": 0.002214, + "nauc_ndcg_at_100_diff1": 0.344517, + "nauc_ndcg_at_1000_max": 0.288739, + "nauc_ndcg_at_1000_std": 0.016163, + "nauc_ndcg_at_1000_diff1": 0.341582, + "nauc_map_at_1_max": 0.34342, + "nauc_map_at_1_std": -0.0136, + "nauc_map_at_1_diff1": 0.433366, + "nauc_map_at_3_max": 0.317985, + "nauc_map_at_3_std": -0.028076, + "nauc_map_at_3_diff1": 0.373514, + "nauc_map_at_5_max": 0.330389, + "nauc_map_at_5_std": -0.030043, + "nauc_map_at_5_diff1": 0.361352, + "nauc_map_at_10_max": 0.308804, + "nauc_map_at_10_std": -0.037228, + "nauc_map_at_10_diff1": 0.358722, + "nauc_map_at_20_max": 0.31533, + "nauc_map_at_20_std": -0.027, + "nauc_map_at_20_diff1": 0.362479, + "nauc_map_at_100_max": 0.315926, + "nauc_map_at_100_std": -0.023623, + "nauc_map_at_100_diff1": 0.361422, + "nauc_map_at_1000_max": 0.315701, + "nauc_map_at_1000_std": -0.022637, + "nauc_map_at_1000_diff1": 0.361644, + "nauc_recall_at_1_max": 0.34342, + "nauc_recall_at_1_std": -0.0136, + "nauc_recall_at_1_diff1": 0.433366, + "nauc_recall_at_3_max": 0.231595, + "nauc_recall_at_3_std": -0.037722, + "nauc_recall_at_3_diff1": 0.265762, + "nauc_recall_at_5_max": 0.224165, + "nauc_recall_at_5_std": -0.068521, + "nauc_recall_at_5_diff1": 0.251466, + "nauc_recall_at_10_max": 0.116481, + "nauc_recall_at_10_std": -0.104293, + "nauc_recall_at_10_diff1": 0.210983, + "nauc_recall_at_20_max": 0.148585, + "nauc_recall_at_20_std": -0.013932, + "nauc_recall_at_20_diff1": 0.246158, + "nauc_recall_at_100_max": 0.115732, + "nauc_recall_at_100_std": 0.017569, + "nauc_recall_at_100_diff1": 0.261808, + "nauc_recall_at_1000_max": 0.018707, + "nauc_recall_at_1000_std": 0.112385, + "nauc_recall_at_1000_diff1": 0.204573, + "nauc_precision_at_1_max": 0.443426, + "nauc_precision_at_1_std": 0.057658, + "nauc_precision_at_1_diff1": 0.433034, + "nauc_precision_at_3_max": 0.372676, + "nauc_precision_at_3_std": 0.033763, + "nauc_precision_at_3_diff1": 0.266439, + "nauc_precision_at_5_max": 0.38602, + "nauc_precision_at_5_std": 0.009947, + "nauc_precision_at_5_diff1": 0.245485, + "nauc_precision_at_10_max": 0.313953, + "nauc_precision_at_10_std": -0.028516, + "nauc_precision_at_10_diff1": 0.272506, + "nauc_precision_at_20_max": 0.37027, + "nauc_precision_at_20_std": 0.098986, + "nauc_precision_at_20_diff1": 0.290624, + "nauc_precision_at_100_max": 0.276981, + "nauc_precision_at_100_std": 0.131115, + "nauc_precision_at_100_diff1": 0.211145, + "nauc_precision_at_1000_max": 0.258201, + "nauc_precision_at_1000_std": 0.180358, + "nauc_precision_at_1000_diff1": 0.13699, + "nauc_mrr_at_1_max": 0.443426, + "nauc_mrr_at_1_std": 0.057658, + "nauc_mrr_at_1_diff1": 0.433034, + "nauc_mrr_at_3_max": 0.374712, + "nauc_mrr_at_3_std": 0.014559, + "nauc_mrr_at_3_diff1": 0.337, + "nauc_mrr_at_5_max": 0.369351, + "nauc_mrr_at_5_std": 0.002507, + "nauc_mrr_at_5_diff1": 0.334051, + "nauc_mrr_at_10_max": 0.355793, + "nauc_mrr_at_10_std": -0.003678, + "nauc_mrr_at_10_diff1": 0.333025, + "nauc_mrr_at_20_max": 0.357827, + "nauc_mrr_at_20_std": 0.006925, + "nauc_mrr_at_20_diff1": 0.334499, + "nauc_mrr_at_100_max": 0.357696, + "nauc_mrr_at_100_std": 0.009049, + "nauc_mrr_at_100_diff1": 0.336726, + "nauc_mrr_at_1000_max": 0.357325, + "nauc_mrr_at_1000_std": 0.008888, + "nauc_mrr_at_1000_diff1": 0.336603, + "main_score": 0.19668, + "hf_subset": "PMC-Treatment", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.12281, + "ndcg_at_3": 0.12049, + "ndcg_at_5": 0.13531, + "ndcg_at_10": 0.16318, + "ndcg_at_20": 0.18243, + "ndcg_at_100": 0.23335, + "ndcg_at_1000": 0.27772, + "map_at_1": 0.0614, + "map_at_3": 0.09064, + "map_at_5": 0.09942, + "map_at_10": 0.11194, + "map_at_20": 0.11748, + "map_at_100": 0.12658, + "map_at_1000": 0.12834, + "recall_at_1": 0.0614, + "recall_at_3": 0.12354, + "recall_at_5": 0.15716, + "recall_at_10": 0.22588, + "recall_at_20": 0.28436, + "recall_at_100": 0.5117, + "recall_at_1000": 0.80409, + "precision_at_1": 0.12281, + "precision_at_3": 0.0848, + "precision_at_5": 0.06491, + "precision_at_10": 0.04649, + "precision_at_20": 0.03026, + "precision_at_100": 0.01061, + "precision_at_1000": 0.00171, + "mrr_at_1": 0.122807, + "mrr_at_3": 0.172515, + "mrr_at_5": 0.183918, + "mrr_at_10": 0.196805, + "mrr_at_20": 0.203362, + "mrr_at_100": 0.208701, + "mrr_at_1000": 0.209797, + "nauc_ndcg_at_1_max": 0.169645, + "nauc_ndcg_at_1_std": 0.086512, + "nauc_ndcg_at_1_diff1": 0.259034, + "nauc_ndcg_at_3_max": 0.215349, + "nauc_ndcg_at_3_std": 0.103638, + "nauc_ndcg_at_3_diff1": 0.190799, + "nauc_ndcg_at_5_max": 0.222495, + "nauc_ndcg_at_5_std": 0.087801, + "nauc_ndcg_at_5_diff1": 0.204035, + "nauc_ndcg_at_10_max": 0.188661, + "nauc_ndcg_at_10_std": 0.068893, + "nauc_ndcg_at_10_diff1": 0.163527, + "nauc_ndcg_at_20_max": 0.165223, + "nauc_ndcg_at_20_std": 0.053953, + "nauc_ndcg_at_20_diff1": 0.12147, + "nauc_ndcg_at_100_max": 0.157739, + "nauc_ndcg_at_100_std": 0.092827, + "nauc_ndcg_at_100_diff1": 0.098738, + "nauc_ndcg_at_1000_max": 0.185248, + "nauc_ndcg_at_1000_std": 0.10283, + "nauc_ndcg_at_1000_diff1": 0.145056, + "nauc_map_at_1_max": 0.146135, + "nauc_map_at_1_std": 0.107548, + "nauc_map_at_1_diff1": 0.249071, + "nauc_map_at_3_max": 0.22907, + "nauc_map_at_3_std": 0.105895, + "nauc_map_at_3_diff1": 0.220778, + "nauc_map_at_5_max": 0.22655, + "nauc_map_at_5_std": 0.095182, + "nauc_map_at_5_diff1": 0.219996, + "nauc_map_at_10_max": 0.203672, + "nauc_map_at_10_std": 0.092381, + "nauc_map_at_10_diff1": 0.195327, + "nauc_map_at_20_max": 0.192269, + "nauc_map_at_20_std": 0.085628, + "nauc_map_at_20_diff1": 0.177635, + "nauc_map_at_100_max": 0.188389, + "nauc_map_at_100_std": 0.093941, + "nauc_map_at_100_diff1": 0.175489, + "nauc_map_at_1000_max": 0.190864, + "nauc_map_at_1000_std": 0.095149, + "nauc_map_at_1000_diff1": 0.178235, + "nauc_recall_at_1_max": 0.146135, + "nauc_recall_at_1_std": 0.107548, + "nauc_recall_at_1_diff1": 0.249071, + "nauc_recall_at_3_max": 0.242097, + "nauc_recall_at_3_std": 0.092795, + "nauc_recall_at_3_diff1": 0.163303, + "nauc_recall_at_5_max": 0.210143, + "nauc_recall_at_5_std": 0.061994, + "nauc_recall_at_5_diff1": 0.173598, + "nauc_recall_at_10_max": 0.152534, + "nauc_recall_at_10_std": 0.030007, + "nauc_recall_at_10_diff1": 0.103103, + "nauc_recall_at_20_max": 0.097913, + "nauc_recall_at_20_std": 0.001111, + "nauc_recall_at_20_diff1": 0.008658, + "nauc_recall_at_100_max": 0.080843, + "nauc_recall_at_100_std": 0.122606, + "nauc_recall_at_100_diff1": -0.070764, + "nauc_recall_at_1000_max": 0.178749, + "nauc_recall_at_1000_std": 0.194512, + "nauc_recall_at_1000_diff1": 0.116439, + "nauc_precision_at_1_max": 0.169645, + "nauc_precision_at_1_std": 0.086512, + "nauc_precision_at_1_diff1": 0.259034, + "nauc_precision_at_3_max": 0.238968, + "nauc_precision_at_3_std": 0.065391, + "nauc_precision_at_3_diff1": 0.179019, + "nauc_precision_at_5_max": 0.263924, + "nauc_precision_at_5_std": 0.054835, + "nauc_precision_at_5_diff1": 0.231202, + "nauc_precision_at_10_max": 0.153012, + "nauc_precision_at_10_std": 0.024587, + "nauc_precision_at_10_diff1": 0.140975, + "nauc_precision_at_20_max": 0.076827, + "nauc_precision_at_20_std": -0.007035, + "nauc_precision_at_20_diff1": 0.028611, + "nauc_precision_at_100_max": 0.052042, + "nauc_precision_at_100_std": 0.088079, + "nauc_precision_at_100_diff1": 0.006262, + "nauc_precision_at_1000_max": 0.075013, + "nauc_precision_at_1000_std": 0.060707, + "nauc_precision_at_1000_diff1": 0.087456, + "nauc_mrr_at_1_max": 0.169645, + "nauc_mrr_at_1_std": 0.086512, + "nauc_mrr_at_1_diff1": 0.259034, + "nauc_mrr_at_3_max": 0.189775, + "nauc_mrr_at_3_std": 0.105056, + "nauc_mrr_at_3_diff1": 0.171393, + "nauc_mrr_at_5_max": 0.190839, + "nauc_mrr_at_5_std": 0.102628, + "nauc_mrr_at_5_diff1": 0.191635, + "nauc_mrr_at_10_max": 0.182533, + "nauc_mrr_at_10_std": 0.082044, + "nauc_mrr_at_10_diff1": 0.171184, + "nauc_mrr_at_20_max": 0.181536, + "nauc_mrr_at_20_std": 0.079568, + "nauc_mrr_at_20_diff1": 0.161937, + "nauc_mrr_at_100_max": 0.182877, + "nauc_mrr_at_100_std": 0.082911, + "nauc_mrr_at_100_diff1": 0.1587, + "nauc_mrr_at_1000_max": 0.183006, + "nauc_mrr_at_1000_std": 0.083354, + "nauc_mrr_at_1000_diff1": 0.160242, + "main_score": 0.16318, + "hf_subset": "PMC-Clinical", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.13953, + "ndcg_at_3": 0.11952, + "ndcg_at_5": 0.13432, + "ndcg_at_10": 0.1539, + "ndcg_at_20": 0.18232, + "ndcg_at_100": 0.26282, + "ndcg_at_1000": 0.32984, + "map_at_1": 0.03953, + "map_at_3": 0.06807, + "map_at_5": 0.08462, + "map_at_10": 0.09388, + "map_at_20": 0.10284, + "map_at_100": 0.11894, + "map_at_1000": 0.12329, + "recall_at_1": 0.03953, + "recall_at_3": 0.09276, + "recall_at_5": 0.14315, + "recall_at_10": 0.18928, + "recall_at_20": 0.26163, + "recall_at_100": 0.56331, + "recall_at_1000": 0.92429, + "precision_at_1": 0.13953, + "precision_at_3": 0.10078, + "precision_at_5": 0.09612, + "precision_at_10": 0.06589, + "precision_at_20": 0.04729, + "precision_at_100": 0.02023, + "precision_at_1000": 0.00332, + "mrr_at_1": 0.139535, + "mrr_at_3": 0.197674, + "mrr_at_5": 0.218992, + "mrr_at_10": 0.229519, + "mrr_at_20": 0.238318, + "mrr_at_100": 0.244657, + "mrr_at_1000": 0.245448, + "nauc_ndcg_at_1_max": 0.254824, + "nauc_ndcg_at_1_std": 0.172705, + "nauc_ndcg_at_1_diff1": 0.058908, + "nauc_ndcg_at_3_max": 0.209052, + "nauc_ndcg_at_3_std": 0.137926, + "nauc_ndcg_at_3_diff1": 0.081678, + "nauc_ndcg_at_5_max": 0.211499, + "nauc_ndcg_at_5_std": 0.188849, + "nauc_ndcg_at_5_diff1": 0.073359, + "nauc_ndcg_at_10_max": 0.21883, + "nauc_ndcg_at_10_std": 0.171563, + "nauc_ndcg_at_10_diff1": 0.072559, + "nauc_ndcg_at_20_max": 0.21543, + "nauc_ndcg_at_20_std": 0.187349, + "nauc_ndcg_at_20_diff1": 0.050331, + "nauc_ndcg_at_100_max": 0.23119, + "nauc_ndcg_at_100_std": 0.261227, + "nauc_ndcg_at_100_diff1": 0.034208, + "nauc_ndcg_at_1000_max": 0.238239, + "nauc_ndcg_at_1000_std": 0.309201, + "nauc_ndcg_at_1000_diff1": -0.007805, + "nauc_map_at_1_max": 0.181174, + "nauc_map_at_1_std": 0.100545, + "nauc_map_at_1_diff1": 0.072952, + "nauc_map_at_3_max": 0.184944, + "nauc_map_at_3_std": 0.108469, + "nauc_map_at_3_diff1": 0.110981, + "nauc_map_at_5_max": 0.210788, + "nauc_map_at_5_std": 0.178389, + "nauc_map_at_5_diff1": 0.112753, + "nauc_map_at_10_max": 0.209348, + "nauc_map_at_10_std": 0.171956, + "nauc_map_at_10_diff1": 0.101941, + "nauc_map_at_20_max": 0.209875, + "nauc_map_at_20_std": 0.181036, + "nauc_map_at_20_diff1": 0.091958, + "nauc_map_at_100_max": 0.220146, + "nauc_map_at_100_std": 0.208391, + "nauc_map_at_100_diff1": 0.087918, + "nauc_map_at_1000_max": 0.220486, + "nauc_map_at_1000_std": 0.216525, + "nauc_map_at_1000_diff1": 0.083151, + "nauc_recall_at_1_max": 0.181174, + "nauc_recall_at_1_std": 0.100545, + "nauc_recall_at_1_diff1": 0.072952, + "nauc_recall_at_3_max": 0.132116, + "nauc_recall_at_3_std": 0.03394, + "nauc_recall_at_3_diff1": 0.142951, + "nauc_recall_at_5_max": 0.172569, + "nauc_recall_at_5_std": 0.166415, + "nauc_recall_at_5_diff1": 0.078067, + "nauc_recall_at_10_max": 0.159474, + "nauc_recall_at_10_std": 0.120667, + "nauc_recall_at_10_diff1": 0.06741, + "nauc_recall_at_20_max": 0.150295, + "nauc_recall_at_20_std": 0.138723, + "nauc_recall_at_20_diff1": 0.027336, + "nauc_recall_at_100_max": 0.191746, + "nauc_recall_at_100_std": 0.248544, + "nauc_recall_at_100_diff1": 0.010778, + "nauc_recall_at_1000_max": 0.306403, + "nauc_recall_at_1000_std": 0.763772, + "nauc_recall_at_1000_diff1": -0.358365, + "nauc_precision_at_1_max": 0.254824, + "nauc_precision_at_1_std": 0.172705, + "nauc_precision_at_1_diff1": 0.058908, + "nauc_precision_at_3_max": 0.267078, + "nauc_precision_at_3_std": 0.196798, + "nauc_precision_at_3_diff1": 0.091233, + "nauc_precision_at_5_max": 0.278691, + "nauc_precision_at_5_std": 0.287537, + "nauc_precision_at_5_diff1": 0.065819, + "nauc_precision_at_10_max": 0.273203, + "nauc_precision_at_10_std": 0.248227, + "nauc_precision_at_10_diff1": 0.052255, + "nauc_precision_at_20_max": 0.233093, + "nauc_precision_at_20_std": 0.266196, + "nauc_precision_at_20_diff1": -0.001165, + "nauc_precision_at_100_max": 0.192059, + "nauc_precision_at_100_std": 0.389829, + "nauc_precision_at_100_diff1": -0.076178, + "nauc_precision_at_1000_max": 0.135957, + "nauc_precision_at_1000_std": 0.426799, + "nauc_precision_at_1000_diff1": -0.215209, + "nauc_mrr_at_1_max": 0.254824, + "nauc_mrr_at_1_std": 0.172705, + "nauc_mrr_at_1_diff1": 0.058908, + "nauc_mrr_at_3_max": 0.225043, + "nauc_mrr_at_3_std": 0.157184, + "nauc_mrr_at_3_diff1": 0.053979, + "nauc_mrr_at_5_max": 0.222278, + "nauc_mrr_at_5_std": 0.168326, + "nauc_mrr_at_5_diff1": 0.027098, + "nauc_mrr_at_10_max": 0.230683, + "nauc_mrr_at_10_std": 0.168795, + "nauc_mrr_at_10_diff1": 0.027943, + "nauc_mrr_at_20_max": 0.225971, + "nauc_mrr_at_20_std": 0.172501, + "nauc_mrr_at_20_diff1": 0.018828, + "nauc_mrr_at_100_max": 0.224439, + "nauc_mrr_at_100_std": 0.176597, + "nauc_mrr_at_100_diff1": 0.021951, + "nauc_mrr_at_1000_max": 0.22405, + "nauc_mrr_at_1000_std": 0.175853, + "nauc_mrr_at_1000_diff1": 0.021483, + "main_score": 0.1539, + "hf_subset": "IIYi-Clinical", + "languages": [ + "eng-Latn" + ] + } + ] + }, + "evaluation_time": 274.3114514350891, + "kg_co2_emissions": null +} \ No newline at end of file diff --git a/results/GritLM__GritLM-7B/13f00a0e36500c80ce12870ea513846a066004af/R2MEDRetrieval.json b/results/GritLM__GritLM-7B/13f00a0e36500c80ce12870ea513846a066004af/R2MEDRetrieval.json new file mode 100644 index 0000000000..565c554e55 --- /dev/null +++ b/results/GritLM__GritLM-7B/13f00a0e36500c80ce12870ea513846a066004af/R2MEDRetrieval.json @@ -0,0 +1,1187 @@ +{ + "dataset_revision": "1.0", + "task_name": "R2MEDRetrieval", + "mteb_version": "1.38.20", + "scores": { + "test": [ + { + "ndcg_at_1": 0.14563, + "ndcg_at_3": 0.14967, + "ndcg_at_5": 0.15097, + "ndcg_at_10": 0.18313, + "ndcg_at_20": 0.2203, + "ndcg_at_100": 0.28899, + "ndcg_at_1000": 0.34335, + "map_at_1": 0.03751, + "map_at_3": 0.0844, + "map_at_5": 0.09658, + "map_at_10": 0.11721, + "map_at_20": 0.13349, + "map_at_100": 0.14833, + "map_at_1000": 0.15165, + "recall_at_1": 0.03751, + "recall_at_3": 0.11892, + "recall_at_5": 0.14987, + "recall_at_10": 0.23999, + "recall_at_20": 0.33766, + "recall_at_100": 0.59674, + "recall_at_1000": 0.90418, + "precision_at_1": 0.14563, + "precision_at_3": 0.12945, + "precision_at_5": 0.10485, + "precision_at_10": 0.08738, + "precision_at_20": 0.06408, + "precision_at_100": 0.02262, + "precision_at_1000": 0.00331, + "mrr_at_1": 0.145631, + "mrr_at_3": 0.200647, + "mrr_at_5": 0.213754, + "mrr_at_10": 0.231172, + "mrr_at_20": 0.238629, + "mrr_at_100": 0.243559, + "mrr_at_1000": 0.244385, + "nauc_ndcg_at_1_max": 0.007519, + "nauc_ndcg_at_1_std": -0.278497, + "nauc_ndcg_at_1_diff1": 0.125926, + "nauc_ndcg_at_3_max": -0.094597, + "nauc_ndcg_at_3_std": -0.287916, + "nauc_ndcg_at_3_diff1": -0.052645, + "nauc_ndcg_at_5_max": -0.082901, + "nauc_ndcg_at_5_std": -0.307288, + "nauc_ndcg_at_5_diff1": -0.022918, + "nauc_ndcg_at_10_max": -0.072597, + "nauc_ndcg_at_10_std": -0.308817, + "nauc_ndcg_at_10_diff1": -0.032579, + "nauc_ndcg_at_20_max": -0.088297, + "nauc_ndcg_at_20_std": -0.324763, + "nauc_ndcg_at_20_diff1": -0.022289, + "nauc_ndcg_at_100_max": -0.084555, + "nauc_ndcg_at_100_std": -0.341997, + "nauc_ndcg_at_100_diff1": -0.03562, + "nauc_ndcg_at_1000_max": -0.063824, + "nauc_ndcg_at_1000_std": -0.307505, + "nauc_ndcg_at_1000_diff1": -0.031227, + "nauc_map_at_1_max": -0.049019, + "nauc_map_at_1_std": -0.265898, + "nauc_map_at_1_diff1": 0.081364, + "nauc_map_at_3_max": -0.134721, + "nauc_map_at_3_std": -0.275889, + "nauc_map_at_3_diff1": -0.095366, + "nauc_map_at_5_max": -0.077803, + "nauc_map_at_5_std": -0.27791, + "nauc_map_at_5_diff1": -0.058963, + "nauc_map_at_10_max": -0.069344, + "nauc_map_at_10_std": -0.284016, + "nauc_map_at_10_diff1": -0.045531, + "nauc_map_at_20_max": -0.07049, + "nauc_map_at_20_std": -0.296479, + "nauc_map_at_20_diff1": -0.033673, + "nauc_map_at_100_max": -0.077202, + "nauc_map_at_100_std": -0.306991, + "nauc_map_at_100_diff1": -0.043852, + "nauc_map_at_1000_max": -0.076819, + "nauc_map_at_1000_std": -0.306775, + "nauc_map_at_1000_diff1": -0.044864, + "nauc_recall_at_1_max": -0.049019, + "nauc_recall_at_1_std": -0.265898, + "nauc_recall_at_1_diff1": 0.081364, + "nauc_recall_at_3_max": -0.136701, + "nauc_recall_at_3_std": -0.261975, + "nauc_recall_at_3_diff1": -0.116534, + "nauc_recall_at_5_max": -0.078755, + "nauc_recall_at_5_std": -0.290468, + "nauc_recall_at_5_diff1": -0.045788, + "nauc_recall_at_10_max": -0.088907, + "nauc_recall_at_10_std": -0.291093, + "nauc_recall_at_10_diff1": -0.064835, + "nauc_recall_at_20_max": -0.122917, + "nauc_recall_at_20_std": -0.305633, + "nauc_recall_at_20_diff1": -0.04781, + "nauc_recall_at_100_max": -0.109764, + "nauc_recall_at_100_std": -0.329487, + "nauc_recall_at_100_diff1": -0.065802, + "nauc_recall_at_1000_max": 0.163117, + "nauc_recall_at_1000_std": 0.174123, + "nauc_recall_at_1000_diff1": -0.061407, + "nauc_precision_at_1_max": 0.007519, + "nauc_precision_at_1_std": -0.278497, + "nauc_precision_at_1_diff1": 0.125926, + "nauc_precision_at_3_max": -0.058285, + "nauc_precision_at_3_std": -0.254348, + "nauc_precision_at_3_diff1": -0.054163, + "nauc_precision_at_5_max": -0.0005, + "nauc_precision_at_5_std": -0.290619, + "nauc_precision_at_5_diff1": 0.013264, + "nauc_precision_at_10_max": -0.057619, + "nauc_precision_at_10_std": -0.319099, + "nauc_precision_at_10_diff1": -0.027439, + "nauc_precision_at_20_max": -0.087886, + "nauc_precision_at_20_std": -0.3317, + "nauc_precision_at_20_diff1": -0.008245, + "nauc_precision_at_100_max": -0.062091, + "nauc_precision_at_100_std": -0.295436, + "nauc_precision_at_100_diff1": -0.070108, + "nauc_precision_at_1000_max": -0.012414, + "nauc_precision_at_1000_std": -0.158372, + "nauc_precision_at_1000_diff1": -0.057727, + "nauc_mrr_at_1_max": 0.007519, + "nauc_mrr_at_1_std": -0.278497, + "nauc_mrr_at_1_diff1": 0.125926, + "nauc_mrr_at_3_max": -0.029407, + "nauc_mrr_at_3_std": -0.289519, + "nauc_mrr_at_3_diff1": 0.058546, + "nauc_mrr_at_5_max": -0.035291, + "nauc_mrr_at_5_std": -0.307299, + "nauc_mrr_at_5_diff1": 0.061236, + "nauc_mrr_at_10_max": -0.036898, + "nauc_mrr_at_10_std": -0.309111, + "nauc_mrr_at_10_diff1": 0.035295, + "nauc_mrr_at_20_max": -0.050791, + "nauc_mrr_at_20_std": -0.323142, + "nauc_mrr_at_20_diff1": 0.048653, + "nauc_mrr_at_100_max": -0.048676, + "nauc_mrr_at_100_std": -0.322018, + "nauc_mrr_at_100_diff1": 0.050303, + "nauc_mrr_at_1000_max": -0.048185, + "nauc_mrr_at_1000_std": -0.321221, + "nauc_mrr_at_1000_diff1": 0.05009, + "main_score": 0.18313, + "hf_subset": "Biology", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.27273, + "ndcg_at_3": 0.30705, + "ndcg_at_5": 0.3486, + "ndcg_at_10": 0.39546, + "ndcg_at_20": 0.44775, + "ndcg_at_100": 0.49985, + "ndcg_at_1000": 0.52086, + "map_at_1": 0.13811, + "map_at_3": 0.22079, + "map_at_5": 0.26672, + "map_at_10": 0.29904, + "map_at_20": 0.3241, + "map_at_100": 0.33799, + "map_at_1000": 0.33952, + "recall_at_1": 0.13811, + "recall_at_3": 0.28545, + "recall_at_5": 0.40541, + "recall_at_10": 0.53649, + "recall_at_20": 0.68057, + "recall_at_100": 0.87353, + "recall_at_1000": 0.99382, + "precision_at_1": 0.27273, + "precision_at_3": 0.20779, + "precision_at_5": 0.19481, + "precision_at_10": 0.13506, + "precision_at_20": 0.09156, + "precision_at_100": 0.02545, + "precision_at_1000": 0.00292, + "mrr_at_1": 0.272727, + "mrr_at_3": 0.372294, + "mrr_at_5": 0.398268, + "mrr_at_10": 0.415842, + "mrr_at_20": 0.422031, + "mrr_at_100": 0.424756, + "mrr_at_1000": 0.425138, + "nauc_ndcg_at_1_max": 0.125187, + "nauc_ndcg_at_1_std": -0.22573, + "nauc_ndcg_at_1_diff1": 0.117205, + "nauc_ndcg_at_3_max": 0.016705, + "nauc_ndcg_at_3_std": -0.233157, + "nauc_ndcg_at_3_diff1": 0.123187, + "nauc_ndcg_at_5_max": 0.082658, + "nauc_ndcg_at_5_std": -0.163495, + "nauc_ndcg_at_5_diff1": 0.113404, + "nauc_ndcg_at_10_max": 0.112188, + "nauc_ndcg_at_10_std": -0.139714, + "nauc_ndcg_at_10_diff1": 0.035169, + "nauc_ndcg_at_20_max": 0.115077, + "nauc_ndcg_at_20_std": -0.14901, + "nauc_ndcg_at_20_diff1": 0.026141, + "nauc_ndcg_at_100_max": 0.102494, + "nauc_ndcg_at_100_std": -0.138072, + "nauc_ndcg_at_100_diff1": 0.036273, + "nauc_ndcg_at_1000_max": 0.091327, + "nauc_ndcg_at_1000_std": -0.16245, + "nauc_ndcg_at_1000_diff1": 0.043867, + "nauc_map_at_1_max": -0.094393, + "nauc_map_at_1_std": -0.204863, + "nauc_map_at_1_diff1": 0.192928, + "nauc_map_at_3_max": -0.064818, + "nauc_map_at_3_std": -0.222871, + "nauc_map_at_3_diff1": 0.145134, + "nauc_map_at_5_max": 0.024041, + "nauc_map_at_5_std": -0.168014, + "nauc_map_at_5_diff1": 0.134739, + "nauc_map_at_10_max": 0.064993, + "nauc_map_at_10_std": -0.144087, + "nauc_map_at_10_diff1": 0.089154, + "nauc_map_at_20_max": 0.072219, + "nauc_map_at_20_std": -0.152698, + "nauc_map_at_20_diff1": 0.082437, + "nauc_map_at_100_max": 0.071024, + "nauc_map_at_100_std": -0.151851, + "nauc_map_at_100_diff1": 0.079706, + "nauc_map_at_1000_max": 0.069488, + "nauc_map_at_1000_std": -0.153562, + "nauc_map_at_1000_diff1": 0.079794, + "nauc_recall_at_1_max": -0.094393, + "nauc_recall_at_1_std": -0.204863, + "nauc_recall_at_1_diff1": 0.192928, + "nauc_recall_at_3_max": -0.046547, + "nauc_recall_at_3_std": -0.195966, + "nauc_recall_at_3_diff1": 0.113432, + "nauc_recall_at_5_max": 0.100169, + "nauc_recall_at_5_std": -0.079576, + "nauc_recall_at_5_diff1": 0.073312, + "nauc_recall_at_10_max": 0.159451, + "nauc_recall_at_10_std": -0.041709, + "nauc_recall_at_10_diff1": -0.078813, + "nauc_recall_at_20_max": 0.169777, + "nauc_recall_at_20_std": -0.022371, + "nauc_recall_at_20_diff1": -0.129667, + "nauc_recall_at_100_max": 0.185079, + "nauc_recall_at_100_std": 0.167977, + "nauc_recall_at_100_diff1": -0.083108, + "nauc_recall_at_1000_max": 0.439966, + "nauc_recall_at_1000_std": 0.337689, + "nauc_recall_at_1000_diff1": 0.037972, + "nauc_precision_at_1_max": 0.125187, + "nauc_precision_at_1_std": -0.22573, + "nauc_precision_at_1_diff1": 0.117205, + "nauc_precision_at_3_max": 0.104549, + "nauc_precision_at_3_std": -0.196859, + "nauc_precision_at_3_diff1": 0.016266, + "nauc_precision_at_5_max": 0.253733, + "nauc_precision_at_5_std": -0.048876, + "nauc_precision_at_5_diff1": -0.006117, + "nauc_precision_at_10_max": 0.257505, + "nauc_precision_at_10_std": -0.025405, + "nauc_precision_at_10_diff1": -0.116464, + "nauc_precision_at_20_max": 0.215006, + "nauc_precision_at_20_std": -0.046302, + "nauc_precision_at_20_diff1": -0.091147, + "nauc_precision_at_100_max": 0.098726, + "nauc_precision_at_100_std": 0.00021, + "nauc_precision_at_100_diff1": -0.080737, + "nauc_precision_at_1000_max": 0.056436, + "nauc_precision_at_1000_std": -0.015866, + "nauc_precision_at_1000_diff1": -0.068234, + "nauc_mrr_at_1_max": 0.125187, + "nauc_mrr_at_1_std": -0.22573, + "nauc_mrr_at_1_diff1": 0.117205, + "nauc_mrr_at_3_max": 0.084195, + "nauc_mrr_at_3_std": -0.253118, + "nauc_mrr_at_3_diff1": 0.092237, + "nauc_mrr_at_5_max": 0.109906, + "nauc_mrr_at_5_std": -0.215326, + "nauc_mrr_at_5_diff1": 0.08098, + "nauc_mrr_at_10_max": 0.113134, + "nauc_mrr_at_10_std": -0.220638, + "nauc_mrr_at_10_diff1": 0.068889, + "nauc_mrr_at_20_max": 0.110484, + "nauc_mrr_at_20_std": -0.223218, + "nauc_mrr_at_20_diff1": 0.071023, + "nauc_mrr_at_100_max": 0.111072, + "nauc_mrr_at_100_std": -0.221249, + "nauc_mrr_at_100_diff1": 0.073698, + "nauc_mrr_at_1000_max": 0.110695, + "nauc_mrr_at_1000_std": -0.222022, + "nauc_mrr_at_1000_diff1": 0.073684, + "main_score": 0.39546, + "hf_subset": "Bioinformatics", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.35227, + "ndcg_at_3": 0.38147, + "ndcg_at_5": 0.40584, + "ndcg_at_10": 0.45676, + "ndcg_at_20": 0.49957, + "ndcg_at_100": 0.54889, + "ndcg_at_1000": 0.56589, + "map_at_1": 0.19671, + "map_at_3": 0.30359, + "map_at_5": 0.33251, + "map_at_10": 0.36551, + "map_at_20": 0.38221, + "map_at_100": 0.3951, + "map_at_1000": 0.3964, + "recall_at_1": 0.19671, + "recall_at_3": 0.38351, + "recall_at_5": 0.45931, + "recall_at_10": 0.58939, + "recall_at_20": 0.71627, + "recall_at_100": 0.88908, + "recall_at_1000": 0.98106, + "precision_at_1": 0.35227, + "precision_at_3": 0.25, + "precision_at_5": 0.19318, + "precision_at_10": 0.1375, + "precision_at_20": 0.08636, + "precision_at_100": 0.02409, + "precision_at_1000": 0.00274, + "mrr_at_1": 0.352273, + "mrr_at_3": 0.441288, + "mrr_at_5": 0.464583, + "mrr_at_10": 0.478526, + "mrr_at_20": 0.488301, + "mrr_at_100": 0.490609, + "mrr_at_1000": 0.490784, + "nauc_ndcg_at_1_max": 0.321198, + "nauc_ndcg_at_1_std": 0.125558, + "nauc_ndcg_at_1_diff1": 0.080205, + "nauc_ndcg_at_3_max": 0.336965, + "nauc_ndcg_at_3_std": 0.015712, + "nauc_ndcg_at_3_diff1": 0.071715, + "nauc_ndcg_at_5_max": 0.365259, + "nauc_ndcg_at_5_std": 0.018258, + "nauc_ndcg_at_5_diff1": 0.104508, + "nauc_ndcg_at_10_max": 0.340993, + "nauc_ndcg_at_10_std": -0.016031, + "nauc_ndcg_at_10_diff1": 0.093993, + "nauc_ndcg_at_20_max": 0.331543, + "nauc_ndcg_at_20_std": -0.029619, + "nauc_ndcg_at_20_diff1": 0.075542, + "nauc_ndcg_at_100_max": 0.345762, + "nauc_ndcg_at_100_std": 0.037251, + "nauc_ndcg_at_100_diff1": 0.055495, + "nauc_ndcg_at_1000_max": 0.348712, + "nauc_ndcg_at_1000_std": 0.053581, + "nauc_ndcg_at_1000_diff1": 0.046165, + "nauc_map_at_1_max": 0.194802, + "nauc_map_at_1_std": -0.023639, + "nauc_map_at_1_diff1": 0.156575, + "nauc_map_at_3_max": 0.301359, + "nauc_map_at_3_std": -0.02167, + "nauc_map_at_3_diff1": 0.12012, + "nauc_map_at_5_max": 0.323199, + "nauc_map_at_5_std": -0.000234, + "nauc_map_at_5_diff1": 0.116353, + "nauc_map_at_10_max": 0.318453, + "nauc_map_at_10_std": -0.003888, + "nauc_map_at_10_diff1": 0.090451, + "nauc_map_at_20_max": 0.316411, + "nauc_map_at_20_std": -0.010547, + "nauc_map_at_20_diff1": 0.084647, + "nauc_map_at_100_max": 0.321934, + "nauc_map_at_100_std": 0.006811, + "nauc_map_at_100_diff1": 0.078303, + "nauc_map_at_1000_max": 0.321728, + "nauc_map_at_1000_std": 0.007762, + "nauc_map_at_1000_diff1": 0.077006, + "nauc_recall_at_1_max": 0.194802, + "nauc_recall_at_1_std": -0.023639, + "nauc_recall_at_1_diff1": 0.156575, + "nauc_recall_at_3_max": 0.289609, + "nauc_recall_at_3_std": -0.097583, + "nauc_recall_at_3_diff1": 0.09703, + "nauc_recall_at_5_max": 0.361637, + "nauc_recall_at_5_std": -0.056437, + "nauc_recall_at_5_diff1": 0.146788, + "nauc_recall_at_10_max": 0.320475, + "nauc_recall_at_10_std": -0.139523, + "nauc_recall_at_10_diff1": 0.126317, + "nauc_recall_at_20_max": 0.237511, + "nauc_recall_at_20_std": -0.269406, + "nauc_recall_at_20_diff1": 0.086471, + "nauc_recall_at_100_max": 0.258505, + "nauc_recall_at_100_std": -0.095992, + "nauc_recall_at_100_diff1": -0.014746, + "nauc_recall_at_1000_max": 0.499841, + "nauc_recall_at_1000_std": 0.298748, + "nauc_recall_at_1000_diff1": -0.62775, + "nauc_precision_at_1_max": 0.321198, + "nauc_precision_at_1_std": 0.125558, + "nauc_precision_at_1_diff1": 0.080205, + "nauc_precision_at_3_max": 0.398302, + "nauc_precision_at_3_std": 0.149704, + "nauc_precision_at_3_diff1": -0.022904, + "nauc_precision_at_5_max": 0.421773, + "nauc_precision_at_5_std": 0.205801, + "nauc_precision_at_5_diff1": -0.048271, + "nauc_precision_at_10_max": 0.259884, + "nauc_precision_at_10_std": 0.125251, + "nauc_precision_at_10_diff1": -0.164845, + "nauc_precision_at_20_max": 0.185833, + "nauc_precision_at_20_std": 0.132937, + "nauc_precision_at_20_diff1": -0.229464, + "nauc_precision_at_100_max": 0.098941, + "nauc_precision_at_100_std": 0.279769, + "nauc_precision_at_100_diff1": -0.237913, + "nauc_precision_at_1000_max": 0.04178, + "nauc_precision_at_1000_std": 0.287286, + "nauc_precision_at_1000_diff1": -0.257499, + "nauc_mrr_at_1_max": 0.321198, + "nauc_mrr_at_1_std": 0.125558, + "nauc_mrr_at_1_diff1": 0.080205, + "nauc_mrr_at_3_max": 0.339742, + "nauc_mrr_at_3_std": 0.07202, + "nauc_mrr_at_3_diff1": 0.06971, + "nauc_mrr_at_5_max": 0.366213, + "nauc_mrr_at_5_std": 0.088396, + "nauc_mrr_at_5_diff1": 0.08652, + "nauc_mrr_at_10_max": 0.356746, + "nauc_mrr_at_10_std": 0.076617, + "nauc_mrr_at_10_diff1": 0.080952, + "nauc_mrr_at_20_max": 0.350746, + "nauc_mrr_at_20_std": 0.075958, + "nauc_mrr_at_20_diff1": 0.0715, + "nauc_mrr_at_100_max": 0.351158, + "nauc_mrr_at_100_std": 0.080858, + "nauc_mrr_at_100_diff1": 0.073082, + "nauc_mrr_at_1000_max": 0.35129, + "nauc_mrr_at_1000_std": 0.080916, + "nauc_mrr_at_1000_diff1": 0.073283, + "main_score": 0.45676, + "hf_subset": "Medical-Sciences", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.13402, + "ndcg_at_3": 0.12202, + "ndcg_at_5": 0.12082, + "ndcg_at_10": 0.13325, + "ndcg_at_20": 0.16033, + "ndcg_at_100": 0.20617, + "ndcg_at_1000": 0.26071, + "map_at_1": 0.06807, + "map_at_3": 0.08715, + "map_at_5": 0.09043, + "map_at_10": 0.09702, + "map_at_20": 0.10498, + "map_at_100": 0.11268, + "map_at_1000": 0.11478, + "recall_at_1": 0.06807, + "recall_at_3": 0.10631, + "recall_at_5": 0.12048, + "recall_at_10": 0.1547, + "recall_at_20": 0.24148, + "recall_at_100": 0.42787, + "recall_at_1000": 0.76529, + "precision_at_1": 0.13402, + "precision_at_3": 0.08247, + "precision_at_5": 0.05979, + "precision_at_10": 0.04021, + "precision_at_20": 0.03041, + "precision_at_100": 0.01186, + "precision_at_1000": 0.00222, + "mrr_at_1": 0.134021, + "mrr_at_3": 0.166667, + "mrr_at_5": 0.178522, + "mrr_at_10": 0.185178, + "mrr_at_20": 0.191806, + "mrr_at_100": 0.196048, + "mrr_at_1000": 0.197117, + "nauc_ndcg_at_1_max": 0.148123, + "nauc_ndcg_at_1_std": 0.190142, + "nauc_ndcg_at_1_diff1": -0.010443, + "nauc_ndcg_at_3_max": 0.090078, + "nauc_ndcg_at_3_std": 0.098444, + "nauc_ndcg_at_3_diff1": 0.013233, + "nauc_ndcg_at_5_max": 0.052937, + "nauc_ndcg_at_5_std": 0.077328, + "nauc_ndcg_at_5_diff1": -0.011475, + "nauc_ndcg_at_10_max": 0.053335, + "nauc_ndcg_at_10_std": 0.097818, + "nauc_ndcg_at_10_diff1": 0.001765, + "nauc_ndcg_at_20_max": 0.086017, + "nauc_ndcg_at_20_std": 0.124924, + "nauc_ndcg_at_20_diff1": -0.01358, + "nauc_ndcg_at_100_max": 0.152298, + "nauc_ndcg_at_100_std": 0.180937, + "nauc_ndcg_at_100_diff1": -0.035217, + "nauc_ndcg_at_1000_max": 0.141274, + "nauc_ndcg_at_1000_std": 0.19781, + "nauc_ndcg_at_1000_diff1": -0.036276, + "nauc_map_at_1_max": -0.03102, + "nauc_map_at_1_std": -0.041293, + "nauc_map_at_1_diff1": 0.117753, + "nauc_map_at_3_max": 0.021036, + "nauc_map_at_3_std": -0.016704, + "nauc_map_at_3_diff1": 0.059168, + "nauc_map_at_5_max": 0.01778, + "nauc_map_at_5_std": -0.008787, + "nauc_map_at_5_diff1": 0.039972, + "nauc_map_at_10_max": 0.024739, + "nauc_map_at_10_std": 0.022402, + "nauc_map_at_10_diff1": 0.042643, + "nauc_map_at_20_max": 0.034778, + "nauc_map_at_20_std": 0.03332, + "nauc_map_at_20_diff1": 0.033239, + "nauc_map_at_100_max": 0.053316, + "nauc_map_at_100_std": 0.054594, + "nauc_map_at_100_diff1": 0.028494, + "nauc_map_at_1000_max": 0.053756, + "nauc_map_at_1000_std": 0.056741, + "nauc_map_at_1000_diff1": 0.028299, + "nauc_recall_at_1_max": -0.03102, + "nauc_recall_at_1_std": -0.041293, + "nauc_recall_at_1_diff1": 0.117753, + "nauc_recall_at_3_max": 0.036974, + "nauc_recall_at_3_std": 0.007672, + "nauc_recall_at_3_diff1": 0.027316, + "nauc_recall_at_5_max": 0.027688, + "nauc_recall_at_5_std": 0.039551, + "nauc_recall_at_5_diff1": -0.03722, + "nauc_recall_at_10_max": 0.021121, + "nauc_recall_at_10_std": 0.079287, + "nauc_recall_at_10_diff1": -0.002955, + "nauc_recall_at_20_max": 0.096758, + "nauc_recall_at_20_std": 0.140799, + "nauc_recall_at_20_diff1": -0.038067, + "nauc_recall_at_100_max": 0.292944, + "nauc_recall_at_100_std": 0.272648, + "nauc_recall_at_100_diff1": -0.063151, + "nauc_recall_at_1000_max": 0.383743, + "nauc_recall_at_1000_std": 0.462862, + "nauc_recall_at_1000_diff1": 0.00617, + "nauc_precision_at_1_max": 0.148123, + "nauc_precision_at_1_std": 0.190142, + "nauc_precision_at_1_diff1": -0.010443, + "nauc_precision_at_3_max": 0.12404, + "nauc_precision_at_3_std": 0.197481, + "nauc_precision_at_3_diff1": -0.04403, + "nauc_precision_at_5_max": 0.111637, + "nauc_precision_at_5_std": 0.233964, + "nauc_precision_at_5_diff1": -0.136846, + "nauc_precision_at_10_max": 0.156282, + "nauc_precision_at_10_std": 0.303231, + "nauc_precision_at_10_diff1": -0.090207, + "nauc_precision_at_20_max": 0.214049, + "nauc_precision_at_20_std": 0.305588, + "nauc_precision_at_20_diff1": -0.084372, + "nauc_precision_at_100_max": 0.294098, + "nauc_precision_at_100_std": 0.364733, + "nauc_precision_at_100_diff1": -0.153226, + "nauc_precision_at_1000_max": 0.143931, + "nauc_precision_at_1000_std": 0.304845, + "nauc_precision_at_1000_diff1": -0.190371, + "nauc_mrr_at_1_max": 0.148123, + "nauc_mrr_at_1_std": 0.190142, + "nauc_mrr_at_1_diff1": -0.010443, + "nauc_mrr_at_3_max": 0.136725, + "nauc_mrr_at_3_std": 0.192821, + "nauc_mrr_at_3_diff1": -0.006169, + "nauc_mrr_at_5_max": 0.130576, + "nauc_mrr_at_5_std": 0.202363, + "nauc_mrr_at_5_diff1": -0.038736, + "nauc_mrr_at_10_max": 0.12315, + "nauc_mrr_at_10_std": 0.196777, + "nauc_mrr_at_10_diff1": -0.038401, + "nauc_mrr_at_20_max": 0.135693, + "nauc_mrr_at_20_std": 0.204833, + "nauc_mrr_at_20_diff1": -0.040009, + "nauc_mrr_at_100_max": 0.136157, + "nauc_mrr_at_100_std": 0.204052, + "nauc_mrr_at_100_diff1": -0.043264, + "nauc_mrr_at_1000_max": 0.135839, + "nauc_mrr_at_1000_std": 0.203833, + "nauc_mrr_at_1000_diff1": -0.042625, + "main_score": 0.13325, + "hf_subset": "MedXpertQA-Exam", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.17797, + "ndcg_at_3": 0.16405, + "ndcg_at_5": 0.1671, + "ndcg_at_10": 0.19697, + "ndcg_at_20": 0.22409, + "ndcg_at_100": 0.28734, + "ndcg_at_1000": 0.34653, + "map_at_1": 0.05847, + "map_at_3": 0.09952, + "map_at_5": 0.11246, + "map_at_10": 0.13391, + "map_at_20": 0.14526, + "map_at_100": 0.15775, + "map_at_1000": 0.16161, + "recall_at_1": 0.05847, + "recall_at_3": 0.13051, + "recall_at_5": 0.16422, + "recall_at_10": 0.2344, + "recall_at_20": 0.30604, + "recall_at_100": 0.52759, + "recall_at_1000": 0.82524, + "precision_at_1": 0.17797, + "precision_at_3": 0.13842, + "precision_at_5": 0.11525, + "precision_at_10": 0.08898, + "precision_at_20": 0.05805, + "precision_at_100": 0.02153, + "precision_at_1000": 0.00358, + "mrr_at_1": 0.177966, + "mrr_at_3": 0.233051, + "mrr_at_5": 0.257203, + "mrr_at_10": 0.265355, + "mrr_at_20": 0.269188, + "mrr_at_100": 0.27537, + "mrr_at_1000": 0.276154, + "nauc_ndcg_at_1_max": 0.056562, + "nauc_ndcg_at_1_std": 0.019468, + "nauc_ndcg_at_1_diff1": -0.001711, + "nauc_ndcg_at_3_max": 0.080554, + "nauc_ndcg_at_3_std": 0.021028, + "nauc_ndcg_at_3_diff1": 0.032576, + "nauc_ndcg_at_5_max": 0.058537, + "nauc_ndcg_at_5_std": 0.001771, + "nauc_ndcg_at_5_diff1": -0.004246, + "nauc_ndcg_at_10_max": 0.098376, + "nauc_ndcg_at_10_std": 0.038759, + "nauc_ndcg_at_10_diff1": 0.003457, + "nauc_ndcg_at_20_max": 0.152379, + "nauc_ndcg_at_20_std": 0.071799, + "nauc_ndcg_at_20_diff1": 0.027044, + "nauc_ndcg_at_100_max": 0.148836, + "nauc_ndcg_at_100_std": 0.086119, + "nauc_ndcg_at_100_diff1": 0.022519, + "nauc_ndcg_at_1000_max": 0.131579, + "nauc_ndcg_at_1000_std": 0.061563, + "nauc_ndcg_at_1000_diff1": 0.014548, + "nauc_map_at_1_max": -0.085157, + "nauc_map_at_1_std": -0.124027, + "nauc_map_at_1_diff1": -0.114886, + "nauc_map_at_3_max": 0.01999, + "nauc_map_at_3_std": -0.055043, + "nauc_map_at_3_diff1": 0.006249, + "nauc_map_at_5_max": 0.032407, + "nauc_map_at_5_std": -0.035722, + "nauc_map_at_5_diff1": -1.3e-05, + "nauc_map_at_10_max": 0.066824, + "nauc_map_at_10_std": 0.001072, + "nauc_map_at_10_diff1": -0.003334, + "nauc_map_at_20_max": 0.097148, + "nauc_map_at_20_std": 0.025804, + "nauc_map_at_20_diff1": 0.007358, + "nauc_map_at_100_max": 0.097349, + "nauc_map_at_100_std": 0.028103, + "nauc_map_at_100_diff1": 0.001375, + "nauc_map_at_1000_max": 0.095381, + "nauc_map_at_1000_std": 0.027461, + "nauc_map_at_1000_diff1": 0.001295, + "nauc_recall_at_1_max": -0.085157, + "nauc_recall_at_1_std": -0.124027, + "nauc_recall_at_1_diff1": -0.114886, + "nauc_recall_at_3_max": 0.071574, + "nauc_recall_at_3_std": -0.018402, + "nauc_recall_at_3_diff1": 0.063178, + "nauc_recall_at_5_max": 0.075083, + "nauc_recall_at_5_std": 0.002823, + "nauc_recall_at_5_diff1": 0.023802, + "nauc_recall_at_10_max": 0.130984, + "nauc_recall_at_10_std": 0.077626, + "nauc_recall_at_10_diff1": 0.026918, + "nauc_recall_at_20_max": 0.25358, + "nauc_recall_at_20_std": 0.146724, + "nauc_recall_at_20_diff1": 0.07554, + "nauc_recall_at_100_max": 0.26364, + "nauc_recall_at_100_std": 0.242074, + "nauc_recall_at_100_diff1": 0.052216, + "nauc_recall_at_1000_max": 0.293565, + "nauc_recall_at_1000_std": 0.227033, + "nauc_recall_at_1000_diff1": -0.025375, + "nauc_precision_at_1_max": 0.056562, + "nauc_precision_at_1_std": 0.019468, + "nauc_precision_at_1_diff1": -0.001711, + "nauc_precision_at_3_max": 0.141421, + "nauc_precision_at_3_std": 0.049502, + "nauc_precision_at_3_diff1": 0.075025, + "nauc_precision_at_5_max": 0.090126, + "nauc_precision_at_5_std": 0.030634, + "nauc_precision_at_5_diff1": -0.017485, + "nauc_precision_at_10_max": 0.127555, + "nauc_precision_at_10_std": 0.08032, + "nauc_precision_at_10_diff1": -0.039297, + "nauc_precision_at_20_max": 0.197441, + "nauc_precision_at_20_std": 0.118029, + "nauc_precision_at_20_diff1": 0.00597, + "nauc_precision_at_100_max": 0.120303, + "nauc_precision_at_100_std": 0.101014, + "nauc_precision_at_100_diff1": 0.027431, + "nauc_precision_at_1000_max": 0.002714, + "nauc_precision_at_1000_std": -0.024707, + "nauc_precision_at_1000_diff1": 0.021652, + "nauc_mrr_at_1_max": 0.056562, + "nauc_mrr_at_1_std": 0.019468, + "nauc_mrr_at_1_diff1": -0.001711, + "nauc_mrr_at_3_max": 0.114958, + "nauc_mrr_at_3_std": 0.054917, + "nauc_mrr_at_3_diff1": 0.0414, + "nauc_mrr_at_5_max": 0.094917, + "nauc_mrr_at_5_std": 0.0428, + "nauc_mrr_at_5_diff1": 0.004649, + "nauc_mrr_at_10_max": 0.095913, + "nauc_mrr_at_10_std": 0.04952, + "nauc_mrr_at_10_diff1": 0.012291, + "nauc_mrr_at_20_max": 0.099902, + "nauc_mrr_at_20_std": 0.047432, + "nauc_mrr_at_20_diff1": 0.014808, + "nauc_mrr_at_100_max": 0.099509, + "nauc_mrr_at_100_std": 0.045363, + "nauc_mrr_at_100_diff1": 0.016582, + "nauc_mrr_at_1000_max": 0.099271, + "nauc_mrr_at_1000_std": 0.045287, + "nauc_mrr_at_1000_diff1": 0.016033, + "main_score": 0.19697, + "hf_subset": "MedQA-Diag", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.37333, + "ndcg_at_3": 0.32499, + "ndcg_at_5": 0.34215, + "ndcg_at_10": 0.3721, + "ndcg_at_20": 0.3985, + "ndcg_at_100": 0.43544, + "ndcg_at_1000": 0.46684, + "map_at_1": 0.23444, + "map_at_3": 0.27706, + "map_at_5": 0.29469, + "map_at_10": 0.31152, + "map_at_20": 0.32012, + "map_at_100": 0.32665, + "map_at_1000": 0.3281, + "recall_at_1": 0.23444, + "recall_at_3": 0.30533, + "recall_at_5": 0.35878, + "recall_at_10": 0.42978, + "recall_at_20": 0.51878, + "recall_at_100": 0.68067, + "recall_at_1000": 0.89067, + "precision_at_1": 0.37333, + "precision_at_3": 0.18444, + "precision_at_5": 0.13333, + "precision_at_10": 0.08533, + "precision_at_20": 0.05067, + "precision_at_100": 0.014, + "precision_at_1000": 0.00187, + "mrr_at_1": 0.373333, + "mrr_at_3": 0.412222, + "mrr_at_5": 0.426222, + "mrr_at_10": 0.435646, + "mrr_at_20": 0.441955, + "mrr_at_100": 0.444351, + "mrr_at_1000": 0.44487, + "nauc_ndcg_at_1_max": 0.462087, + "nauc_ndcg_at_1_std": -0.058591, + "nauc_ndcg_at_1_diff1": 0.553115, + "nauc_ndcg_at_3_max": 0.362859, + "nauc_ndcg_at_3_std": -0.075447, + "nauc_ndcg_at_3_diff1": 0.459242, + "nauc_ndcg_at_5_max": 0.331736, + "nauc_ndcg_at_5_std": -0.060149, + "nauc_ndcg_at_5_diff1": 0.419127, + "nauc_ndcg_at_10_max": 0.340331, + "nauc_ndcg_at_10_std": -0.055166, + "nauc_ndcg_at_10_diff1": 0.411033, + "nauc_ndcg_at_20_max": 0.323772, + "nauc_ndcg_at_20_std": -0.05667, + "nauc_ndcg_at_20_diff1": 0.392792, + "nauc_ndcg_at_100_max": 0.354394, + "nauc_ndcg_at_100_std": -0.024171, + "nauc_ndcg_at_100_diff1": 0.40454, + "nauc_ndcg_at_1000_max": 0.362906, + "nauc_ndcg_at_1000_std": -0.032596, + "nauc_ndcg_at_1000_diff1": 0.416891, + "nauc_map_at_1_max": 0.243915, + "nauc_map_at_1_std": -0.103499, + "nauc_map_at_1_diff1": 0.455141, + "nauc_map_at_3_max": 0.300534, + "nauc_map_at_3_std": -0.087386, + "nauc_map_at_3_diff1": 0.440061, + "nauc_map_at_5_max": 0.301072, + "nauc_map_at_5_std": -0.070596, + "nauc_map_at_5_diff1": 0.415587, + "nauc_map_at_10_max": 0.309608, + "nauc_map_at_10_std": -0.069379, + "nauc_map_at_10_diff1": 0.409485, + "nauc_map_at_20_max": 0.30672, + "nauc_map_at_20_std": -0.069665, + "nauc_map_at_20_diff1": 0.405721, + "nauc_map_at_100_max": 0.313704, + "nauc_map_at_100_std": -0.062977, + "nauc_map_at_100_diff1": 0.40602, + "nauc_map_at_1000_max": 0.31421, + "nauc_map_at_1000_std": -0.063073, + "nauc_map_at_1000_diff1": 0.406674, + "nauc_recall_at_1_max": 0.243915, + "nauc_recall_at_1_std": -0.103499, + "nauc_recall_at_1_diff1": 0.455141, + "nauc_recall_at_3_max": 0.283, + "nauc_recall_at_3_std": -0.100133, + "nauc_recall_at_3_diff1": 0.407163, + "nauc_recall_at_5_max": 0.24747, + "nauc_recall_at_5_std": -0.053462, + "nauc_recall_at_5_diff1": 0.315804, + "nauc_recall_at_10_max": 0.24175, + "nauc_recall_at_10_std": -0.047919, + "nauc_recall_at_10_diff1": 0.291085, + "nauc_recall_at_20_max": 0.157672, + "nauc_recall_at_20_std": -0.052823, + "nauc_recall_at_20_diff1": 0.201182, + "nauc_recall_at_100_max": 0.248593, + "nauc_recall_at_100_std": 0.104705, + "nauc_recall_at_100_diff1": 0.231883, + "nauc_recall_at_1000_max": 0.301373, + "nauc_recall_at_1000_std": 0.116107, + "nauc_recall_at_1000_diff1": 0.28084, + "nauc_precision_at_1_max": 0.462087, + "nauc_precision_at_1_std": -0.058591, + "nauc_precision_at_1_diff1": 0.553115, + "nauc_precision_at_3_max": 0.518021, + "nauc_precision_at_3_std": -0.008131, + "nauc_precision_at_3_diff1": 0.422758, + "nauc_precision_at_5_max": 0.459053, + "nauc_precision_at_5_std": 0.05161, + "nauc_precision_at_5_diff1": 0.304043, + "nauc_precision_at_10_max": 0.41778, + "nauc_precision_at_10_std": 0.0781, + "nauc_precision_at_10_diff1": 0.2028, + "nauc_precision_at_20_max": 0.358918, + "nauc_precision_at_20_std": 0.087241, + "nauc_precision_at_20_diff1": 0.13394, + "nauc_precision_at_100_max": 0.379318, + "nauc_precision_at_100_std": 0.206932, + "nauc_precision_at_100_diff1": 0.071652, + "nauc_precision_at_1000_max": 0.30767, + "nauc_precision_at_1000_std": 0.157627, + "nauc_precision_at_1000_diff1": 0.022853, + "nauc_mrr_at_1_max": 0.462087, + "nauc_mrr_at_1_std": -0.058591, + "nauc_mrr_at_1_diff1": 0.553115, + "nauc_mrr_at_3_max": 0.466156, + "nauc_mrr_at_3_std": -0.068377, + "nauc_mrr_at_3_diff1": 0.542474, + "nauc_mrr_at_5_max": 0.457568, + "nauc_mrr_at_5_std": -0.058152, + "nauc_mrr_at_5_diff1": 0.528393, + "nauc_mrr_at_10_max": 0.457632, + "nauc_mrr_at_10_std": -0.055663, + "nauc_mrr_at_10_diff1": 0.52648, + "nauc_mrr_at_20_max": 0.451442, + "nauc_mrr_at_20_std": -0.057369, + "nauc_mrr_at_20_diff1": 0.520308, + "nauc_mrr_at_100_max": 0.452592, + "nauc_mrr_at_100_std": -0.055404, + "nauc_mrr_at_100_diff1": 0.521576, + "nauc_mrr_at_1000_max": 0.452715, + "nauc_mrr_at_1000_std": -0.055809, + "nauc_mrr_at_1000_diff1": 0.521928, + "main_score": 0.3721, + "hf_subset": "PMC-Treatment", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.21053, + "ndcg_at_3": 0.21441, + "ndcg_at_5": 0.24365, + "ndcg_at_10": 0.27713, + "ndcg_at_20": 0.30673, + "ndcg_at_100": 0.35536, + "ndcg_at_1000": 0.39237, + "map_at_1": 0.12354, + "map_at_3": 0.17714, + "map_at_5": 0.19557, + "map_at_10": 0.21173, + "map_at_20": 0.22145, + "map_at_100": 0.22915, + "map_at_1000": 0.23115, + "recall_at_1": 0.12354, + "recall_at_3": 0.22076, + "recall_at_5": 0.28216, + "recall_at_10": 0.36696, + "recall_at_20": 0.4598, + "recall_at_100": 0.68202, + "recall_at_1000": 0.91374, + "precision_at_1": 0.21053, + "precision_at_3": 0.14327, + "precision_at_5": 0.11404, + "precision_at_10": 0.07456, + "precision_at_20": 0.04825, + "precision_at_100": 0.01447, + "precision_at_1000": 0.00198, + "mrr_at_1": 0.210526, + "mrr_at_3": 0.270468, + "mrr_at_5": 0.290205, + "mrr_at_10": 0.303481, + "mrr_at_20": 0.30958, + "mrr_at_100": 0.31393, + "mrr_at_1000": 0.31458, + "nauc_ndcg_at_1_max": 0.06205, + "nauc_ndcg_at_1_std": -0.300173, + "nauc_ndcg_at_1_diff1": 0.187159, + "nauc_ndcg_at_3_max": 0.100445, + "nauc_ndcg_at_3_std": -0.224004, + "nauc_ndcg_at_3_diff1": 0.094648, + "nauc_ndcg_at_5_max": 0.069647, + "nauc_ndcg_at_5_std": -0.228331, + "nauc_ndcg_at_5_diff1": 0.111207, + "nauc_ndcg_at_10_max": 0.057425, + "nauc_ndcg_at_10_std": -0.211651, + "nauc_ndcg_at_10_diff1": 0.082799, + "nauc_ndcg_at_20_max": 0.083657, + "nauc_ndcg_at_20_std": -0.174409, + "nauc_ndcg_at_20_diff1": 0.135936, + "nauc_ndcg_at_100_max": 0.060398, + "nauc_ndcg_at_100_std": -0.176796, + "nauc_ndcg_at_100_diff1": 0.112981, + "nauc_ndcg_at_1000_max": 0.062429, + "nauc_ndcg_at_1000_std": -0.184232, + "nauc_ndcg_at_1000_diff1": 0.110053, + "nauc_map_at_1_max": 0.058537, + "nauc_map_at_1_std": -0.252609, + "nauc_map_at_1_diff1": 0.109044, + "nauc_map_at_3_max": 0.080208, + "nauc_map_at_3_std": -0.22752, + "nauc_map_at_3_diff1": 0.084062, + "nauc_map_at_5_max": 0.056702, + "nauc_map_at_5_std": -0.236893, + "nauc_map_at_5_diff1": 0.087929, + "nauc_map_at_10_max": 0.059453, + "nauc_map_at_10_std": -0.225233, + "nauc_map_at_10_diff1": 0.075595, + "nauc_map_at_20_max": 0.069948, + "nauc_map_at_20_std": -0.213899, + "nauc_map_at_20_diff1": 0.097154, + "nauc_map_at_100_max": 0.063914, + "nauc_map_at_100_std": -0.214129, + "nauc_map_at_100_diff1": 0.09664, + "nauc_map_at_1000_max": 0.063756, + "nauc_map_at_1000_std": -0.213623, + "nauc_map_at_1000_diff1": 0.096281, + "nauc_recall_at_1_max": 0.058537, + "nauc_recall_at_1_std": -0.252609, + "nauc_recall_at_1_diff1": 0.109044, + "nauc_recall_at_3_max": 0.121252, + "nauc_recall_at_3_std": -0.189181, + "nauc_recall_at_3_diff1": 0.080646, + "nauc_recall_at_5_max": 0.052289, + "nauc_recall_at_5_std": -0.202766, + "nauc_recall_at_5_diff1": 0.097766, + "nauc_recall_at_10_max": 0.013126, + "nauc_recall_at_10_std": -0.167949, + "nauc_recall_at_10_diff1": 0.025885, + "nauc_recall_at_20_max": 0.072369, + "nauc_recall_at_20_std": -0.067354, + "nauc_recall_at_20_diff1": 0.16117, + "nauc_recall_at_100_max": -0.009708, + "nauc_recall_at_100_std": -0.032261, + "nauc_recall_at_100_diff1": 0.049489, + "nauc_recall_at_1000_max": -0.059738, + "nauc_recall_at_1000_std": 0.048082, + "nauc_recall_at_1000_diff1": -0.046044, + "nauc_precision_at_1_max": 0.06205, + "nauc_precision_at_1_std": -0.300173, + "nauc_precision_at_1_diff1": 0.187159, + "nauc_precision_at_3_max": 0.110959, + "nauc_precision_at_3_std": -0.195524, + "nauc_precision_at_3_diff1": 0.075343, + "nauc_precision_at_5_max": 0.049187, + "nauc_precision_at_5_std": -0.173214, + "nauc_precision_at_5_diff1": 0.109662, + "nauc_precision_at_10_max": 0.035875, + "nauc_precision_at_10_std": -0.11329, + "nauc_precision_at_10_diff1": 0.05697, + "nauc_precision_at_20_max": 0.107864, + "nauc_precision_at_20_std": 0.016664, + "nauc_precision_at_20_diff1": 0.170879, + "nauc_precision_at_100_max": 0.020722, + "nauc_precision_at_100_std": 0.020062, + "nauc_precision_at_100_diff1": 0.051719, + "nauc_precision_at_1000_max": -0.043078, + "nauc_precision_at_1000_std": 0.013043, + "nauc_precision_at_1000_diff1": -0.042963, + "nauc_mrr_at_1_max": 0.06205, + "nauc_mrr_at_1_std": -0.300173, + "nauc_mrr_at_1_diff1": 0.187159, + "nauc_mrr_at_3_max": 0.104897, + "nauc_mrr_at_3_std": -0.252274, + "nauc_mrr_at_3_diff1": 0.144408, + "nauc_mrr_at_5_max": 0.100671, + "nauc_mrr_at_5_std": -0.236368, + "nauc_mrr_at_5_diff1": 0.159988, + "nauc_mrr_at_10_max": 0.083691, + "nauc_mrr_at_10_std": -0.233923, + "nauc_mrr_at_10_diff1": 0.143348, + "nauc_mrr_at_20_max": 0.08583, + "nauc_mrr_at_20_std": -0.227212, + "nauc_mrr_at_20_diff1": 0.154818, + "nauc_mrr_at_100_max": 0.082962, + "nauc_mrr_at_100_std": -0.229776, + "nauc_mrr_at_100_diff1": 0.152648, + "nauc_mrr_at_1000_max": 0.083877, + "nauc_mrr_at_1000_std": -0.229698, + "nauc_mrr_at_1000_diff1": 0.152781, + "main_score": 0.27713, + "hf_subset": "PMC-Clinical", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.2093, + "ndcg_at_3": 0.19327, + "ndcg_at_5": 0.18505, + "ndcg_at_10": 0.22728, + "ndcg_at_20": 0.28444, + "ndcg_at_100": 0.38785, + "ndcg_at_1000": 0.41975, + "map_at_1": 0.06731, + "map_at_3": 0.1104, + "map_at_5": 0.12111, + "map_at_10": 0.14425, + "map_at_20": 0.16438, + "map_at_100": 0.18846, + "map_at_1000": 0.19127, + "recall_at_1": 0.06731, + "recall_at_3": 0.14948, + "recall_at_5": 0.17636, + "recall_at_10": 0.27545, + "recall_at_20": 0.42972, + "recall_at_100": 0.81305, + "recall_at_1000": 0.97752, + "precision_at_1": 0.2093, + "precision_at_3": 0.17054, + "precision_at_5": 0.12403, + "precision_at_10": 0.0969, + "precision_at_20": 0.07636, + "precision_at_100": 0.0286, + "precision_at_1000": 0.00348, + "mrr_at_1": 0.209302, + "mrr_at_3": 0.303618, + "mrr_at_5": 0.31447, + "mrr_at_10": 0.330063, + "mrr_at_20": 0.342944, + "mrr_at_100": 0.348457, + "mrr_at_1000": 0.348704, + "nauc_ndcg_at_1_max": -0.001591, + "nauc_ndcg_at_1_std": 0.11029, + "nauc_ndcg_at_1_diff1": 0.177096, + "nauc_ndcg_at_3_max": 0.023289, + "nauc_ndcg_at_3_std": 0.115702, + "nauc_ndcg_at_3_diff1": 0.09384, + "nauc_ndcg_at_5_max": 0.016737, + "nauc_ndcg_at_5_std": 0.081483, + "nauc_ndcg_at_5_diff1": 0.075906, + "nauc_ndcg_at_10_max": 0.020073, + "nauc_ndcg_at_10_std": 0.103714, + "nauc_ndcg_at_10_diff1": 0.07431, + "nauc_ndcg_at_20_max": 0.005227, + "nauc_ndcg_at_20_std": 0.11447, + "nauc_ndcg_at_20_diff1": 0.040248, + "nauc_ndcg_at_100_max": 0.075271, + "nauc_ndcg_at_100_std": 0.218871, + "nauc_ndcg_at_100_diff1": 0.082171, + "nauc_ndcg_at_1000_max": 0.059453, + "nauc_ndcg_at_1000_std": 0.204838, + "nauc_ndcg_at_1000_diff1": 0.078701, + "nauc_map_at_1_max": -0.052531, + "nauc_map_at_1_std": 0.039122, + "nauc_map_at_1_diff1": 0.16151, + "nauc_map_at_3_max": -0.003154, + "nauc_map_at_3_std": 0.065016, + "nauc_map_at_3_diff1": 0.123244, + "nauc_map_at_5_max": -0.001352, + "nauc_map_at_5_std": 0.069043, + "nauc_map_at_5_diff1": 0.084998, + "nauc_map_at_10_max": 0.008072, + "nauc_map_at_10_std": 0.095847, + "nauc_map_at_10_diff1": 0.075477, + "nauc_map_at_20_max": -0.004564, + "nauc_map_at_20_std": 0.094854, + "nauc_map_at_20_diff1": 0.062011, + "nauc_map_at_100_max": 0.022787, + "nauc_map_at_100_std": 0.131801, + "nauc_map_at_100_diff1": 0.074117, + "nauc_map_at_1000_max": 0.022314, + "nauc_map_at_1000_std": 0.133221, + "nauc_map_at_1000_diff1": 0.073723, + "nauc_recall_at_1_max": -0.052531, + "nauc_recall_at_1_std": 0.039122, + "nauc_recall_at_1_diff1": 0.16151, + "nauc_recall_at_3_max": -0.006839, + "nauc_recall_at_3_std": 0.049781, + "nauc_recall_at_3_diff1": 0.096894, + "nauc_recall_at_5_max": 0.001175, + "nauc_recall_at_5_std": 0.032126, + "nauc_recall_at_5_diff1": 0.027442, + "nauc_recall_at_10_max": -0.009546, + "nauc_recall_at_10_std": 0.053054, + "nauc_recall_at_10_diff1": 0.022116, + "nauc_recall_at_20_max": -0.065637, + "nauc_recall_at_20_std": 0.035795, + "nauc_recall_at_20_diff1": -0.076963, + "nauc_recall_at_100_max": 0.123297, + "nauc_recall_at_100_std": 0.326726, + "nauc_recall_at_100_diff1": -0.023672, + "nauc_recall_at_1000_max": -0.163987, + "nauc_recall_at_1000_std": 0.653637, + "nauc_recall_at_1000_diff1": -0.538168, + "nauc_precision_at_1_max": -0.001591, + "nauc_precision_at_1_std": 0.11029, + "nauc_precision_at_1_diff1": 0.177096, + "nauc_precision_at_3_max": 0.08703, + "nauc_precision_at_3_std": 0.192515, + "nauc_precision_at_3_diff1": 0.075138, + "nauc_precision_at_5_max": 0.08183, + "nauc_precision_at_5_std": 0.164281, + "nauc_precision_at_5_diff1": -0.013521, + "nauc_precision_at_10_max": 0.062962, + "nauc_precision_at_10_std": 0.192781, + "nauc_precision_at_10_diff1": -0.030476, + "nauc_precision_at_20_max": 0.070682, + "nauc_precision_at_20_std": 0.230022, + "nauc_precision_at_20_diff1": -0.080162, + "nauc_precision_at_100_max": 0.183724, + "nauc_precision_at_100_std": 0.430007, + "nauc_precision_at_100_diff1": -0.019484, + "nauc_precision_at_1000_max": 0.14828, + "nauc_precision_at_1000_std": 0.338986, + "nauc_precision_at_1000_diff1": -0.025408, + "nauc_mrr_at_1_max": -0.001591, + "nauc_mrr_at_1_std": 0.11029, + "nauc_mrr_at_1_diff1": 0.177096, + "nauc_mrr_at_3_max": 0.042019, + "nauc_mrr_at_3_std": 0.115765, + "nauc_mrr_at_3_diff1": 0.151171, + "nauc_mrr_at_5_max": 0.049666, + "nauc_mrr_at_5_std": 0.10502, + "nauc_mrr_at_5_diff1": 0.139102, + "nauc_mrr_at_10_max": 0.044554, + "nauc_mrr_at_10_std": 0.115673, + "nauc_mrr_at_10_diff1": 0.14157, + "nauc_mrr_at_20_max": 0.046167, + "nauc_mrr_at_20_std": 0.125355, + "nauc_mrr_at_20_diff1": 0.140926, + "nauc_mrr_at_100_max": 0.046726, + "nauc_mrr_at_100_std": 0.122835, + "nauc_mrr_at_100_diff1": 0.143458, + "nauc_mrr_at_1000_max": 0.046021, + "nauc_mrr_at_1000_std": 0.122362, + "nauc_mrr_at_1000_diff1": 0.143157, + "main_score": 0.22728, + "hf_subset": "IIYi-Clinical", + "languages": [ + "eng-Latn" + ] + } + ] + }, + "evaluation_time": 3329.852794647217, + "kg_co2_emissions": null +} \ No newline at end of file diff --git a/results/NovaSearch__stella_en_1.5B_v5/d03be74b361d4eb24f42a2fe5bd2e29917df4604/R2MEDRetrieval.json b/results/NovaSearch__stella_en_1.5B_v5/d03be74b361d4eb24f42a2fe5bd2e29917df4604/R2MEDRetrieval.json new file mode 100644 index 0000000000..38c137a116 --- /dev/null +++ b/results/NovaSearch__stella_en_1.5B_v5/d03be74b361d4eb24f42a2fe5bd2e29917df4604/R2MEDRetrieval.json @@ -0,0 +1,1187 @@ +{ + "dataset_revision": "1.0", + "task_name": "R2MEDRetrieval", + "mteb_version": "1.38.20", + "scores": { + "test": [ + { + "ndcg_at_1": 0.18447, + "ndcg_at_3": 0.17276, + "ndcg_at_5": 0.16943, + "ndcg_at_10": 0.18599, + "ndcg_at_20": 0.21395, + "ndcg_at_100": 0.28546, + "ndcg_at_1000": 0.34716, + "map_at_1": 0.04779, + "map_at_3": 0.09478, + "map_at_5": 0.10693, + "map_at_10": 0.12433, + "map_at_20": 0.13729, + "map_at_100": 0.15276, + "map_at_1000": 0.15652, + "recall_at_1": 0.04779, + "recall_at_3": 0.12693, + "recall_at_5": 0.1604, + "recall_at_10": 0.21469, + "recall_at_20": 0.28817, + "recall_at_100": 0.55607, + "recall_at_1000": 0.89995, + "precision_at_1": 0.18447, + "precision_at_3": 0.14887, + "precision_at_5": 0.11456, + "precision_at_10": 0.0835, + "precision_at_20": 0.05825, + "precision_at_100": 0.02136, + "precision_at_1000": 0.00331, + "mrr_at_1": 0.174757, + "mrr_at_3": 0.242718, + "mrr_at_5": 0.251456, + "mrr_at_10": 0.2591, + "mrr_at_20": 0.263918, + "mrr_at_100": 0.270654, + "mrr_at_1000": 0.271375, + "nauc_ndcg_at_1_max": -0.081069, + "nauc_ndcg_at_1_std": -0.217218, + "nauc_ndcg_at_1_diff1": 0.225065, + "nauc_ndcg_at_3_max": -0.020895, + "nauc_ndcg_at_3_std": -0.168299, + "nauc_ndcg_at_3_diff1": 0.219173, + "nauc_ndcg_at_5_max": 0.017403, + "nauc_ndcg_at_5_std": -0.174037, + "nauc_ndcg_at_5_diff1": 0.179129, + "nauc_ndcg_at_10_max": -0.004423, + "nauc_ndcg_at_10_std": -0.179548, + "nauc_ndcg_at_10_diff1": 0.162328, + "nauc_ndcg_at_20_max": -0.034625, + "nauc_ndcg_at_20_std": -0.209747, + "nauc_ndcg_at_20_diff1": 0.154441, + "nauc_ndcg_at_100_max": -0.080637, + "nauc_ndcg_at_100_std": -0.210203, + "nauc_ndcg_at_100_diff1": 0.142032, + "nauc_ndcg_at_1000_max": -0.059513, + "nauc_ndcg_at_1000_std": -0.18498, + "nauc_ndcg_at_1000_diff1": 0.148497, + "nauc_map_at_1_max": -0.095008, + "nauc_map_at_1_std": -0.255374, + "nauc_map_at_1_diff1": 0.170662, + "nauc_map_at_3_max": 0.044233, + "nauc_map_at_3_std": -0.159531, + "nauc_map_at_3_diff1": 0.188541, + "nauc_map_at_5_max": 0.061147, + "nauc_map_at_5_std": -0.157998, + "nauc_map_at_5_diff1": 0.180377, + "nauc_map_at_10_max": 0.030115, + "nauc_map_at_10_std": -0.166229, + "nauc_map_at_10_diff1": 0.195491, + "nauc_map_at_20_max": 0.007523, + "nauc_map_at_20_std": -0.181175, + "nauc_map_at_20_diff1": 0.192813, + "nauc_map_at_100_max": -0.015614, + "nauc_map_at_100_std": -0.184984, + "nauc_map_at_100_diff1": 0.189531, + "nauc_map_at_1000_max": -0.015293, + "nauc_map_at_1000_std": -0.183974, + "nauc_map_at_1000_diff1": 0.188996, + "nauc_recall_at_1_max": -0.095008, + "nauc_recall_at_1_std": -0.255374, + "nauc_recall_at_1_diff1": 0.170662, + "nauc_recall_at_3_max": 0.100026, + "nauc_recall_at_3_std": -0.117206, + "nauc_recall_at_3_diff1": 0.142257, + "nauc_recall_at_5_max": 0.133197, + "nauc_recall_at_5_std": -0.111388, + "nauc_recall_at_5_diff1": 0.087382, + "nauc_recall_at_10_max": 0.040296, + "nauc_recall_at_10_std": -0.152819, + "nauc_recall_at_10_diff1": 0.111508, + "nauc_recall_at_20_max": -0.033354, + "nauc_recall_at_20_std": -0.220073, + "nauc_recall_at_20_diff1": 0.096852, + "nauc_recall_at_100_max": -0.136495, + "nauc_recall_at_100_std": -0.195014, + "nauc_recall_at_100_diff1": 0.056187, + "nauc_recall_at_1000_max": -0.001274, + "nauc_recall_at_1000_std": 0.16386, + "nauc_recall_at_1000_diff1": -0.029702, + "nauc_precision_at_1_max": -0.081069, + "nauc_precision_at_1_std": -0.217218, + "nauc_precision_at_1_diff1": 0.225065, + "nauc_precision_at_3_max": -0.074733, + "nauc_precision_at_3_std": -0.179417, + "nauc_precision_at_3_diff1": 0.19357, + "nauc_precision_at_5_max": -0.035862, + "nauc_precision_at_5_std": -0.16613, + "nauc_precision_at_5_diff1": 0.151411, + "nauc_precision_at_10_max": -0.108032, + "nauc_precision_at_10_std": -0.186391, + "nauc_precision_at_10_diff1": 0.176531, + "nauc_precision_at_20_max": -0.156436, + "nauc_precision_at_20_std": -0.22962, + "nauc_precision_at_20_diff1": 0.17644, + "nauc_precision_at_100_max": -0.214272, + "nauc_precision_at_100_std": -0.191182, + "nauc_precision_at_100_diff1": 0.134182, + "nauc_precision_at_1000_max": -0.174144, + "nauc_precision_at_1000_std": -0.131475, + "nauc_precision_at_1000_diff1": 0.145744, + "nauc_mrr_at_1_max": -0.091119, + "nauc_mrr_at_1_std": -0.21309, + "nauc_mrr_at_1_diff1": 0.272274, + "nauc_mrr_at_3_max": -0.047417, + "nauc_mrr_at_3_std": -0.190468, + "nauc_mrr_at_3_diff1": 0.17257, + "nauc_mrr_at_5_max": -0.044797, + "nauc_mrr_at_5_std": -0.186239, + "nauc_mrr_at_5_diff1": 0.155272, + "nauc_mrr_at_10_max": -0.059949, + "nauc_mrr_at_10_std": -0.19832, + "nauc_mrr_at_10_diff1": 0.15577, + "nauc_mrr_at_20_max": -0.059532, + "nauc_mrr_at_20_std": -0.201866, + "nauc_mrr_at_20_diff1": 0.156924, + "nauc_mrr_at_100_max": -0.063668, + "nauc_mrr_at_100_std": -0.205243, + "nauc_mrr_at_100_diff1": 0.157166, + "nauc_mrr_at_1000_max": -0.062871, + "nauc_mrr_at_1000_std": -0.204127, + "nauc_mrr_at_1000_diff1": 0.158176, + "main_score": 0.18599, + "hf_subset": "Biology", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.28571, + "ndcg_at_3": 0.31792, + "ndcg_at_5": 0.34349, + "ndcg_at_10": 0.38448, + "ndcg_at_20": 0.42404, + "ndcg_at_100": 0.48101, + "ndcg_at_1000": 0.50411, + "map_at_1": 0.11843, + "map_at_3": 0.22901, + "map_at_5": 0.2644, + "map_at_10": 0.29022, + "map_at_20": 0.30563, + "map_at_100": 0.32039, + "map_at_1000": 0.32191, + "recall_at_1": 0.11843, + "recall_at_3": 0.30795, + "recall_at_5": 0.39606, + "recall_at_10": 0.51534, + "recall_at_20": 0.62517, + "recall_at_100": 0.83975, + "recall_at_1000": 0.97897, + "precision_at_1": 0.28571, + "precision_at_3": 0.22944, + "precision_at_5": 0.18961, + "precision_at_10": 0.12857, + "precision_at_20": 0.08377, + "precision_at_100": 0.02468, + "precision_at_1000": 0.0029, + "mrr_at_1": 0.285714, + "mrr_at_3": 0.383117, + "mrr_at_5": 0.402597, + "mrr_at_10": 0.423928, + "mrr_at_20": 0.428819, + "mrr_at_100": 0.431417, + "mrr_at_1000": 0.431783, + "nauc_ndcg_at_1_max": -0.025712, + "nauc_ndcg_at_1_std": 0.05141, + "nauc_ndcg_at_1_diff1": 0.00884, + "nauc_ndcg_at_3_max": 0.049018, + "nauc_ndcg_at_3_std": 0.067172, + "nauc_ndcg_at_3_diff1": 0.099977, + "nauc_ndcg_at_5_max": 0.087989, + "nauc_ndcg_at_5_std": 0.009466, + "nauc_ndcg_at_5_diff1": 0.059788, + "nauc_ndcg_at_10_max": 0.148667, + "nauc_ndcg_at_10_std": 0.07713, + "nauc_ndcg_at_10_diff1": 0.034093, + "nauc_ndcg_at_20_max": 0.132362, + "nauc_ndcg_at_20_std": 0.063676, + "nauc_ndcg_at_20_diff1": 0.01425, + "nauc_ndcg_at_100_max": 0.120738, + "nauc_ndcg_at_100_std": 0.064494, + "nauc_ndcg_at_100_diff1": -0.022034, + "nauc_ndcg_at_1000_max": 0.098101, + "nauc_ndcg_at_1000_std": 0.064535, + "nauc_ndcg_at_1000_diff1": 0.002119, + "nauc_map_at_1_max": 0.149792, + "nauc_map_at_1_std": 0.17982, + "nauc_map_at_1_diff1": 0.186142, + "nauc_map_at_3_max": 0.110231, + "nauc_map_at_3_std": 0.067167, + "nauc_map_at_3_diff1": 0.185831, + "nauc_map_at_5_max": 0.132038, + "nauc_map_at_5_std": 0.034163, + "nauc_map_at_5_diff1": 0.135171, + "nauc_map_at_10_max": 0.154725, + "nauc_map_at_10_std": 0.068425, + "nauc_map_at_10_diff1": 0.108069, + "nauc_map_at_20_max": 0.151331, + "nauc_map_at_20_std": 0.065056, + "nauc_map_at_20_diff1": 0.100131, + "nauc_map_at_100_max": 0.144224, + "nauc_map_at_100_std": 0.063242, + "nauc_map_at_100_diff1": 0.085183, + "nauc_map_at_1000_max": 0.142274, + "nauc_map_at_1000_std": 0.063355, + "nauc_map_at_1000_diff1": 0.086175, + "nauc_recall_at_1_max": 0.149792, + "nauc_recall_at_1_std": 0.17982, + "nauc_recall_at_1_diff1": 0.186142, + "nauc_recall_at_3_max": 0.095852, + "nauc_recall_at_3_std": 0.020405, + "nauc_recall_at_3_diff1": 0.165108, + "nauc_recall_at_5_max": 0.11741, + "nauc_recall_at_5_std": -0.071855, + "nauc_recall_at_5_diff1": 0.06459, + "nauc_recall_at_10_max": 0.210248, + "nauc_recall_at_10_std": 0.075806, + "nauc_recall_at_10_diff1": 0.017596, + "nauc_recall_at_20_max": 0.173332, + "nauc_recall_at_20_std": 0.041933, + "nauc_recall_at_20_diff1": -0.044448, + "nauc_recall_at_100_max": 0.210273, + "nauc_recall_at_100_std": 0.04109, + "nauc_recall_at_100_diff1": -0.169385, + "nauc_recall_at_1000_max": -0.875785, + "nauc_recall_at_1000_std": -0.477944, + "nauc_recall_at_1000_diff1": 0.151543, + "nauc_precision_at_1_max": -0.025712, + "nauc_precision_at_1_std": 0.05141, + "nauc_precision_at_1_diff1": 0.00884, + "nauc_precision_at_3_max": 0.018724, + "nauc_precision_at_3_std": 0.055226, + "nauc_precision_at_3_diff1": 0.01309, + "nauc_precision_at_5_max": 0.069945, + "nauc_precision_at_5_std": -0.000795, + "nauc_precision_at_5_diff1": -0.100171, + "nauc_precision_at_10_max": 0.117567, + "nauc_precision_at_10_std": 0.098476, + "nauc_precision_at_10_diff1": -0.214868, + "nauc_precision_at_20_max": 0.038413, + "nauc_precision_at_20_std": 0.039037, + "nauc_precision_at_20_diff1": -0.225225, + "nauc_precision_at_100_max": -0.037512, + "nauc_precision_at_100_std": 0.028903, + "nauc_precision_at_100_diff1": -0.285755, + "nauc_precision_at_1000_max": -0.072831, + "nauc_precision_at_1000_std": 0.040619, + "nauc_precision_at_1000_diff1": -0.182629, + "nauc_mrr_at_1_max": -0.025712, + "nauc_mrr_at_1_std": 0.05141, + "nauc_mrr_at_1_diff1": 0.00884, + "nauc_mrr_at_3_max": 0.004882, + "nauc_mrr_at_3_std": 0.065236, + "nauc_mrr_at_3_diff1": -0.019405, + "nauc_mrr_at_5_max": -0.009354, + "nauc_mrr_at_5_std": 0.028882, + "nauc_mrr_at_5_diff1": -0.044365, + "nauc_mrr_at_10_max": 0.010489, + "nauc_mrr_at_10_std": 0.060093, + "nauc_mrr_at_10_diff1": -0.057845, + "nauc_mrr_at_20_max": 0.002517, + "nauc_mrr_at_20_std": 0.053648, + "nauc_mrr_at_20_diff1": -0.055665, + "nauc_mrr_at_100_max": 0.003128, + "nauc_mrr_at_100_std": 0.052986, + "nauc_mrr_at_100_diff1": -0.05213, + "nauc_mrr_at_1000_max": 0.003623, + "nauc_mrr_at_1000_std": 0.053538, + "nauc_mrr_at_1000_diff1": -0.051149, + "main_score": 0.38448, + "hf_subset": "Bioinformatics", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.25, + "ndcg_at_3": 0.35093, + "ndcg_at_5": 0.37799, + "ndcg_at_10": 0.42808, + "ndcg_at_20": 0.47024, + "ndcg_at_100": 0.51917, + "ndcg_at_1000": 0.53918, + "map_at_1": 0.16062, + "map_at_3": 0.27414, + "map_at_5": 0.305, + "map_at_10": 0.33642, + "map_at_20": 0.35472, + "map_at_100": 0.36644, + "map_at_1000": 0.3679, + "recall_at_1": 0.16062, + "recall_at_3": 0.37325, + "recall_at_5": 0.45284, + "recall_at_10": 0.57867, + "recall_at_20": 0.69364, + "recall_at_100": 0.87201, + "recall_at_1000": 0.98258, + "precision_at_1": 0.25, + "precision_at_3": 0.23864, + "precision_at_5": 0.18409, + "precision_at_10": 0.12955, + "precision_at_20": 0.08466, + "precision_at_100": 0.02364, + "precision_at_1000": 0.00274, + "mrr_at_1": 0.25, + "mrr_at_3": 0.388258, + "mrr_at_5": 0.407008, + "mrr_at_10": 0.428414, + "mrr_at_20": 0.434188, + "mrr_at_100": 0.436815, + "mrr_at_1000": 0.437042, + "nauc_ndcg_at_1_max": 0.292084, + "nauc_ndcg_at_1_std": -0.049031, + "nauc_ndcg_at_1_diff1": 0.097923, + "nauc_ndcg_at_3_max": 0.239566, + "nauc_ndcg_at_3_std": -0.118168, + "nauc_ndcg_at_3_diff1": 0.142488, + "nauc_ndcg_at_5_max": 0.223803, + "nauc_ndcg_at_5_std": -0.110733, + "nauc_ndcg_at_5_diff1": 0.132936, + "nauc_ndcg_at_10_max": 0.258792, + "nauc_ndcg_at_10_std": -0.123682, + "nauc_ndcg_at_10_diff1": 0.12676, + "nauc_ndcg_at_20_max": 0.252901, + "nauc_ndcg_at_20_std": -0.107867, + "nauc_ndcg_at_20_diff1": 0.108489, + "nauc_ndcg_at_100_max": 0.291657, + "nauc_ndcg_at_100_std": -0.058128, + "nauc_ndcg_at_100_diff1": 0.11197, + "nauc_ndcg_at_1000_max": 0.291183, + "nauc_ndcg_at_1000_std": -0.054647, + "nauc_ndcg_at_1000_diff1": 0.113491, + "nauc_map_at_1_max": 0.18448, + "nauc_map_at_1_std": -0.155478, + "nauc_map_at_1_diff1": 0.206764, + "nauc_map_at_3_max": 0.22998, + "nauc_map_at_3_std": -0.130373, + "nauc_map_at_3_diff1": 0.196299, + "nauc_map_at_5_max": 0.224383, + "nauc_map_at_5_std": -0.116512, + "nauc_map_at_5_diff1": 0.165486, + "nauc_map_at_10_max": 0.24647, + "nauc_map_at_10_std": -0.120468, + "nauc_map_at_10_diff1": 0.149527, + "nauc_map_at_20_max": 0.236613, + "nauc_map_at_20_std": -0.123809, + "nauc_map_at_20_diff1": 0.13331, + "nauc_map_at_100_max": 0.249506, + "nauc_map_at_100_std": -0.111262, + "nauc_map_at_100_diff1": 0.137395, + "nauc_map_at_1000_max": 0.249518, + "nauc_map_at_1000_std": -0.110319, + "nauc_map_at_1000_diff1": 0.137541, + "nauc_recall_at_1_max": 0.18448, + "nauc_recall_at_1_std": -0.155478, + "nauc_recall_at_1_diff1": 0.206764, + "nauc_recall_at_3_max": 0.187464, + "nauc_recall_at_3_std": -0.167041, + "nauc_recall_at_3_diff1": 0.209116, + "nauc_recall_at_5_max": 0.156252, + "nauc_recall_at_5_std": -0.151567, + "nauc_recall_at_5_diff1": 0.163525, + "nauc_recall_at_10_max": 0.242437, + "nauc_recall_at_10_std": -0.201344, + "nauc_recall_at_10_diff1": 0.163789, + "nauc_recall_at_20_max": 0.212433, + "nauc_recall_at_20_std": -0.176757, + "nauc_recall_at_20_diff1": 0.128343, + "nauc_recall_at_100_max": 0.330715, + "nauc_recall_at_100_std": 0.006746, + "nauc_recall_at_100_diff1": 0.153208, + "nauc_recall_at_1000_max": 0.613222, + "nauc_recall_at_1000_std": 0.148451, + "nauc_recall_at_1000_diff1": 0.656526, + "nauc_precision_at_1_max": 0.292084, + "nauc_precision_at_1_std": -0.049031, + "nauc_precision_at_1_diff1": 0.097923, + "nauc_precision_at_3_max": 0.26689, + "nauc_precision_at_3_std": 0.028689, + "nauc_precision_at_3_diff1": 0.002962, + "nauc_precision_at_5_max": 0.24493, + "nauc_precision_at_5_std": 0.080618, + "nauc_precision_at_5_diff1": -0.055731, + "nauc_precision_at_10_max": 0.202702, + "nauc_precision_at_10_std": 0.018914, + "nauc_precision_at_10_diff1": -0.144261, + "nauc_precision_at_20_max": 0.144229, + "nauc_precision_at_20_std": 0.084615, + "nauc_precision_at_20_diff1": -0.180562, + "nauc_precision_at_100_max": 0.198656, + "nauc_precision_at_100_std": 0.262296, + "nauc_precision_at_100_diff1": -0.138555, + "nauc_precision_at_1000_max": 0.147766, + "nauc_precision_at_1000_std": 0.27109, + "nauc_precision_at_1000_diff1": -0.126869, + "nauc_mrr_at_1_max": 0.292084, + "nauc_mrr_at_1_std": -0.049031, + "nauc_mrr_at_1_diff1": 0.097923, + "nauc_mrr_at_3_max": 0.289953, + "nauc_mrr_at_3_std": -0.048663, + "nauc_mrr_at_3_diff1": 0.063899, + "nauc_mrr_at_5_max": 0.285549, + "nauc_mrr_at_5_std": -0.045482, + "nauc_mrr_at_5_diff1": 0.071516, + "nauc_mrr_at_10_max": 0.291777, + "nauc_mrr_at_10_std": -0.048403, + "nauc_mrr_at_10_diff1": 0.07793, + "nauc_mrr_at_20_max": 0.29676, + "nauc_mrr_at_20_std": -0.039814, + "nauc_mrr_at_20_diff1": 0.077605, + "nauc_mrr_at_100_max": 0.295848, + "nauc_mrr_at_100_std": -0.039767, + "nauc_mrr_at_100_diff1": 0.076856, + "nauc_mrr_at_1000_max": 0.295607, + "nauc_mrr_at_1000_std": -0.040096, + "nauc_mrr_at_1000_diff1": 0.076816, + "main_score": 0.42808, + "hf_subset": "Medical-Sciences", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.04124, + "ndcg_at_3": 0.05292, + "ndcg_at_5": 0.06618, + "ndcg_at_10": 0.07993, + "ndcg_at_20": 0.09181, + "ndcg_at_100": 0.13787, + "ndcg_at_1000": 0.19231, + "map_at_1": 0.02612, + "map_at_3": 0.03631, + "map_at_5": 0.04468, + "map_at_10": 0.04989, + "map_at_20": 0.05322, + "map_at_100": 0.05977, + "map_at_1000": 0.06192, + "recall_at_1": 0.02612, + "recall_at_3": 0.04917, + "recall_at_5": 0.08344, + "recall_at_10": 0.11772, + "recall_at_20": 0.15673, + "recall_at_100": 0.35334, + "recall_at_1000": 0.68579, + "precision_at_1": 0.04124, + "precision_at_3": 0.04124, + "precision_at_5": 0.03918, + "precision_at_10": 0.0299, + "precision_at_20": 0.01959, + "precision_at_100": 0.00907, + "precision_at_1000": 0.0019, + "mrr_at_1": 0.041237, + "mrr_at_3": 0.072165, + "mrr_at_5": 0.086598, + "mrr_at_10": 0.096273, + "mrr_at_20": 0.098724, + "mrr_at_100": 0.10494, + "mrr_at_1000": 0.106319, + "nauc_ndcg_at_1_max": 0.41857, + "nauc_ndcg_at_1_std": 0.151858, + "nauc_ndcg_at_1_diff1": 0.752959, + "nauc_ndcg_at_3_max": 0.310433, + "nauc_ndcg_at_3_std": 0.136884, + "nauc_ndcg_at_3_diff1": 0.447181, + "nauc_ndcg_at_5_max": 0.26914, + "nauc_ndcg_at_5_std": 0.123383, + "nauc_ndcg_at_5_diff1": 0.312916, + "nauc_ndcg_at_10_max": 0.245111, + "nauc_ndcg_at_10_std": 0.125074, + "nauc_ndcg_at_10_diff1": 0.258124, + "nauc_ndcg_at_20_max": 0.23788, + "nauc_ndcg_at_20_std": 0.158396, + "nauc_ndcg_at_20_diff1": 0.222541, + "nauc_ndcg_at_100_max": 0.222347, + "nauc_ndcg_at_100_std": 0.175483, + "nauc_ndcg_at_100_diff1": 0.158052, + "nauc_ndcg_at_1000_max": 0.294623, + "nauc_ndcg_at_1000_std": 0.245208, + "nauc_ndcg_at_1000_diff1": 0.196681, + "nauc_map_at_1_max": 0.259877, + "nauc_map_at_1_std": -0.057015, + "nauc_map_at_1_diff1": 0.800634, + "nauc_map_at_3_max": 0.275821, + "nauc_map_at_3_std": 0.051397, + "nauc_map_at_3_diff1": 0.580298, + "nauc_map_at_5_max": 0.270247, + "nauc_map_at_5_std": 0.068087, + "nauc_map_at_5_diff1": 0.453436, + "nauc_map_at_10_max": 0.254952, + "nauc_map_at_10_std": 0.068762, + "nauc_map_at_10_diff1": 0.409129, + "nauc_map_at_20_max": 0.257612, + "nauc_map_at_20_std": 0.0911, + "nauc_map_at_20_diff1": 0.393464, + "nauc_map_at_100_max": 0.248067, + "nauc_map_at_100_std": 0.105044, + "nauc_map_at_100_diff1": 0.363811, + "nauc_map_at_1000_max": 0.253587, + "nauc_map_at_1000_std": 0.109506, + "nauc_map_at_1000_diff1": 0.366533, + "nauc_recall_at_1_max": 0.259877, + "nauc_recall_at_1_std": -0.057015, + "nauc_recall_at_1_diff1": 0.800634, + "nauc_recall_at_3_max": 0.245453, + "nauc_recall_at_3_std": 0.133629, + "nauc_recall_at_3_diff1": 0.405544, + "nauc_recall_at_5_max": 0.246326, + "nauc_recall_at_5_std": 0.126173, + "nauc_recall_at_5_diff1": 0.173581, + "nauc_recall_at_10_max": 0.186065, + "nauc_recall_at_10_std": 0.108986, + "nauc_recall_at_10_diff1": 0.081864, + "nauc_recall_at_20_max": 0.164744, + "nauc_recall_at_20_std": 0.162397, + "nauc_recall_at_20_diff1": 0.025202, + "nauc_recall_at_100_max": 0.147367, + "nauc_recall_at_100_std": 0.173154, + "nauc_recall_at_100_diff1": -0.055806, + "nauc_recall_at_1000_max": 0.422792, + "nauc_recall_at_1000_std": 0.430168, + "nauc_recall_at_1000_diff1": 0.033839, + "nauc_precision_at_1_max": 0.41857, + "nauc_precision_at_1_std": 0.151858, + "nauc_precision_at_1_diff1": 0.752959, + "nauc_precision_at_3_max": 0.31915, + "nauc_precision_at_3_std": 0.235882, + "nauc_precision_at_3_diff1": 0.250971, + "nauc_precision_at_5_max": 0.287627, + "nauc_precision_at_5_std": 0.257571, + "nauc_precision_at_5_diff1": 0.124606, + "nauc_precision_at_10_max": 0.234235, + "nauc_precision_at_10_std": 0.232169, + "nauc_precision_at_10_diff1": 0.077378, + "nauc_precision_at_20_max": 0.215662, + "nauc_precision_at_20_std": 0.266171, + "nauc_precision_at_20_diff1": 0.055727, + "nauc_precision_at_100_max": 0.155358, + "nauc_precision_at_100_std": 0.255291, + "nauc_precision_at_100_diff1": -0.058115, + "nauc_precision_at_1000_max": 0.131924, + "nauc_precision_at_1000_std": 0.286346, + "nauc_precision_at_1000_diff1": -0.016504, + "nauc_mrr_at_1_max": 0.41857, + "nauc_mrr_at_1_std": 0.151858, + "nauc_mrr_at_1_diff1": 0.752959, + "nauc_mrr_at_3_max": 0.337056, + "nauc_mrr_at_3_std": 0.144255, + "nauc_mrr_at_3_diff1": 0.402023, + "nauc_mrr_at_5_max": 0.305274, + "nauc_mrr_at_5_std": 0.154787, + "nauc_mrr_at_5_diff1": 0.335089, + "nauc_mrr_at_10_max": 0.290645, + "nauc_mrr_at_10_std": 0.159832, + "nauc_mrr_at_10_diff1": 0.304045, + "nauc_mrr_at_20_max": 0.28774, + "nauc_mrr_at_20_std": 0.162847, + "nauc_mrr_at_20_diff1": 0.293787, + "nauc_mrr_at_100_max": 0.288959, + "nauc_mrr_at_100_std": 0.158694, + "nauc_mrr_at_100_diff1": 0.293931, + "nauc_mrr_at_1000_max": 0.291737, + "nauc_mrr_at_1000_std": 0.160161, + "nauc_mrr_at_1000_diff1": 0.295042, + "main_score": 0.07993, + "hf_subset": "MedXpertQA-Exam", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.07627, + "ndcg_at_3": 0.08344, + "ndcg_at_5": 0.08783, + "ndcg_at_10": 0.11045, + "ndcg_at_20": 0.12904, + "ndcg_at_100": 0.1868, + "ndcg_at_1000": 0.25055, + "map_at_1": 0.02084, + "map_at_3": 0.0484, + "map_at_5": 0.05934, + "map_at_10": 0.07309, + "map_at_20": 0.07836, + "map_at_100": 0.08804, + "map_at_1000": 0.09124, + "recall_at_1": 0.02084, + "recall_at_3": 0.0719, + "recall_at_5": 0.09556, + "recall_at_10": 0.15022, + "recall_at_20": 0.1951, + "recall_at_100": 0.40134, + "recall_at_1000": 0.74325, + "precision_at_1": 0.07627, + "precision_at_3": 0.07062, + "precision_at_5": 0.06102, + "precision_at_10": 0.04915, + "precision_at_20": 0.03517, + "precision_at_100": 0.01576, + "precision_at_1000": 0.00307, + "mrr_at_1": 0.076271, + "mrr_at_3": 0.118644, + "mrr_at_5": 0.129661, + "mrr_at_10": 0.137745, + "mrr_at_20": 0.14649, + "mrr_at_100": 0.153436, + "mrr_at_1000": 0.154449, + "nauc_ndcg_at_1_max": 0.205104, + "nauc_ndcg_at_1_std": 0.035805, + "nauc_ndcg_at_1_diff1": -0.072708, + "nauc_ndcg_at_3_max": 0.061626, + "nauc_ndcg_at_3_std": 0.052507, + "nauc_ndcg_at_3_diff1": -0.126393, + "nauc_ndcg_at_5_max": 0.08694, + "nauc_ndcg_at_5_std": 0.106196, + "nauc_ndcg_at_5_diff1": -0.103452, + "nauc_ndcg_at_10_max": 0.092083, + "nauc_ndcg_at_10_std": 0.139539, + "nauc_ndcg_at_10_diff1": -0.061883, + "nauc_ndcg_at_20_max": 0.064227, + "nauc_ndcg_at_20_std": 0.118234, + "nauc_ndcg_at_20_diff1": -0.082892, + "nauc_ndcg_at_100_max": 0.12579, + "nauc_ndcg_at_100_std": 0.197086, + "nauc_ndcg_at_100_diff1": -0.046021, + "nauc_ndcg_at_1000_max": 0.125009, + "nauc_ndcg_at_1000_std": 0.184255, + "nauc_ndcg_at_1000_diff1": -0.06543, + "nauc_map_at_1_max": 0.238306, + "nauc_map_at_1_std": 0.032615, + "nauc_map_at_1_diff1": 0.076153, + "nauc_map_at_3_max": 0.072026, + "nauc_map_at_3_std": 0.054913, + "nauc_map_at_3_diff1": -0.099699, + "nauc_map_at_5_max": 0.114507, + "nauc_map_at_5_std": 0.101879, + "nauc_map_at_5_diff1": -0.112354, + "nauc_map_at_10_max": 0.110121, + "nauc_map_at_10_std": 0.133942, + "nauc_map_at_10_diff1": -0.088908, + "nauc_map_at_20_max": 0.098276, + "nauc_map_at_20_std": 0.121738, + "nauc_map_at_20_diff1": -0.097204, + "nauc_map_at_100_max": 0.112343, + "nauc_map_at_100_std": 0.140354, + "nauc_map_at_100_diff1": -0.082063, + "nauc_map_at_1000_max": 0.114443, + "nauc_map_at_1000_std": 0.1425, + "nauc_map_at_1000_diff1": -0.08177, + "nauc_recall_at_1_max": 0.238306, + "nauc_recall_at_1_std": 0.032615, + "nauc_recall_at_1_diff1": 0.076153, + "nauc_recall_at_3_max": -0.016865, + "nauc_recall_at_3_std": 0.077397, + "nauc_recall_at_3_diff1": -0.127354, + "nauc_recall_at_5_max": 0.044005, + "nauc_recall_at_5_std": 0.132568, + "nauc_recall_at_5_diff1": -0.111611, + "nauc_recall_at_10_max": 0.065523, + "nauc_recall_at_10_std": 0.174168, + "nauc_recall_at_10_diff1": -0.040086, + "nauc_recall_at_20_max": 0.019206, + "nauc_recall_at_20_std": 0.129034, + "nauc_recall_at_20_diff1": -0.080027, + "nauc_recall_at_100_max": 0.160906, + "nauc_recall_at_100_std": 0.286036, + "nauc_recall_at_100_diff1": 0.017019, + "nauc_recall_at_1000_max": 0.186994, + "nauc_recall_at_1000_std": 0.362952, + "nauc_recall_at_1000_diff1": -0.109179, + "nauc_precision_at_1_max": 0.205104, + "nauc_precision_at_1_std": 0.035805, + "nauc_precision_at_1_diff1": -0.072708, + "nauc_precision_at_3_max": 0.072626, + "nauc_precision_at_3_std": 0.106177, + "nauc_precision_at_3_diff1": -0.152359, + "nauc_precision_at_5_max": 0.127431, + "nauc_precision_at_5_std": 0.183285, + "nauc_precision_at_5_diff1": -0.1273, + "nauc_precision_at_10_max": 0.110458, + "nauc_precision_at_10_std": 0.191624, + "nauc_precision_at_10_diff1": -0.025527, + "nauc_precision_at_20_max": 0.044457, + "nauc_precision_at_20_std": 0.136729, + "nauc_precision_at_20_diff1": -0.064052, + "nauc_precision_at_100_max": 0.161089, + "nauc_precision_at_100_std": 0.282516, + "nauc_precision_at_100_diff1": -0.006751, + "nauc_precision_at_1000_max": 0.096205, + "nauc_precision_at_1000_std": 0.08733, + "nauc_precision_at_1000_diff1": -0.003652, + "nauc_mrr_at_1_max": 0.205104, + "nauc_mrr_at_1_std": 0.035805, + "nauc_mrr_at_1_diff1": -0.072708, + "nauc_mrr_at_3_max": 0.078517, + "nauc_mrr_at_3_std": 0.026895, + "nauc_mrr_at_3_diff1": -0.100336, + "nauc_mrr_at_5_max": 0.085723, + "nauc_mrr_at_5_std": 0.055862, + "nauc_mrr_at_5_diff1": -0.081819, + "nauc_mrr_at_10_max": 0.093498, + "nauc_mrr_at_10_std": 0.06435, + "nauc_mrr_at_10_diff1": -0.067601, + "nauc_mrr_at_20_max": 0.085914, + "nauc_mrr_at_20_std": 0.06436, + "nauc_mrr_at_20_diff1": -0.080507, + "nauc_mrr_at_100_max": 0.087709, + "nauc_mrr_at_100_std": 0.066256, + "nauc_mrr_at_100_diff1": -0.08196, + "nauc_mrr_at_1000_max": 0.087383, + "nauc_mrr_at_1000_std": 0.064917, + "nauc_mrr_at_1000_diff1": -0.081064, + "main_score": 0.11045, + "hf_subset": "MedQA-Diag", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.36, + "ndcg_at_3": 0.3184, + "ndcg_at_5": 0.33216, + "ndcg_at_10": 0.36132, + "ndcg_at_20": 0.38558, + "ndcg_at_100": 0.42181, + "ndcg_at_1000": 0.4505, + "map_at_1": 0.20667, + "map_at_3": 0.26263, + "map_at_5": 0.28046, + "map_at_10": 0.29462, + "map_at_20": 0.30385, + "map_at_100": 0.31005, + "map_at_1000": 0.3115, + "recall_at_1": 0.20667, + "recall_at_3": 0.30644, + "recall_at_5": 0.35467, + "recall_at_10": 0.43133, + "recall_at_20": 0.50567, + "recall_at_100": 0.673, + "recall_at_1000": 0.85767, + "precision_at_1": 0.36, + "precision_at_3": 0.18889, + "precision_at_5": 0.13733, + "precision_at_10": 0.084, + "precision_at_20": 0.051, + "precision_at_100": 0.0132, + "precision_at_1000": 0.00175, + "mrr_at_1": 0.36, + "mrr_at_3": 0.413333, + "mrr_at_5": 0.421, + "mrr_at_10": 0.430481, + "mrr_at_20": 0.436135, + "mrr_at_100": 0.440304, + "mrr_at_1000": 0.44077, + "nauc_ndcg_at_1_max": 0.532497, + "nauc_ndcg_at_1_std": 0.126804, + "nauc_ndcg_at_1_diff1": 0.493238, + "nauc_ndcg_at_3_max": 0.460633, + "nauc_ndcg_at_3_std": 0.086367, + "nauc_ndcg_at_3_diff1": 0.396866, + "nauc_ndcg_at_5_max": 0.444319, + "nauc_ndcg_at_5_std": 0.074837, + "nauc_ndcg_at_5_diff1": 0.391389, + "nauc_ndcg_at_10_max": 0.437572, + "nauc_ndcg_at_10_std": 0.108515, + "nauc_ndcg_at_10_diff1": 0.36177, + "nauc_ndcg_at_20_max": 0.453865, + "nauc_ndcg_at_20_std": 0.123919, + "nauc_ndcg_at_20_diff1": 0.358779, + "nauc_ndcg_at_100_max": 0.446791, + "nauc_ndcg_at_100_std": 0.12164, + "nauc_ndcg_at_100_diff1": 0.361498, + "nauc_ndcg_at_1000_max": 0.468866, + "nauc_ndcg_at_1000_std": 0.137056, + "nauc_ndcg_at_1000_diff1": 0.36597, + "nauc_map_at_1_max": 0.404966, + "nauc_map_at_1_std": 0.033917, + "nauc_map_at_1_diff1": 0.430948, + "nauc_map_at_3_max": 0.440539, + "nauc_map_at_3_std": 0.059021, + "nauc_map_at_3_diff1": 0.410885, + "nauc_map_at_5_max": 0.435871, + "nauc_map_at_5_std": 0.055036, + "nauc_map_at_5_diff1": 0.404225, + "nauc_map_at_10_max": 0.433431, + "nauc_map_at_10_std": 0.072746, + "nauc_map_at_10_diff1": 0.390869, + "nauc_map_at_20_max": 0.445338, + "nauc_map_at_20_std": 0.082903, + "nauc_map_at_20_diff1": 0.390979, + "nauc_map_at_100_max": 0.444031, + "nauc_map_at_100_std": 0.082274, + "nauc_map_at_100_diff1": 0.392273, + "nauc_map_at_1000_max": 0.445783, + "nauc_map_at_1000_std": 0.083687, + "nauc_map_at_1000_diff1": 0.39288, + "nauc_recall_at_1_max": 0.404966, + "nauc_recall_at_1_std": 0.033917, + "nauc_recall_at_1_diff1": 0.430948, + "nauc_recall_at_3_max": 0.365664, + "nauc_recall_at_3_std": 0.039709, + "nauc_recall_at_3_diff1": 0.33577, + "nauc_recall_at_5_max": 0.348823, + "nauc_recall_at_5_std": 0.029691, + "nauc_recall_at_5_diff1": 0.325813, + "nauc_recall_at_10_max": 0.299659, + "nauc_recall_at_10_std": 0.098703, + "nauc_recall_at_10_diff1": 0.229383, + "nauc_recall_at_20_max": 0.312155, + "nauc_recall_at_20_std": 0.129188, + "nauc_recall_at_20_diff1": 0.194513, + "nauc_recall_at_100_max": 0.204464, + "nauc_recall_at_100_std": 0.117426, + "nauc_recall_at_100_diff1": 0.134091, + "nauc_recall_at_1000_max": 0.304373, + "nauc_recall_at_1000_std": 0.309655, + "nauc_recall_at_1000_diff1": 0.017749, + "nauc_precision_at_1_max": 0.532497, + "nauc_precision_at_1_std": 0.126804, + "nauc_precision_at_1_diff1": 0.493238, + "nauc_precision_at_3_max": 0.535859, + "nauc_precision_at_3_std": 0.196293, + "nauc_precision_at_3_diff1": 0.361274, + "nauc_precision_at_5_max": 0.453307, + "nauc_precision_at_5_std": 0.165312, + "nauc_precision_at_5_diff1": 0.267432, + "nauc_precision_at_10_max": 0.401841, + "nauc_precision_at_10_std": 0.245891, + "nauc_precision_at_10_diff1": 0.156071, + "nauc_precision_at_20_max": 0.410517, + "nauc_precision_at_20_std": 0.274138, + "nauc_precision_at_20_diff1": 0.139109, + "nauc_precision_at_100_max": 0.335572, + "nauc_precision_at_100_std": 0.236618, + "nauc_precision_at_100_diff1": 0.084894, + "nauc_precision_at_1000_max": 0.292141, + "nauc_precision_at_1000_std": 0.231649, + "nauc_precision_at_1000_diff1": -0.000802, + "nauc_mrr_at_1_max": 0.532497, + "nauc_mrr_at_1_std": 0.126804, + "nauc_mrr_at_1_diff1": 0.493238, + "nauc_mrr_at_3_max": 0.529675, + "nauc_mrr_at_3_std": 0.142135, + "nauc_mrr_at_3_diff1": 0.428153, + "nauc_mrr_at_5_max": 0.52902, + "nauc_mrr_at_5_std": 0.14681, + "nauc_mrr_at_5_diff1": 0.427313, + "nauc_mrr_at_10_max": 0.524309, + "nauc_mrr_at_10_std": 0.153169, + "nauc_mrr_at_10_diff1": 0.417836, + "nauc_mrr_at_20_max": 0.523035, + "nauc_mrr_at_20_std": 0.15179, + "nauc_mrr_at_20_diff1": 0.417173, + "nauc_mrr_at_100_max": 0.522925, + "nauc_mrr_at_100_std": 0.15078, + "nauc_mrr_at_100_diff1": 0.419076, + "nauc_mrr_at_1000_max": 0.523303, + "nauc_mrr_at_1000_std": 0.151126, + "nauc_mrr_at_1000_diff1": 0.419624, + "main_score": 0.36132, + "hf_subset": "PMC-Treatment", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.16667, + "ndcg_at_3": 0.17427, + "ndcg_at_5": 0.18915, + "ndcg_at_10": 0.23832, + "ndcg_at_20": 0.26824, + "ndcg_at_100": 0.31776, + "ndcg_at_1000": 0.35758, + "map_at_1": 0.08333, + "map_at_3": 0.13255, + "map_at_5": 0.14323, + "map_at_10": 0.16464, + "map_at_20": 0.17463, + "map_at_100": 0.18353, + "map_at_1000": 0.18553, + "recall_at_1": 0.08333, + "recall_at_3": 0.18275, + "recall_at_5": 0.2193, + "recall_at_10": 0.34649, + "recall_at_20": 0.44225, + "recall_at_100": 0.65863, + "recall_at_1000": 0.91155, + "precision_at_1": 0.16667, + "precision_at_3": 0.12281, + "precision_at_5": 0.09123, + "precision_at_10": 0.07018, + "precision_at_20": 0.04561, + "precision_at_100": 0.01386, + "precision_at_1000": 0.00196, + "mrr_at_1": 0.166667, + "mrr_at_3": 0.238304, + "mrr_at_5": 0.247515, + "mrr_at_10": 0.269051, + "mrr_at_20": 0.275951, + "mrr_at_100": 0.280836, + "mrr_at_1000": 0.281642, + "nauc_ndcg_at_1_max": 0.108081, + "nauc_ndcg_at_1_std": 0.077223, + "nauc_ndcg_at_1_diff1": 0.262994, + "nauc_ndcg_at_3_max": 0.18118, + "nauc_ndcg_at_3_std": 0.155433, + "nauc_ndcg_at_3_diff1": 0.258506, + "nauc_ndcg_at_5_max": 0.163968, + "nauc_ndcg_at_5_std": 0.121105, + "nauc_ndcg_at_5_diff1": 0.253262, + "nauc_ndcg_at_10_max": 0.184567, + "nauc_ndcg_at_10_std": 0.105908, + "nauc_ndcg_at_10_diff1": 0.222549, + "nauc_ndcg_at_20_max": 0.202206, + "nauc_ndcg_at_20_std": 0.102197, + "nauc_ndcg_at_20_diff1": 0.23148, + "nauc_ndcg_at_100_max": 0.161588, + "nauc_ndcg_at_100_std": 0.112496, + "nauc_ndcg_at_100_diff1": 0.188585, + "nauc_ndcg_at_1000_max": 0.182105, + "nauc_ndcg_at_1000_std": 0.119071, + "nauc_ndcg_at_1000_diff1": 0.213175, + "nauc_map_at_1_max": 0.091225, + "nauc_map_at_1_std": 0.137962, + "nauc_map_at_1_diff1": 0.251297, + "nauc_map_at_3_max": 0.163239, + "nauc_map_at_3_std": 0.152489, + "nauc_map_at_3_diff1": 0.277578, + "nauc_map_at_5_max": 0.156508, + "nauc_map_at_5_std": 0.130161, + "nauc_map_at_5_diff1": 0.259758, + "nauc_map_at_10_max": 0.165283, + "nauc_map_at_10_std": 0.120934, + "nauc_map_at_10_diff1": 0.248432, + "nauc_map_at_20_max": 0.179861, + "nauc_map_at_20_std": 0.121938, + "nauc_map_at_20_diff1": 0.251231, + "nauc_map_at_100_max": 0.171596, + "nauc_map_at_100_std": 0.126185, + "nauc_map_at_100_diff1": 0.242242, + "nauc_map_at_1000_max": 0.172292, + "nauc_map_at_1000_std": 0.127108, + "nauc_map_at_1000_diff1": 0.242692, + "nauc_recall_at_1_max": 0.091225, + "nauc_recall_at_1_std": 0.137962, + "nauc_recall_at_1_diff1": 0.251297, + "nauc_recall_at_3_max": 0.173228, + "nauc_recall_at_3_std": 0.160451, + "nauc_recall_at_3_diff1": 0.266818, + "nauc_recall_at_5_max": 0.125823, + "nauc_recall_at_5_std": 0.104877, + "nauc_recall_at_5_diff1": 0.229475, + "nauc_recall_at_10_max": 0.158024, + "nauc_recall_at_10_std": 0.065786, + "nauc_recall_at_10_diff1": 0.148942, + "nauc_recall_at_20_max": 0.178733, + "nauc_recall_at_20_std": 0.047581, + "nauc_recall_at_20_diff1": 0.176351, + "nauc_recall_at_100_max": 0.015814, + "nauc_recall_at_100_std": 0.047668, + "nauc_recall_at_100_diff1": 0.020147, + "nauc_recall_at_1000_max": 0.061552, + "nauc_recall_at_1000_std": 0.037394, + "nauc_recall_at_1000_diff1": 0.092308, + "nauc_precision_at_1_max": 0.108081, + "nauc_precision_at_1_std": 0.077223, + "nauc_precision_at_1_diff1": 0.262994, + "nauc_precision_at_3_max": 0.249159, + "nauc_precision_at_3_std": 0.155947, + "nauc_precision_at_3_diff1": 0.194365, + "nauc_precision_at_5_max": 0.193755, + "nauc_precision_at_5_std": 0.086756, + "nauc_precision_at_5_diff1": 0.142498, + "nauc_precision_at_10_max": 0.231202, + "nauc_precision_at_10_std": 0.057776, + "nauc_precision_at_10_diff1": 0.060503, + "nauc_precision_at_20_max": 0.262824, + "nauc_precision_at_20_std": 0.063678, + "nauc_precision_at_20_diff1": 0.054246, + "nauc_precision_at_100_max": 0.131846, + "nauc_precision_at_100_std": 0.093411, + "nauc_precision_at_100_diff1": -0.09247, + "nauc_precision_at_1000_max": 0.147555, + "nauc_precision_at_1000_std": 0.051726, + "nauc_precision_at_1000_diff1": -0.063148, + "nauc_mrr_at_1_max": 0.108081, + "nauc_mrr_at_1_std": 0.077223, + "nauc_mrr_at_1_diff1": 0.262994, + "nauc_mrr_at_3_max": 0.186357, + "nauc_mrr_at_3_std": 0.114785, + "nauc_mrr_at_3_diff1": 0.248392, + "nauc_mrr_at_5_max": 0.170317, + "nauc_mrr_at_5_std": 0.106447, + "nauc_mrr_at_5_diff1": 0.253324, + "nauc_mrr_at_10_max": 0.182977, + "nauc_mrr_at_10_std": 0.104004, + "nauc_mrr_at_10_diff1": 0.246054, + "nauc_mrr_at_20_max": 0.182049, + "nauc_mrr_at_20_std": 0.099038, + "nauc_mrr_at_20_diff1": 0.246707, + "nauc_mrr_at_100_max": 0.177797, + "nauc_mrr_at_100_std": 0.102347, + "nauc_mrr_at_100_diff1": 0.243003, + "nauc_mrr_at_1000_max": 0.178442, + "nauc_mrr_at_1000_std": 0.102398, + "nauc_mrr_at_1000_diff1": 0.243859, + "main_score": 0.23832, + "hf_subset": "PMC-Clinical", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.17829, + "ndcg_at_3": 0.1498, + "ndcg_at_5": 0.15532, + "ndcg_at_10": 0.20141, + "ndcg_at_20": 0.24809, + "ndcg_at_100": 0.33915, + "ndcg_at_1000": 0.38591, + "map_at_1": 0.05465, + "map_at_3": 0.08854, + "map_at_5": 0.1029, + "map_at_10": 0.12673, + "map_at_20": 0.14254, + "map_at_100": 0.16398, + "map_at_1000": 0.16743, + "recall_at_1": 0.05465, + "recall_at_3": 0.11085, + "recall_at_5": 0.15969, + "recall_at_10": 0.26176, + "recall_at_20": 0.39121, + "recall_at_100": 0.71925, + "recall_at_1000": 0.97287, + "precision_at_1": 0.17829, + "precision_at_3": 0.12403, + "precision_at_5": 0.10543, + "precision_at_10": 0.09147, + "precision_at_20": 0.06783, + "precision_at_100": 0.02581, + "precision_at_1000": 0.00346, + "mrr_at_1": 0.178295, + "mrr_at_3": 0.22739, + "mrr_at_5": 0.251421, + "mrr_at_10": 0.273044, + "mrr_at_20": 0.283309, + "mrr_at_100": 0.288678, + "mrr_at_1000": 0.28906, + "nauc_ndcg_at_1_max": 0.161331, + "nauc_ndcg_at_1_std": 0.219226, + "nauc_ndcg_at_1_diff1": 0.062335, + "nauc_ndcg_at_3_max": 0.145709, + "nauc_ndcg_at_3_std": 0.131016, + "nauc_ndcg_at_3_diff1": 0.08561, + "nauc_ndcg_at_5_max": 0.112042, + "nauc_ndcg_at_5_std": 0.131377, + "nauc_ndcg_at_5_diff1": 0.109583, + "nauc_ndcg_at_10_max": 0.137869, + "nauc_ndcg_at_10_std": 0.134783, + "nauc_ndcg_at_10_diff1": 0.042172, + "nauc_ndcg_at_20_max": 0.184084, + "nauc_ndcg_at_20_std": 0.142767, + "nauc_ndcg_at_20_diff1": 0.097115, + "nauc_ndcg_at_100_max": 0.223021, + "nauc_ndcg_at_100_std": 0.252178, + "nauc_ndcg_at_100_diff1": 0.083183, + "nauc_ndcg_at_1000_max": 0.17286, + "nauc_ndcg_at_1000_std": 0.227504, + "nauc_ndcg_at_1000_diff1": 0.055681, + "nauc_map_at_1_max": 0.028726, + "nauc_map_at_1_std": 0.045229, + "nauc_map_at_1_diff1": 0.074523, + "nauc_map_at_3_max": 0.10734, + "nauc_map_at_3_std": 0.083699, + "nauc_map_at_3_diff1": 0.102075, + "nauc_map_at_5_max": 0.086428, + "nauc_map_at_5_std": 0.101867, + "nauc_map_at_5_diff1": 0.110707, + "nauc_map_at_10_max": 0.104221, + "nauc_map_at_10_std": 0.112335, + "nauc_map_at_10_diff1": 0.068146, + "nauc_map_at_20_max": 0.134631, + "nauc_map_at_20_std": 0.122027, + "nauc_map_at_20_diff1": 0.092043, + "nauc_map_at_100_max": 0.156514, + "nauc_map_at_100_std": 0.151904, + "nauc_map_at_100_diff1": 0.090405, + "nauc_map_at_1000_max": 0.152482, + "nauc_map_at_1000_std": 0.152537, + "nauc_map_at_1000_diff1": 0.087034, + "nauc_recall_at_1_max": 0.028726, + "nauc_recall_at_1_std": 0.045229, + "nauc_recall_at_1_diff1": 0.074523, + "nauc_recall_at_3_max": 0.068428, + "nauc_recall_at_3_std": 0.034887, + "nauc_recall_at_3_diff1": 0.080767, + "nauc_recall_at_5_max": 0.062518, + "nauc_recall_at_5_std": 0.046507, + "nauc_recall_at_5_diff1": 0.146629, + "nauc_recall_at_10_max": 0.093823, + "nauc_recall_at_10_std": 0.072073, + "nauc_recall_at_10_diff1": 0.003786, + "nauc_recall_at_20_max": 0.165789, + "nauc_recall_at_20_std": 0.060629, + "nauc_recall_at_20_diff1": 0.141435, + "nauc_recall_at_100_max": 0.290607, + "nauc_recall_at_100_std": 0.376304, + "nauc_recall_at_100_diff1": 0.08093, + "nauc_recall_at_1000_max": -0.540994, + "nauc_recall_at_1000_std": 0.556906, + "nauc_recall_at_1000_diff1": -0.34217, + "nauc_precision_at_1_max": 0.161331, + "nauc_precision_at_1_std": 0.219226, + "nauc_precision_at_1_diff1": 0.062335, + "nauc_precision_at_3_max": 0.232952, + "nauc_precision_at_3_std": 0.197249, + "nauc_precision_at_3_diff1": 0.084286, + "nauc_precision_at_5_max": 0.183199, + "nauc_precision_at_5_std": 0.247605, + "nauc_precision_at_5_diff1": 0.105949, + "nauc_precision_at_10_max": 0.195974, + "nauc_precision_at_10_std": 0.20617, + "nauc_precision_at_10_diff1": -0.033565, + "nauc_precision_at_20_max": 0.279822, + "nauc_precision_at_20_std": 0.217402, + "nauc_precision_at_20_diff1": 0.052466, + "nauc_precision_at_100_max": 0.248803, + "nauc_precision_at_100_std": 0.387713, + "nauc_precision_at_100_diff1": 0.025849, + "nauc_precision_at_1000_max": 0.096233, + "nauc_precision_at_1000_std": 0.303173, + "nauc_precision_at_1000_diff1": -0.072032, + "nauc_mrr_at_1_max": 0.161331, + "nauc_mrr_at_1_std": 0.219226, + "nauc_mrr_at_1_diff1": 0.062335, + "nauc_mrr_at_3_max": 0.166822, + "nauc_mrr_at_3_std": 0.166697, + "nauc_mrr_at_3_diff1": 0.057097, + "nauc_mrr_at_5_max": 0.170657, + "nauc_mrr_at_5_std": 0.17567, + "nauc_mrr_at_5_diff1": 0.076898, + "nauc_mrr_at_10_max": 0.175666, + "nauc_mrr_at_10_std": 0.194935, + "nauc_mrr_at_10_diff1": 0.053318, + "nauc_mrr_at_20_max": 0.177884, + "nauc_mrr_at_20_std": 0.193992, + "nauc_mrr_at_20_diff1": 0.060448, + "nauc_mrr_at_100_max": 0.175062, + "nauc_mrr_at_100_std": 0.194884, + "nauc_mrr_at_100_diff1": 0.059402, + "nauc_mrr_at_1000_max": 0.174901, + "nauc_mrr_at_1000_std": 0.194349, + "nauc_mrr_at_1000_diff1": 0.059418, + "main_score": 0.20141, + "hf_subset": "IIYi-Clinical", + "languages": [ + "eng-Latn" + ] + } + ] + }, + "evaluation_time": 1450.442634344101, + "kg_co2_emissions": null +} \ No newline at end of file diff --git a/results/NovaSearch__stella_en_400M_v5/1bb50bc7bb726810eac2140e62155b88b0df198f/R2MEDRetrieval.json b/results/NovaSearch__stella_en_400M_v5/1bb50bc7bb726810eac2140e62155b88b0df198f/R2MEDRetrieval.json new file mode 100644 index 0000000000..3fe4e01435 --- /dev/null +++ b/results/NovaSearch__stella_en_400M_v5/1bb50bc7bb726810eac2140e62155b88b0df198f/R2MEDRetrieval.json @@ -0,0 +1,1187 @@ +{ + "dataset_revision": "1.0", + "task_name": "R2MEDRetrieval", + "mteb_version": "1.38.20", + "scores": { + "test": [ + { + "ndcg_at_1": 0.13592, + "ndcg_at_3": 0.10818, + "ndcg_at_5": 0.12258, + "ndcg_at_10": 0.13941, + "ndcg_at_20": 0.17047, + "ndcg_at_100": 0.22337, + "ndcg_at_1000": 0.28231, + "map_at_1": 0.04312, + "map_at_3": 0.06514, + "map_at_5": 0.07989, + "map_at_10": 0.08966, + "map_at_20": 0.10143, + "map_at_100": 0.11288, + "map_at_1000": 0.11605, + "recall_at_1": 0.04312, + "recall_at_3": 0.07867, + "recall_at_5": 0.12475, + "recall_at_10": 0.16615, + "recall_at_20": 0.24836, + "recall_at_100": 0.44367, + "recall_at_1000": 0.77699, + "precision_at_1": 0.13592, + "precision_at_3": 0.08414, + "precision_at_5": 0.0835, + "precision_at_10": 0.06214, + "precision_at_20": 0.04854, + "precision_at_100": 0.01699, + "precision_at_1000": 0.00283, + "mrr_at_1": 0.135922, + "mrr_at_3": 0.161812, + "mrr_at_5": 0.18657, + "mrr_at_10": 0.197704, + "mrr_at_20": 0.205262, + "mrr_at_100": 0.20991, + "mrr_at_1000": 0.211044, + "nauc_ndcg_at_1_max": -0.007609, + "nauc_ndcg_at_1_std": -0.119878, + "nauc_ndcg_at_1_diff1": 0.110621, + "nauc_ndcg_at_3_max": 0.018846, + "nauc_ndcg_at_3_std": -0.156428, + "nauc_ndcg_at_3_diff1": 0.188576, + "nauc_ndcg_at_5_max": -0.033406, + "nauc_ndcg_at_5_std": -0.201251, + "nauc_ndcg_at_5_diff1": 0.147696, + "nauc_ndcg_at_10_max": -0.083706, + "nauc_ndcg_at_10_std": -0.189805, + "nauc_ndcg_at_10_diff1": 0.077481, + "nauc_ndcg_at_20_max": -0.090157, + "nauc_ndcg_at_20_std": -0.2369, + "nauc_ndcg_at_20_diff1": 0.038213, + "nauc_ndcg_at_100_max": -0.115395, + "nauc_ndcg_at_100_std": -0.246237, + "nauc_ndcg_at_100_diff1": 0.02773, + "nauc_ndcg_at_1000_max": -0.082938, + "nauc_ndcg_at_1000_std": -0.169308, + "nauc_ndcg_at_1000_diff1": 0.064684, + "nauc_map_at_1_max": -0.02032, + "nauc_map_at_1_std": -0.113644, + "nauc_map_at_1_diff1": 0.291332, + "nauc_map_at_3_max": 0.007522, + "nauc_map_at_3_std": -0.163015, + "nauc_map_at_3_diff1": 0.301791, + "nauc_map_at_5_max": -0.024303, + "nauc_map_at_5_std": -0.196746, + "nauc_map_at_5_diff1": 0.243798, + "nauc_map_at_10_max": -0.069944, + "nauc_map_at_10_std": -0.197481, + "nauc_map_at_10_diff1": 0.184186, + "nauc_map_at_20_max": -0.071055, + "nauc_map_at_20_std": -0.220091, + "nauc_map_at_20_diff1": 0.147563, + "nauc_map_at_100_max": -0.088948, + "nauc_map_at_100_std": -0.225899, + "nauc_map_at_100_diff1": 0.1313, + "nauc_map_at_1000_max": -0.087868, + "nauc_map_at_1000_std": -0.22046, + "nauc_map_at_1000_diff1": 0.131979, + "nauc_recall_at_1_max": -0.02032, + "nauc_recall_at_1_std": -0.113644, + "nauc_recall_at_1_diff1": 0.291332, + "nauc_recall_at_3_max": 0.097292, + "nauc_recall_at_3_std": -0.162689, + "nauc_recall_at_3_diff1": 0.344284, + "nauc_recall_at_5_max": 0.001859, + "nauc_recall_at_5_std": -0.21173, + "nauc_recall_at_5_diff1": 0.18963, + "nauc_recall_at_10_max": -0.091774, + "nauc_recall_at_10_std": -0.184646, + "nauc_recall_at_10_diff1": 0.041989, + "nauc_recall_at_20_max": -0.113964, + "nauc_recall_at_20_std": -0.27103, + "nauc_recall_at_20_diff1": -0.031609, + "nauc_recall_at_100_max": -0.169854, + "nauc_recall_at_100_std": -0.260048, + "nauc_recall_at_100_diff1": -0.027446, + "nauc_recall_at_1000_max": -0.061679, + "nauc_recall_at_1000_std": 0.159399, + "nauc_recall_at_1000_diff1": 0.140774, + "nauc_precision_at_1_max": -0.007609, + "nauc_precision_at_1_std": -0.119878, + "nauc_precision_at_1_diff1": 0.110621, + "nauc_precision_at_3_max": 0.015626, + "nauc_precision_at_3_std": -0.166043, + "nauc_precision_at_3_diff1": 0.125573, + "nauc_precision_at_5_max": -0.072306, + "nauc_precision_at_5_std": -0.23751, + "nauc_precision_at_5_diff1": 0.017651, + "nauc_precision_at_10_max": -0.220365, + "nauc_precision_at_10_std": -0.226535, + "nauc_precision_at_10_diff1": -0.156015, + "nauc_precision_at_20_max": -0.190673, + "nauc_precision_at_20_std": -0.273634, + "nauc_precision_at_20_diff1": -0.193686, + "nauc_precision_at_100_max": -0.160161, + "nauc_precision_at_100_std": -0.238333, + "nauc_precision_at_100_diff1": -0.17087, + "nauc_precision_at_1000_max": -0.027538, + "nauc_precision_at_1000_std": -0.047161, + "nauc_precision_at_1000_diff1": -0.073047, + "nauc_mrr_at_1_max": 0.018549, + "nauc_mrr_at_1_std": -0.102158, + "nauc_mrr_at_1_diff1": 0.110621, + "nauc_mrr_at_3_max": 0.020292, + "nauc_mrr_at_3_std": -0.123436, + "nauc_mrr_at_3_diff1": 0.094715, + "nauc_mrr_at_5_max": -0.012739, + "nauc_mrr_at_5_std": -0.13819, + "nauc_mrr_at_5_diff1": 0.051162, + "nauc_mrr_at_10_max": -0.024624, + "nauc_mrr_at_10_std": -0.141884, + "nauc_mrr_at_10_diff1": 0.028763, + "nauc_mrr_at_20_max": -0.026289, + "nauc_mrr_at_20_std": -0.150761, + "nauc_mrr_at_20_diff1": 0.033235, + "nauc_mrr_at_100_max": -0.023662, + "nauc_mrr_at_100_std": -0.154069, + "nauc_mrr_at_100_diff1": 0.037485, + "nauc_mrr_at_1000_max": -0.022802, + "nauc_mrr_at_1000_std": -0.152252, + "nauc_mrr_at_1000_diff1": 0.038776, + "main_score": 0.13941, + "hf_subset": "Biology", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.22078, + "ndcg_at_3": 0.25452, + "ndcg_at_5": 0.26489, + "ndcg_at_10": 0.31906, + "ndcg_at_20": 0.35286, + "ndcg_at_100": 0.40875, + "ndcg_at_1000": 0.44825, + "map_at_1": 0.10425, + "map_at_3": 0.18162, + "map_at_5": 0.20142, + "map_at_10": 0.23297, + "map_at_20": 0.24573, + "map_at_100": 0.25768, + "map_at_1000": 0.2605, + "recall_at_1": 0.10425, + "recall_at_3": 0.23891, + "recall_at_5": 0.29184, + "recall_at_10": 0.43476, + "recall_at_20": 0.53375, + "recall_at_100": 0.75651, + "recall_at_1000": 0.98632, + "precision_at_1": 0.22078, + "precision_at_3": 0.18615, + "precision_at_5": 0.14545, + "precision_at_10": 0.11558, + "precision_at_20": 0.07273, + "precision_at_100": 0.02169, + "precision_at_1000": 0.00287, + "mrr_at_1": 0.220779, + "mrr_at_3": 0.311688, + "mrr_at_5": 0.336364, + "mrr_at_10": 0.351551, + "mrr_at_20": 0.356371, + "mrr_at_100": 0.360345, + "mrr_at_1000": 0.360911, + "nauc_ndcg_at_1_max": 0.080076, + "nauc_ndcg_at_1_std": -0.152397, + "nauc_ndcg_at_1_diff1": 0.185579, + "nauc_ndcg_at_3_max": 0.023459, + "nauc_ndcg_at_3_std": -0.182753, + "nauc_ndcg_at_3_diff1": 0.215055, + "nauc_ndcg_at_5_max": 0.083972, + "nauc_ndcg_at_5_std": -0.172658, + "nauc_ndcg_at_5_diff1": 0.23039, + "nauc_ndcg_at_10_max": 0.11795, + "nauc_ndcg_at_10_std": -0.121121, + "nauc_ndcg_at_10_diff1": 0.227965, + "nauc_ndcg_at_20_max": 0.103945, + "nauc_ndcg_at_20_std": -0.116056, + "nauc_ndcg_at_20_diff1": 0.210954, + "nauc_ndcg_at_100_max": 0.078913, + "nauc_ndcg_at_100_std": -0.09593, + "nauc_ndcg_at_100_diff1": 0.148067, + "nauc_ndcg_at_1000_max": 0.068675, + "nauc_ndcg_at_1000_std": -0.131327, + "nauc_ndcg_at_1000_diff1": 0.186299, + "nauc_map_at_1_max": 0.123205, + "nauc_map_at_1_std": -0.218438, + "nauc_map_at_1_diff1": 0.362942, + "nauc_map_at_3_max": 0.114745, + "nauc_map_at_3_std": -0.176515, + "nauc_map_at_3_diff1": 0.32576, + "nauc_map_at_5_max": 0.138018, + "nauc_map_at_5_std": -0.155383, + "nauc_map_at_5_diff1": 0.291102, + "nauc_map_at_10_max": 0.134683, + "nauc_map_at_10_std": -0.144705, + "nauc_map_at_10_diff1": 0.27041, + "nauc_map_at_20_max": 0.131319, + "nauc_map_at_20_std": -0.144369, + "nauc_map_at_20_diff1": 0.269301, + "nauc_map_at_100_max": 0.123003, + "nauc_map_at_100_std": -0.141911, + "nauc_map_at_100_diff1": 0.252666, + "nauc_map_at_1000_max": 0.122338, + "nauc_map_at_1000_std": -0.143276, + "nauc_map_at_1000_diff1": 0.254876, + "nauc_recall_at_1_max": 0.123205, + "nauc_recall_at_1_std": -0.218438, + "nauc_recall_at_1_diff1": 0.362942, + "nauc_recall_at_3_max": 0.049367, + "nauc_recall_at_3_std": -0.169028, + "nauc_recall_at_3_diff1": 0.260042, + "nauc_recall_at_5_max": 0.117976, + "nauc_recall_at_5_std": -0.135154, + "nauc_recall_at_5_diff1": 0.219846, + "nauc_recall_at_10_max": 0.183361, + "nauc_recall_at_10_std": -0.017031, + "nauc_recall_at_10_diff1": 0.195809, + "nauc_recall_at_20_max": 0.146003, + "nauc_recall_at_20_std": 0.014368, + "nauc_recall_at_20_diff1": 0.136697, + "nauc_recall_at_100_max": 0.087882, + "nauc_recall_at_100_std": 0.153709, + "nauc_recall_at_100_diff1": -0.135577, + "nauc_recall_at_1000_max": -0.14364, + "nauc_recall_at_1000_std": -0.028767, + "nauc_recall_at_1000_diff1": -0.181149, + "nauc_precision_at_1_max": 0.080076, + "nauc_precision_at_1_std": -0.152397, + "nauc_precision_at_1_diff1": 0.185579, + "nauc_precision_at_3_max": 0.003379, + "nauc_precision_at_3_std": -0.118156, + "nauc_precision_at_3_diff1": 0.098864, + "nauc_precision_at_5_max": 0.078027, + "nauc_precision_at_5_std": -0.098852, + "nauc_precision_at_5_diff1": 0.053032, + "nauc_precision_at_10_max": 0.044501, + "nauc_precision_at_10_std": -0.031221, + "nauc_precision_at_10_diff1": 0.01538, + "nauc_precision_at_20_max": -0.014715, + "nauc_precision_at_20_std": -0.031374, + "nauc_precision_at_20_diff1": -0.044986, + "nauc_precision_at_100_max": -0.114245, + "nauc_precision_at_100_std": 0.032713, + "nauc_precision_at_100_diff1": -0.214738, + "nauc_precision_at_1000_max": -0.143985, + "nauc_precision_at_1000_std": -0.04941, + "nauc_precision_at_1000_diff1": -0.101725, + "nauc_mrr_at_1_max": 0.080076, + "nauc_mrr_at_1_std": -0.152397, + "nauc_mrr_at_1_diff1": 0.185579, + "nauc_mrr_at_3_max": -0.019233, + "nauc_mrr_at_3_std": -0.169864, + "nauc_mrr_at_3_diff1": 0.146074, + "nauc_mrr_at_5_max": 0.011169, + "nauc_mrr_at_5_std": -0.173481, + "nauc_mrr_at_5_diff1": 0.157027, + "nauc_mrr_at_10_max": 0.020893, + "nauc_mrr_at_10_std": -0.152258, + "nauc_mrr_at_10_diff1": 0.160081, + "nauc_mrr_at_20_max": 0.017992, + "nauc_mrr_at_20_std": -0.148584, + "nauc_mrr_at_20_diff1": 0.154866, + "nauc_mrr_at_100_max": 0.01624, + "nauc_mrr_at_100_std": -0.149174, + "nauc_mrr_at_100_diff1": 0.150299, + "nauc_mrr_at_1000_max": 0.017031, + "nauc_mrr_at_1000_std": -0.149697, + "nauc_mrr_at_1000_diff1": 0.15161, + "main_score": 0.31906, + "hf_subset": "Bioinformatics", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.18182, + "ndcg_at_3": 0.23725, + "ndcg_at_5": 0.27553, + "ndcg_at_10": 0.31266, + "ndcg_at_20": 0.35149, + "ndcg_at_100": 0.40645, + "ndcg_at_1000": 0.43451, + "map_at_1": 0.09643, + "map_at_3": 0.17636, + "map_at_5": 0.20732, + "map_at_10": 0.22684, + "map_at_20": 0.24308, + "map_at_100": 0.25513, + "map_at_1000": 0.25707, + "recall_at_1": 0.09643, + "recall_at_3": 0.26983, + "recall_at_5": 0.36058, + "recall_at_10": 0.45248, + "recall_at_20": 0.56146, + "recall_at_100": 0.77317, + "recall_at_1000": 0.92281, + "precision_at_1": 0.18182, + "precision_at_3": 0.1553, + "precision_at_5": 0.13864, + "precision_at_10": 0.09432, + "precision_at_20": 0.06477, + "precision_at_100": 0.01966, + "precision_at_1000": 0.00251, + "mrr_at_1": 0.181818, + "mrr_at_3": 0.280303, + "mrr_at_5": 0.306439, + "mrr_at_10": 0.325749, + "mrr_at_20": 0.330141, + "mrr_at_100": 0.335193, + "mrr_at_1000": 0.335593, + "nauc_ndcg_at_1_max": 0.154162, + "nauc_ndcg_at_1_std": -0.036331, + "nauc_ndcg_at_1_diff1": 0.150641, + "nauc_ndcg_at_3_max": 0.146567, + "nauc_ndcg_at_3_std": -0.12366, + "nauc_ndcg_at_3_diff1": 0.159372, + "nauc_ndcg_at_5_max": 0.152205, + "nauc_ndcg_at_5_std": -0.096585, + "nauc_ndcg_at_5_diff1": 0.175357, + "nauc_ndcg_at_10_max": 0.173348, + "nauc_ndcg_at_10_std": -0.077968, + "nauc_ndcg_at_10_diff1": 0.158848, + "nauc_ndcg_at_20_max": 0.164136, + "nauc_ndcg_at_20_std": -0.057896, + "nauc_ndcg_at_20_diff1": 0.142197, + "nauc_ndcg_at_100_max": 0.20116, + "nauc_ndcg_at_100_std": -0.030298, + "nauc_ndcg_at_100_diff1": 0.194184, + "nauc_ndcg_at_1000_max": 0.208612, + "nauc_ndcg_at_1000_std": -0.014386, + "nauc_ndcg_at_1000_diff1": 0.174066, + "nauc_map_at_1_max": 0.084216, + "nauc_map_at_1_std": -0.155627, + "nauc_map_at_1_diff1": 0.155596, + "nauc_map_at_3_max": 0.133344, + "nauc_map_at_3_std": -0.180981, + "nauc_map_at_3_diff1": 0.161394, + "nauc_map_at_5_max": 0.146379, + "nauc_map_at_5_std": -0.133984, + "nauc_map_at_5_diff1": 0.164133, + "nauc_map_at_10_max": 0.164883, + "nauc_map_at_10_std": -0.120839, + "nauc_map_at_10_diff1": 0.158071, + "nauc_map_at_20_max": 0.164318, + "nauc_map_at_20_std": -0.113084, + "nauc_map_at_20_diff1": 0.148896, + "nauc_map_at_100_max": 0.172675, + "nauc_map_at_100_std": -0.102885, + "nauc_map_at_100_diff1": 0.163642, + "nauc_map_at_1000_max": 0.174592, + "nauc_map_at_1000_std": -0.099747, + "nauc_map_at_1000_diff1": 0.163131, + "nauc_recall_at_1_max": 0.084216, + "nauc_recall_at_1_std": -0.155627, + "nauc_recall_at_1_diff1": 0.155596, + "nauc_recall_at_3_max": 0.113942, + "nauc_recall_at_3_std": -0.177996, + "nauc_recall_at_3_diff1": 0.163672, + "nauc_recall_at_5_max": 0.108488, + "nauc_recall_at_5_std": -0.119053, + "nauc_recall_at_5_diff1": 0.200559, + "nauc_recall_at_10_max": 0.127793, + "nauc_recall_at_10_std": -0.097217, + "nauc_recall_at_10_diff1": 0.160787, + "nauc_recall_at_20_max": 0.092316, + "nauc_recall_at_20_std": -0.06057, + "nauc_recall_at_20_diff1": 0.111085, + "nauc_recall_at_100_max": 0.166255, + "nauc_recall_at_100_std": 0.019871, + "nauc_recall_at_100_diff1": 0.287745, + "nauc_recall_at_1000_max": 0.165802, + "nauc_recall_at_1000_std": 0.172824, + "nauc_recall_at_1000_diff1": 0.195021, + "nauc_precision_at_1_max": 0.154162, + "nauc_precision_at_1_std": -0.036331, + "nauc_precision_at_1_diff1": 0.150641, + "nauc_precision_at_3_max": 0.240452, + "nauc_precision_at_3_std": 0.016272, + "nauc_precision_at_3_diff1": 0.136528, + "nauc_precision_at_5_max": 0.234536, + "nauc_precision_at_5_std": 0.118486, + "nauc_precision_at_5_diff1": 0.102092, + "nauc_precision_at_10_max": 0.285828, + "nauc_precision_at_10_std": 0.180633, + "nauc_precision_at_10_diff1": 0.029605, + "nauc_precision_at_20_max": 0.224753, + "nauc_precision_at_20_std": 0.20476, + "nauc_precision_at_20_diff1": 0.009582, + "nauc_precision_at_100_max": 0.290159, + "nauc_precision_at_100_std": 0.277064, + "nauc_precision_at_100_diff1": 0.1173, + "nauc_precision_at_1000_max": 0.237791, + "nauc_precision_at_1000_std": 0.292281, + "nauc_precision_at_1000_diff1": -0.012664, + "nauc_mrr_at_1_max": 0.154162, + "nauc_mrr_at_1_std": -0.036331, + "nauc_mrr_at_1_diff1": 0.150641, + "nauc_mrr_at_3_max": 0.157487, + "nauc_mrr_at_3_std": -0.033289, + "nauc_mrr_at_3_diff1": 0.133605, + "nauc_mrr_at_5_max": 0.159796, + "nauc_mrr_at_5_std": -0.033726, + "nauc_mrr_at_5_diff1": 0.158382, + "nauc_mrr_at_10_max": 0.162963, + "nauc_mrr_at_10_std": -0.017245, + "nauc_mrr_at_10_diff1": 0.146157, + "nauc_mrr_at_20_max": 0.156907, + "nauc_mrr_at_20_std": -0.014014, + "nauc_mrr_at_20_diff1": 0.141035, + "nauc_mrr_at_100_max": 0.159173, + "nauc_mrr_at_100_std": -0.017711, + "nauc_mrr_at_100_diff1": 0.14609, + "nauc_mrr_at_1000_max": 0.15926, + "nauc_mrr_at_1000_std": -0.017952, + "nauc_mrr_at_1000_diff1": 0.146099, + "main_score": 0.31266, + "hf_subset": "Medical-Sciences", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.05155, + "ndcg_at_3": 0.04921, + "ndcg_at_5": 0.0524, + "ndcg_at_10": 0.07114, + "ndcg_at_20": 0.0774, + "ndcg_at_100": 0.1096, + "ndcg_at_1000": 0.16818, + "map_at_1": 0.02182, + "map_at_3": 0.03351, + "map_at_5": 0.03686, + "map_at_10": 0.04311, + "map_at_20": 0.04523, + "map_at_100": 0.04929, + "map_at_1000": 0.05201, + "recall_at_1": 0.02182, + "recall_at_3": 0.04837, + "recall_at_5": 0.05988, + "recall_at_10": 0.10569, + "recall_at_20": 0.12331, + "recall_at_100": 0.26095, + "recall_at_1000": 0.61156, + "precision_at_1": 0.05155, + "precision_at_3": 0.03436, + "precision_at_5": 0.02887, + "precision_at_10": 0.02784, + "precision_at_20": 0.01649, + "precision_at_100": 0.00691, + "precision_at_1000": 0.00176, + "mrr_at_1": 0.051546, + "mrr_at_3": 0.068729, + "mrr_at_5": 0.075945, + "mrr_at_10": 0.088803, + "mrr_at_20": 0.090349, + "mrr_at_100": 0.095869, + "mrr_at_1000": 0.09705, + "nauc_ndcg_at_1_max": 0.303211, + "nauc_ndcg_at_1_std": -0.011538, + "nauc_ndcg_at_1_diff1": 0.443217, + "nauc_ndcg_at_3_max": 0.230179, + "nauc_ndcg_at_3_std": 0.071133, + "nauc_ndcg_at_3_diff1": 0.311817, + "nauc_ndcg_at_5_max": 0.257058, + "nauc_ndcg_at_5_std": 0.065601, + "nauc_ndcg_at_5_diff1": 0.330518, + "nauc_ndcg_at_10_max": 0.191543, + "nauc_ndcg_at_10_std": 0.057733, + "nauc_ndcg_at_10_diff1": 0.244924, + "nauc_ndcg_at_20_max": 0.162356, + "nauc_ndcg_at_20_std": 0.075954, + "nauc_ndcg_at_20_diff1": 0.199595, + "nauc_ndcg_at_100_max": 0.153169, + "nauc_ndcg_at_100_std": 0.111013, + "nauc_ndcg_at_100_diff1": 0.195997, + "nauc_ndcg_at_1000_max": 0.189671, + "nauc_ndcg_at_1000_std": 0.2177, + "nauc_ndcg_at_1000_diff1": 0.182566, + "nauc_map_at_1_max": 0.612801, + "nauc_map_at_1_std": -0.156513, + "nauc_map_at_1_diff1": 0.699694, + "nauc_map_at_3_max": 0.381908, + "nauc_map_at_3_std": -0.001277, + "nauc_map_at_3_diff1": 0.402356, + "nauc_map_at_5_max": 0.35485, + "nauc_map_at_5_std": 0.020511, + "nauc_map_at_5_diff1": 0.397938, + "nauc_map_at_10_max": 0.2977, + "nauc_map_at_10_std": 0.012408, + "nauc_map_at_10_diff1": 0.342522, + "nauc_map_at_20_max": 0.279008, + "nauc_map_at_20_std": 0.02692, + "nauc_map_at_20_diff1": 0.31362, + "nauc_map_at_100_max": 0.267754, + "nauc_map_at_100_std": 0.038778, + "nauc_map_at_100_diff1": 0.308051, + "nauc_map_at_1000_max": 0.266536, + "nauc_map_at_1000_std": 0.047827, + "nauc_map_at_1000_diff1": 0.300833, + "nauc_recall_at_1_max": 0.612801, + "nauc_recall_at_1_std": -0.156513, + "nauc_recall_at_1_diff1": 0.699694, + "nauc_recall_at_3_max": 0.278729, + "nauc_recall_at_3_std": 0.077003, + "nauc_recall_at_3_diff1": 0.240433, + "nauc_recall_at_5_max": 0.230652, + "nauc_recall_at_5_std": 0.114781, + "nauc_recall_at_5_diff1": 0.223825, + "nauc_recall_at_10_max": 0.092638, + "nauc_recall_at_10_std": 0.068298, + "nauc_recall_at_10_diff1": 0.094912, + "nauc_recall_at_20_max": 0.048069, + "nauc_recall_at_20_std": 0.103891, + "nauc_recall_at_20_diff1": 0.020077, + "nauc_recall_at_100_max": 0.077627, + "nauc_recall_at_100_std": 0.159902, + "nauc_recall_at_100_diff1": 0.066435, + "nauc_recall_at_1000_max": 0.258324, + "nauc_recall_at_1000_std": 0.501543, + "nauc_recall_at_1000_diff1": 0.041284, + "nauc_precision_at_1_max": 0.303211, + "nauc_precision_at_1_std": -0.011538, + "nauc_precision_at_1_diff1": 0.443217, + "nauc_precision_at_3_max": 0.080264, + "nauc_precision_at_3_std": 0.161461, + "nauc_precision_at_3_diff1": 0.253242, + "nauc_precision_at_5_max": 0.065711, + "nauc_precision_at_5_std": 0.190844, + "nauc_precision_at_5_diff1": 0.261958, + "nauc_precision_at_10_max": 0.030694, + "nauc_precision_at_10_std": 0.14663, + "nauc_precision_at_10_diff1": 0.147818, + "nauc_precision_at_20_max": -0.013965, + "nauc_precision_at_20_std": 0.157448, + "nauc_precision_at_20_diff1": 0.066495, + "nauc_precision_at_100_max": 0.005369, + "nauc_precision_at_100_std": 0.213897, + "nauc_precision_at_100_diff1": 0.076195, + "nauc_precision_at_1000_max": 0.00948, + "nauc_precision_at_1000_std": 0.25942, + "nauc_precision_at_1000_diff1": 0.048129, + "nauc_mrr_at_1_max": 0.303211, + "nauc_mrr_at_1_std": -0.011538, + "nauc_mrr_at_1_diff1": 0.443217, + "nauc_mrr_at_3_max": 0.223533, + "nauc_mrr_at_3_std": 0.035477, + "nauc_mrr_at_3_diff1": 0.371023, + "nauc_mrr_at_5_max": 0.195549, + "nauc_mrr_at_5_std": 0.046881, + "nauc_mrr_at_5_diff1": 0.342791, + "nauc_mrr_at_10_max": 0.194554, + "nauc_mrr_at_10_std": 0.057903, + "nauc_mrr_at_10_diff1": 0.302248, + "nauc_mrr_at_20_max": 0.18704, + "nauc_mrr_at_20_std": 0.058098, + "nauc_mrr_at_20_diff1": 0.296185, + "nauc_mrr_at_100_max": 0.180856, + "nauc_mrr_at_100_std": 0.057553, + "nauc_mrr_at_100_diff1": 0.295005, + "nauc_mrr_at_1000_max": 0.182375, + "nauc_mrr_at_1000_std": 0.060743, + "nauc_mrr_at_1000_diff1": 0.295621, + "main_score": 0.07114, + "hf_subset": "MedXpertQA-Exam", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.05932, + "ndcg_at_3": 0.06122, + "ndcg_at_5": 0.07418, + "ndcg_at_10": 0.08418, + "ndcg_at_20": 0.10091, + "ndcg_at_100": 0.13269, + "ndcg_at_1000": 0.19703, + "map_at_1": 0.02246, + "map_at_3": 0.03786, + "map_at_5": 0.05137, + "map_at_10": 0.0567, + "map_at_20": 0.06119, + "map_at_100": 0.06605, + "map_at_1000": 0.06874, + "recall_at_1": 0.02246, + "recall_at_3": 0.05043, + "recall_at_5": 0.08441, + "recall_at_10": 0.10929, + "recall_at_20": 0.15216, + "recall_at_100": 0.26655, + "recall_at_1000": 0.61923, + "precision_at_1": 0.05932, + "precision_at_3": 0.05085, + "precision_at_5": 0.05254, + "precision_at_10": 0.03559, + "precision_at_20": 0.02627, + "precision_at_100": 0.01034, + "precision_at_1000": 0.00251, + "mrr_at_1": 0.059322, + "mrr_at_3": 0.090395, + "mrr_at_5": 0.103531, + "mrr_at_10": 0.108885, + "mrr_at_20": 0.116636, + "mrr_at_100": 0.120728, + "mrr_at_1000": 0.122094, + "nauc_ndcg_at_1_max": 0.443228, + "nauc_ndcg_at_1_std": 0.108221, + "nauc_ndcg_at_1_diff1": 0.462218, + "nauc_ndcg_at_3_max": 0.369109, + "nauc_ndcg_at_3_std": 0.188109, + "nauc_ndcg_at_3_diff1": 0.270551, + "nauc_ndcg_at_5_max": 0.331548, + "nauc_ndcg_at_5_std": 0.169506, + "nauc_ndcg_at_5_diff1": 0.191532, + "nauc_ndcg_at_10_max": 0.270081, + "nauc_ndcg_at_10_std": 0.166027, + "nauc_ndcg_at_10_diff1": 0.151567, + "nauc_ndcg_at_20_max": 0.231882, + "nauc_ndcg_at_20_std": 0.189412, + "nauc_ndcg_at_20_diff1": 0.137941, + "nauc_ndcg_at_100_max": 0.184623, + "nauc_ndcg_at_100_std": 0.201674, + "nauc_ndcg_at_100_diff1": 0.117533, + "nauc_ndcg_at_1000_max": 0.244936, + "nauc_ndcg_at_1000_std": 0.23723, + "nauc_ndcg_at_1000_diff1": 0.171131, + "nauc_map_at_1_max": 0.339208, + "nauc_map_at_1_std": -0.007306, + "nauc_map_at_1_diff1": 0.467771, + "nauc_map_at_3_max": 0.369526, + "nauc_map_at_3_std": 0.10431, + "nauc_map_at_3_diff1": 0.282196, + "nauc_map_at_5_max": 0.372672, + "nauc_map_at_5_std": 0.13531, + "nauc_map_at_5_diff1": 0.197125, + "nauc_map_at_10_max": 0.324274, + "nauc_map_at_10_std": 0.14095, + "nauc_map_at_10_diff1": 0.181697, + "nauc_map_at_20_max": 0.307833, + "nauc_map_at_20_std": 0.150318, + "nauc_map_at_20_diff1": 0.173651, + "nauc_map_at_100_max": 0.288199, + "nauc_map_at_100_std": 0.155442, + "nauc_map_at_100_diff1": 0.161892, + "nauc_map_at_1000_max": 0.290464, + "nauc_map_at_1000_std": 0.160293, + "nauc_map_at_1000_diff1": 0.167977, + "nauc_recall_at_1_max": 0.339208, + "nauc_recall_at_1_std": -0.007306, + "nauc_recall_at_1_diff1": 0.467771, + "nauc_recall_at_3_max": 0.333496, + "nauc_recall_at_3_std": 0.198612, + "nauc_recall_at_3_diff1": 0.149529, + "nauc_recall_at_5_max": 0.285546, + "nauc_recall_at_5_std": 0.168597, + "nauc_recall_at_5_diff1": 0.072311, + "nauc_recall_at_10_max": 0.191568, + "nauc_recall_at_10_std": 0.175728, + "nauc_recall_at_10_diff1": 0.056915, + "nauc_recall_at_20_max": 0.141306, + "nauc_recall_at_20_std": 0.19734, + "nauc_recall_at_20_diff1": 0.046825, + "nauc_recall_at_100_max": 0.070116, + "nauc_recall_at_100_std": 0.209725, + "nauc_recall_at_100_diff1": 0.016384, + "nauc_recall_at_1000_max": 0.290609, + "nauc_recall_at_1000_std": 0.315581, + "nauc_recall_at_1000_diff1": 0.112941, + "nauc_precision_at_1_max": 0.443228, + "nauc_precision_at_1_std": 0.108221, + "nauc_precision_at_1_diff1": 0.462218, + "nauc_precision_at_3_max": 0.386161, + "nauc_precision_at_3_std": 0.274067, + "nauc_precision_at_3_diff1": 0.210307, + "nauc_precision_at_5_max": 0.34457, + "nauc_precision_at_5_std": 0.22293, + "nauc_precision_at_5_diff1": 0.157877, + "nauc_precision_at_10_max": 0.218769, + "nauc_precision_at_10_std": 0.193686, + "nauc_precision_at_10_diff1": 0.102325, + "nauc_precision_at_20_max": 0.127238, + "nauc_precision_at_20_std": 0.258151, + "nauc_precision_at_20_diff1": 0.081294, + "nauc_precision_at_100_max": 0.008038, + "nauc_precision_at_100_std": 0.239747, + "nauc_precision_at_100_diff1": 0.067118, + "nauc_precision_at_1000_max": 0.087487, + "nauc_precision_at_1000_std": 0.228772, + "nauc_precision_at_1000_diff1": 0.223957, + "nauc_mrr_at_1_max": 0.443228, + "nauc_mrr_at_1_std": 0.108221, + "nauc_mrr_at_1_diff1": 0.462218, + "nauc_mrr_at_3_max": 0.358694, + "nauc_mrr_at_3_std": 0.213493, + "nauc_mrr_at_3_diff1": 0.29853, + "nauc_mrr_at_5_max": 0.332151, + "nauc_mrr_at_5_std": 0.193201, + "nauc_mrr_at_5_diff1": 0.28741, + "nauc_mrr_at_10_max": 0.318687, + "nauc_mrr_at_10_std": 0.185631, + "nauc_mrr_at_10_diff1": 0.268011, + "nauc_mrr_at_20_max": 0.296811, + "nauc_mrr_at_20_std": 0.195552, + "nauc_mrr_at_20_diff1": 0.260462, + "nauc_mrr_at_100_max": 0.295686, + "nauc_mrr_at_100_std": 0.192888, + "nauc_mrr_at_100_diff1": 0.263328, + "nauc_mrr_at_1000_max": 0.296683, + "nauc_mrr_at_1000_std": 0.192193, + "nauc_mrr_at_1000_diff1": 0.263413, + "main_score": 0.08418, + "hf_subset": "MedQA-Diag", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.26667, + "ndcg_at_3": 0.2472, + "ndcg_at_5": 0.25623, + "ndcg_at_10": 0.28013, + "ndcg_at_20": 0.29423, + "ndcg_at_100": 0.34146, + "ndcg_at_1000": 0.37884, + "map_at_1": 0.15144, + "map_at_3": 0.20283, + "map_at_5": 0.21379, + "map_at_10": 0.22301, + "map_at_20": 0.22782, + "map_at_100": 0.23532, + "map_at_1000": 0.23716, + "recall_at_1": 0.15144, + "recall_at_3": 0.25022, + "recall_at_5": 0.284, + "recall_at_10": 0.34622, + "recall_at_20": 0.391, + "recall_at_100": 0.60856, + "recall_at_1000": 0.84822, + "precision_at_1": 0.26667, + "precision_at_3": 0.14444, + "precision_at_5": 0.10267, + "precision_at_10": 0.06467, + "precision_at_20": 0.03733, + "precision_at_100": 0.01173, + "precision_at_1000": 0.00173, + "mrr_at_1": 0.266667, + "mrr_at_3": 0.313333, + "mrr_at_5": 0.323667, + "mrr_at_10": 0.334558, + "mrr_at_20": 0.337982, + "mrr_at_100": 0.343224, + "mrr_at_1000": 0.34389, + "nauc_ndcg_at_1_max": 0.281339, + "nauc_ndcg_at_1_std": 0.112831, + "nauc_ndcg_at_1_diff1": 0.548238, + "nauc_ndcg_at_3_max": 0.228996, + "nauc_ndcg_at_3_std": 0.054947, + "nauc_ndcg_at_3_diff1": 0.40894, + "nauc_ndcg_at_5_max": 0.238045, + "nauc_ndcg_at_5_std": 0.065457, + "nauc_ndcg_at_5_diff1": 0.403021, + "nauc_ndcg_at_10_max": 0.228001, + "nauc_ndcg_at_10_std": 0.059981, + "nauc_ndcg_at_10_diff1": 0.37186, + "nauc_ndcg_at_20_max": 0.21512, + "nauc_ndcg_at_20_std": 0.078426, + "nauc_ndcg_at_20_diff1": 0.353212, + "nauc_ndcg_at_100_max": 0.216281, + "nauc_ndcg_at_100_std": 0.071564, + "nauc_ndcg_at_100_diff1": 0.362019, + "nauc_ndcg_at_1000_max": 0.227835, + "nauc_ndcg_at_1000_std": 0.087818, + "nauc_ndcg_at_1000_diff1": 0.38461, + "nauc_map_at_1_max": 0.193079, + "nauc_map_at_1_std": 0.027944, + "nauc_map_at_1_diff1": 0.523967, + "nauc_map_at_3_max": 0.215557, + "nauc_map_at_3_std": 0.032294, + "nauc_map_at_3_diff1": 0.421018, + "nauc_map_at_5_max": 0.232669, + "nauc_map_at_5_std": 0.038448, + "nauc_map_at_5_diff1": 0.427076, + "nauc_map_at_10_max": 0.229461, + "nauc_map_at_10_std": 0.037667, + "nauc_map_at_10_diff1": 0.414342, + "nauc_map_at_20_max": 0.227058, + "nauc_map_at_20_std": 0.045529, + "nauc_map_at_20_diff1": 0.408251, + "nauc_map_at_100_max": 0.225852, + "nauc_map_at_100_std": 0.045207, + "nauc_map_at_100_diff1": 0.412351, + "nauc_map_at_1000_max": 0.226634, + "nauc_map_at_1000_std": 0.04624, + "nauc_map_at_1000_diff1": 0.413267, + "nauc_recall_at_1_max": 0.193079, + "nauc_recall_at_1_std": 0.027944, + "nauc_recall_at_1_diff1": 0.523967, + "nauc_recall_at_3_max": 0.15684, + "nauc_recall_at_3_std": 0.0424, + "nauc_recall_at_3_diff1": 0.275401, + "nauc_recall_at_5_max": 0.180967, + "nauc_recall_at_5_std": 0.067213, + "nauc_recall_at_5_diff1": 0.269327, + "nauc_recall_at_10_max": 0.14117, + "nauc_recall_at_10_std": 0.045991, + "nauc_recall_at_10_diff1": 0.178763, + "nauc_recall_at_20_max": 0.091465, + "nauc_recall_at_20_std": 0.097578, + "nauc_recall_at_20_diff1": 0.115724, + "nauc_recall_at_100_max": 0.072797, + "nauc_recall_at_100_std": 0.074713, + "nauc_recall_at_100_diff1": 0.059268, + "nauc_recall_at_1000_max": 0.116349, + "nauc_recall_at_1000_std": 0.263464, + "nauc_recall_at_1000_diff1": 0.15978, + "nauc_precision_at_1_max": 0.281339, + "nauc_precision_at_1_std": 0.112831, + "nauc_precision_at_1_diff1": 0.548238, + "nauc_precision_at_3_max": 0.30985, + "nauc_precision_at_3_std": 0.090178, + "nauc_precision_at_3_diff1": 0.364699, + "nauc_precision_at_5_max": 0.326686, + "nauc_precision_at_5_std": 0.09426, + "nauc_precision_at_5_diff1": 0.347958, + "nauc_precision_at_10_max": 0.279868, + "nauc_precision_at_10_std": 0.087556, + "nauc_precision_at_10_diff1": 0.249015, + "nauc_precision_at_20_max": 0.244083, + "nauc_precision_at_20_std": 0.139233, + "nauc_precision_at_20_diff1": 0.176781, + "nauc_precision_at_100_max": 0.177367, + "nauc_precision_at_100_std": 0.06617, + "nauc_precision_at_100_diff1": 0.114051, + "nauc_precision_at_1000_max": 0.14515, + "nauc_precision_at_1000_std": 0.096151, + "nauc_precision_at_1000_diff1": 0.073368, + "nauc_mrr_at_1_max": 0.281339, + "nauc_mrr_at_1_std": 0.112831, + "nauc_mrr_at_1_diff1": 0.548238, + "nauc_mrr_at_3_max": 0.275725, + "nauc_mrr_at_3_std": 0.103991, + "nauc_mrr_at_3_diff1": 0.477372, + "nauc_mrr_at_5_max": 0.28205, + "nauc_mrr_at_5_std": 0.113645, + "nauc_mrr_at_5_diff1": 0.470085, + "nauc_mrr_at_10_max": 0.276661, + "nauc_mrr_at_10_std": 0.105706, + "nauc_mrr_at_10_diff1": 0.456581, + "nauc_mrr_at_20_max": 0.271526, + "nauc_mrr_at_20_std": 0.107687, + "nauc_mrr_at_20_diff1": 0.452819, + "nauc_mrr_at_100_max": 0.271576, + "nauc_mrr_at_100_std": 0.106782, + "nauc_mrr_at_100_diff1": 0.45583, + "nauc_mrr_at_1000_max": 0.271798, + "nauc_mrr_at_1000_std": 0.107113, + "nauc_mrr_at_1000_diff1": 0.456689, + "main_score": 0.28013, + "hf_subset": "PMC-Treatment", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.14035, + "ndcg_at_3": 0.12477, + "ndcg_at_5": 0.1495, + "ndcg_at_10": 0.19325, + "ndcg_at_20": 0.21992, + "ndcg_at_100": 0.26856, + "ndcg_at_1000": 0.31022, + "map_at_1": 0.05556, + "map_at_3": 0.09491, + "map_at_5": 0.10927, + "map_at_10": 0.1281, + "map_at_20": 0.13597, + "map_at_100": 0.14438, + "map_at_1000": 0.14623, + "recall_at_1": 0.05556, + "recall_at_3": 0.125, + "recall_at_5": 0.18421, + "recall_at_10": 0.29459, + "recall_at_20": 0.3867, + "recall_at_100": 0.60088, + "recall_at_1000": 0.87281, + "precision_at_1": 0.14035, + "precision_at_3": 0.09357, + "precision_at_5": 0.07544, + "precision_at_10": 0.06228, + "precision_at_20": 0.03904, + "precision_at_100": 0.01263, + "precision_at_1000": 0.00188, + "mrr_at_1": 0.140351, + "mrr_at_3": 0.181287, + "mrr_at_5": 0.196199, + "mrr_at_10": 0.216736, + "mrr_at_20": 0.223753, + "mrr_at_100": 0.228224, + "mrr_at_1000": 0.229093, + "nauc_ndcg_at_1_max": 0.196868, + "nauc_ndcg_at_1_std": -0.060522, + "nauc_ndcg_at_1_diff1": 0.28548, + "nauc_ndcg_at_3_max": 0.203125, + "nauc_ndcg_at_3_std": -0.018665, + "nauc_ndcg_at_3_diff1": 0.271464, + "nauc_ndcg_at_5_max": 0.203055, + "nauc_ndcg_at_5_std": 0.055679, + "nauc_ndcg_at_5_diff1": 0.258571, + "nauc_ndcg_at_10_max": 0.149122, + "nauc_ndcg_at_10_std": 0.01771, + "nauc_ndcg_at_10_diff1": 0.242153, + "nauc_ndcg_at_20_max": 0.14683, + "nauc_ndcg_at_20_std": -0.000291, + "nauc_ndcg_at_20_diff1": 0.247559, + "nauc_ndcg_at_100_max": 0.159286, + "nauc_ndcg_at_100_std": 0.061633, + "nauc_ndcg_at_100_diff1": 0.219037, + "nauc_ndcg_at_1000_max": 0.170965, + "nauc_ndcg_at_1000_std": 0.031165, + "nauc_ndcg_at_1000_diff1": 0.247762, + "nauc_map_at_1_max": 0.21816, + "nauc_map_at_1_std": -0.015179, + "nauc_map_at_1_diff1": 0.25682, + "nauc_map_at_3_max": 0.195694, + "nauc_map_at_3_std": 0.003665, + "nauc_map_at_3_diff1": 0.260932, + "nauc_map_at_5_max": 0.195897, + "nauc_map_at_5_std": 0.05299, + "nauc_map_at_5_diff1": 0.262108, + "nauc_map_at_10_max": 0.165572, + "nauc_map_at_10_std": 0.028914, + "nauc_map_at_10_diff1": 0.252577, + "nauc_map_at_20_max": 0.166772, + "nauc_map_at_20_std": 0.023052, + "nauc_map_at_20_diff1": 0.261039, + "nauc_map_at_100_max": 0.173614, + "nauc_map_at_100_std": 0.041586, + "nauc_map_at_100_diff1": 0.25519, + "nauc_map_at_1000_max": 0.174495, + "nauc_map_at_1000_std": 0.04066, + "nauc_map_at_1000_diff1": 0.255391, + "nauc_recall_at_1_max": 0.21816, + "nauc_recall_at_1_std": -0.015179, + "nauc_recall_at_1_diff1": 0.25682, + "nauc_recall_at_3_max": 0.189566, + "nauc_recall_at_3_std": -0.009928, + "nauc_recall_at_3_diff1": 0.247792, + "nauc_recall_at_5_max": 0.184491, + "nauc_recall_at_5_std": 0.142921, + "nauc_recall_at_5_diff1": 0.200947, + "nauc_recall_at_10_max": 0.061803, + "nauc_recall_at_10_std": 0.039311, + "nauc_recall_at_10_diff1": 0.168685, + "nauc_recall_at_20_max": 0.046938, + "nauc_recall_at_20_std": -0.005264, + "nauc_recall_at_20_diff1": 0.160785, + "nauc_recall_at_100_max": 0.059117, + "nauc_recall_at_100_std": 0.167608, + "nauc_recall_at_100_diff1": 0.075851, + "nauc_recall_at_1000_max": 0.018709, + "nauc_recall_at_1000_std": 0.03867, + "nauc_recall_at_1000_diff1": 0.269118, + "nauc_precision_at_1_max": 0.196868, + "nauc_precision_at_1_std": -0.060522, + "nauc_precision_at_1_diff1": 0.28548, + "nauc_precision_at_3_max": 0.202979, + "nauc_precision_at_3_std": -0.071167, + "nauc_precision_at_3_diff1": 0.253038, + "nauc_precision_at_5_max": 0.182732, + "nauc_precision_at_5_std": 0.021602, + "nauc_precision_at_5_diff1": 0.254766, + "nauc_precision_at_10_max": 0.101818, + "nauc_precision_at_10_std": -0.025537, + "nauc_precision_at_10_diff1": 0.225605, + "nauc_precision_at_20_max": 0.109179, + "nauc_precision_at_20_std": -0.064906, + "nauc_precision_at_20_diff1": 0.238651, + "nauc_precision_at_100_max": 0.091905, + "nauc_precision_at_100_std": 0.089219, + "nauc_precision_at_100_diff1": 0.055718, + "nauc_precision_at_1000_max": 0.102379, + "nauc_precision_at_1000_std": -0.071679, + "nauc_precision_at_1000_diff1": 0.084809, + "nauc_mrr_at_1_max": 0.196868, + "nauc_mrr_at_1_std": -0.060522, + "nauc_mrr_at_1_diff1": 0.28548, + "nauc_mrr_at_3_max": 0.216587, + "nauc_mrr_at_3_std": -0.044465, + "nauc_mrr_at_3_diff1": 0.294406, + "nauc_mrr_at_5_max": 0.212945, + "nauc_mrr_at_5_std": -0.018901, + "nauc_mrr_at_5_diff1": 0.281591, + "nauc_mrr_at_10_max": 0.201823, + "nauc_mrr_at_10_std": -0.020223, + "nauc_mrr_at_10_diff1": 0.279781, + "nauc_mrr_at_20_max": 0.19964, + "nauc_mrr_at_20_std": -0.025284, + "nauc_mrr_at_20_diff1": 0.273666, + "nauc_mrr_at_100_max": 0.200772, + "nauc_mrr_at_100_std": -0.019468, + "nauc_mrr_at_100_diff1": 0.273269, + "nauc_mrr_at_1000_max": 0.20131, + "nauc_mrr_at_1000_std": -0.019933, + "nauc_mrr_at_1000_diff1": 0.27422, + "main_score": 0.19325, + "hf_subset": "PMC-Clinical", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.1938, + "ndcg_at_3": 0.16508, + "ndcg_at_5": 0.16293, + "ndcg_at_10": 0.19801, + "ndcg_at_20": 0.2367, + "ndcg_at_100": 0.32333, + "ndcg_at_1000": 0.37827, + "map_at_1": 0.05271, + "map_at_3": 0.0949, + "map_at_5": 0.1057, + "map_at_10": 0.12431, + "map_at_20": 0.13801, + "map_at_100": 0.1566, + "map_at_1000": 0.16038, + "recall_at_1": 0.05271, + "recall_at_3": 0.12455, + "recall_at_5": 0.15801, + "recall_at_10": 0.24522, + "recall_at_20": 0.34871, + "recall_at_100": 0.66783, + "recall_at_1000": 0.9668, + "precision_at_1": 0.1938, + "precision_at_3": 0.1447, + "precision_at_5": 0.11473, + "precision_at_10": 0.08605, + "precision_at_20": 0.06163, + "precision_at_100": 0.02419, + "precision_at_1000": 0.00345, + "mrr_at_1": 0.193798, + "mrr_at_3": 0.257106, + "mrr_at_5": 0.272222, + "mrr_at_10": 0.285594, + "mrr_at_20": 0.293396, + "mrr_at_100": 0.299216, + "mrr_at_1000": 0.300006, + "nauc_ndcg_at_1_max": 0.114439, + "nauc_ndcg_at_1_std": 0.135854, + "nauc_ndcg_at_1_diff1": 0.075416, + "nauc_ndcg_at_3_max": 0.13779, + "nauc_ndcg_at_3_std": 0.14564, + "nauc_ndcg_at_3_diff1": -0.036377, + "nauc_ndcg_at_5_max": 0.128136, + "nauc_ndcg_at_5_std": 0.161314, + "nauc_ndcg_at_5_diff1": -0.00503, + "nauc_ndcg_at_10_max": 0.157634, + "nauc_ndcg_at_10_std": 0.176912, + "nauc_ndcg_at_10_diff1": -0.001486, + "nauc_ndcg_at_20_max": 0.192848, + "nauc_ndcg_at_20_std": 0.20811, + "nauc_ndcg_at_20_diff1": 0.014289, + "nauc_ndcg_at_100_max": 0.206255, + "nauc_ndcg_at_100_std": 0.306581, + "nauc_ndcg_at_100_diff1": 0.012309, + "nauc_ndcg_at_1000_max": 0.16706, + "nauc_ndcg_at_1000_std": 0.295984, + "nauc_ndcg_at_1000_diff1": -0.020756, + "nauc_map_at_1_max": 0.050398, + "nauc_map_at_1_std": 0.110866, + "nauc_map_at_1_diff1": 0.139311, + "nauc_map_at_3_max": 0.086987, + "nauc_map_at_3_std": 0.16339, + "nauc_map_at_3_diff1": 0.075563, + "nauc_map_at_5_max": 0.098082, + "nauc_map_at_5_std": 0.171908, + "nauc_map_at_5_diff1": 0.059806, + "nauc_map_at_10_max": 0.109997, + "nauc_map_at_10_std": 0.172342, + "nauc_map_at_10_diff1": 0.058058, + "nauc_map_at_20_max": 0.130452, + "nauc_map_at_20_std": 0.196854, + "nauc_map_at_20_diff1": 0.056736, + "nauc_map_at_100_max": 0.141123, + "nauc_map_at_100_std": 0.234824, + "nauc_map_at_100_diff1": 0.052762, + "nauc_map_at_1000_max": 0.138495, + "nauc_map_at_1000_std": 0.236201, + "nauc_map_at_1000_diff1": 0.049426, + "nauc_recall_at_1_max": 0.050398, + "nauc_recall_at_1_std": 0.110866, + "nauc_recall_at_1_diff1": 0.139311, + "nauc_recall_at_3_max": 0.055406, + "nauc_recall_at_3_std": 0.125852, + "nauc_recall_at_3_diff1": -0.023699, + "nauc_recall_at_5_max": 0.112079, + "nauc_recall_at_5_std": 0.141666, + "nauc_recall_at_5_diff1": -0.018006, + "nauc_recall_at_10_max": 0.144586, + "nauc_recall_at_10_std": 0.134685, + "nauc_recall_at_10_diff1": 0.002281, + "nauc_recall_at_20_max": 0.189161, + "nauc_recall_at_20_std": 0.16859, + "nauc_recall_at_20_diff1": 0.039835, + "nauc_recall_at_100_max": 0.236813, + "nauc_recall_at_100_std": 0.368073, + "nauc_recall_at_100_diff1": 0.044245, + "nauc_recall_at_1000_max": -0.329618, + "nauc_recall_at_1000_std": 0.812951, + "nauc_recall_at_1000_diff1": -0.42288, + "nauc_precision_at_1_max": 0.114439, + "nauc_precision_at_1_std": 0.135854, + "nauc_precision_at_1_diff1": 0.075416, + "nauc_precision_at_3_max": 0.187798, + "nauc_precision_at_3_std": 0.174948, + "nauc_precision_at_3_diff1": -0.101214, + "nauc_precision_at_5_max": 0.205685, + "nauc_precision_at_5_std": 0.197829, + "nauc_precision_at_5_diff1": -0.102037, + "nauc_precision_at_10_max": 0.236374, + "nauc_precision_at_10_std": 0.225802, + "nauc_precision_at_10_diff1": -0.092693, + "nauc_precision_at_20_max": 0.303657, + "nauc_precision_at_20_std": 0.287183, + "nauc_precision_at_20_diff1": -0.037982, + "nauc_precision_at_100_max": 0.225952, + "nauc_precision_at_100_std": 0.438736, + "nauc_precision_at_100_diff1": -0.035707, + "nauc_precision_at_1000_max": 0.088753, + "nauc_precision_at_1000_std": 0.360182, + "nauc_precision_at_1000_diff1": -0.163425, + "nauc_mrr_at_1_max": 0.114439, + "nauc_mrr_at_1_std": 0.135854, + "nauc_mrr_at_1_diff1": 0.075416, + "nauc_mrr_at_3_max": 0.129894, + "nauc_mrr_at_3_std": 0.128145, + "nauc_mrr_at_3_diff1": -0.061409, + "nauc_mrr_at_5_max": 0.147243, + "nauc_mrr_at_5_std": 0.135105, + "nauc_mrr_at_5_diff1": -0.049866, + "nauc_mrr_at_10_max": 0.166409, + "nauc_mrr_at_10_std": 0.161761, + "nauc_mrr_at_10_diff1": -0.048188, + "nauc_mrr_at_20_max": 0.166619, + "nauc_mrr_at_20_std": 0.156699, + "nauc_mrr_at_20_diff1": -0.043644, + "nauc_mrr_at_100_max": 0.160674, + "nauc_mrr_at_100_std": 0.158944, + "nauc_mrr_at_100_diff1": -0.042866, + "nauc_mrr_at_1000_max": 0.160283, + "nauc_mrr_at_1000_std": 0.157851, + "nauc_mrr_at_1000_diff1": -0.042873, + "main_score": 0.19801, + "hf_subset": "IIYi-Clinical", + "languages": [ + "eng-Latn" + ] + } + ] + }, + "evaluation_time": 550.9791347980499, + "kg_co2_emissions": null +} \ No newline at end of file diff --git a/results/Salesforce__SFR-Embedding-2_R/91762139d94ed4371a9fa31db5551272e0b83818/R2MEDRetrieval.json b/results/Salesforce__SFR-Embedding-2_R/91762139d94ed4371a9fa31db5551272e0b83818/R2MEDRetrieval.json new file mode 100644 index 0000000000..9a77c51aef --- /dev/null +++ b/results/Salesforce__SFR-Embedding-2_R/91762139d94ed4371a9fa31db5551272e0b83818/R2MEDRetrieval.json @@ -0,0 +1,1187 @@ +{ + "dataset_revision": "1.0", + "task_name": "R2MEDRetrieval", + "mteb_version": "1.38.20", + "scores": { + "test": [ + { + "ndcg_at_1": 0.18447, + "ndcg_at_3": 0.17527, + "ndcg_at_5": 0.19124, + "ndcg_at_10": 0.22112, + "ndcg_at_20": 0.25214, + "ndcg_at_100": 0.31051, + "ndcg_at_1000": 0.36754, + "map_at_1": 0.05779, + "map_at_3": 0.10375, + "map_at_5": 0.12703, + "map_at_10": 0.15388, + "map_at_20": 0.16759, + "map_at_100": 0.1799, + "map_at_1000": 0.18297, + "recall_at_1": 0.05779, + "recall_at_3": 0.13296, + "recall_at_5": 0.18871, + "recall_at_10": 0.27353, + "recall_at_20": 0.355, + "recall_at_100": 0.57108, + "recall_at_1000": 0.90189, + "precision_at_1": 0.18447, + "precision_at_3": 0.1521, + "precision_at_5": 0.13592, + "precision_at_10": 0.10291, + "precision_at_20": 0.06893, + "precision_at_100": 0.02223, + "precision_at_1000": 0.0033, + "mrr_at_1": 0.184466, + "mrr_at_3": 0.247573, + "mrr_at_5": 0.260194, + "mrr_at_10": 0.270912, + "mrr_at_20": 0.277138, + "mrr_at_100": 0.281493, + "mrr_at_1000": 0.28254, + "nauc_ndcg_at_1_max": 0.116386, + "nauc_ndcg_at_1_std": -0.182271, + "nauc_ndcg_at_1_diff1": 0.287297, + "nauc_ndcg_at_3_max": 0.049671, + "nauc_ndcg_at_3_std": -0.206207, + "nauc_ndcg_at_3_diff1": 0.294058, + "nauc_ndcg_at_5_max": 0.011981, + "nauc_ndcg_at_5_std": -0.247854, + "nauc_ndcg_at_5_diff1": 0.323107, + "nauc_ndcg_at_10_max": 0.008012, + "nauc_ndcg_at_10_std": -0.249695, + "nauc_ndcg_at_10_diff1": 0.306702, + "nauc_ndcg_at_20_max": -0.042699, + "nauc_ndcg_at_20_std": -0.27202, + "nauc_ndcg_at_20_diff1": 0.275755, + "nauc_ndcg_at_100_max": -0.031603, + "nauc_ndcg_at_100_std": -0.259641, + "nauc_ndcg_at_100_diff1": 0.259099, + "nauc_ndcg_at_1000_max": -0.01656, + "nauc_ndcg_at_1000_std": -0.242126, + "nauc_ndcg_at_1000_diff1": 0.248285, + "nauc_map_at_1_max": 0.147091, + "nauc_map_at_1_std": -0.138244, + "nauc_map_at_1_diff1": 0.320137, + "nauc_map_at_3_max": 0.087797, + "nauc_map_at_3_std": -0.179271, + "nauc_map_at_3_diff1": 0.343363, + "nauc_map_at_5_max": 0.061845, + "nauc_map_at_5_std": -0.220794, + "nauc_map_at_5_diff1": 0.380058, + "nauc_map_at_10_max": 0.045658, + "nauc_map_at_10_std": -0.230808, + "nauc_map_at_10_diff1": 0.37648, + "nauc_map_at_20_max": 0.016885, + "nauc_map_at_20_std": -0.245501, + "nauc_map_at_20_diff1": 0.362126, + "nauc_map_at_100_max": 0.01849, + "nauc_map_at_100_std": -0.241899, + "nauc_map_at_100_diff1": 0.352138, + "nauc_map_at_1000_max": 0.019305, + "nauc_map_at_1000_std": -0.241182, + "nauc_map_at_1000_diff1": 0.349642, + "nauc_recall_at_1_max": 0.147091, + "nauc_recall_at_1_std": -0.138244, + "nauc_recall_at_1_diff1": 0.320137, + "nauc_recall_at_3_max": 0.042717, + "nauc_recall_at_3_std": -0.195132, + "nauc_recall_at_3_diff1": 0.276032, + "nauc_recall_at_5_max": 0.005231, + "nauc_recall_at_5_std": -0.239437, + "nauc_recall_at_5_diff1": 0.331972, + "nauc_recall_at_10_max": -0.034236, + "nauc_recall_at_10_std": -0.255839, + "nauc_recall_at_10_diff1": 0.268552, + "nauc_recall_at_20_max": -0.137382, + "nauc_recall_at_20_std": -0.288684, + "nauc_recall_at_20_diff1": 0.196753, + "nauc_recall_at_100_max": -0.072314, + "nauc_recall_at_100_std": -0.247831, + "nauc_recall_at_100_diff1": 0.202624, + "nauc_recall_at_1000_max": -0.060788, + "nauc_recall_at_1000_std": -0.042958, + "nauc_recall_at_1000_diff1": 0.112057, + "nauc_precision_at_1_max": 0.116386, + "nauc_precision_at_1_std": -0.182271, + "nauc_precision_at_1_diff1": 0.287297, + "nauc_precision_at_3_max": 0.019075, + "nauc_precision_at_3_std": -0.228197, + "nauc_precision_at_3_diff1": 0.306642, + "nauc_precision_at_5_max": -0.037968, + "nauc_precision_at_5_std": -0.269894, + "nauc_precision_at_5_diff1": 0.295333, + "nauc_precision_at_10_max": -0.074611, + "nauc_precision_at_10_std": -0.292046, + "nauc_precision_at_10_diff1": 0.23851, + "nauc_precision_at_20_max": -0.165737, + "nauc_precision_at_20_std": -0.312131, + "nauc_precision_at_20_diff1": 0.141901, + "nauc_precision_at_100_max": -0.182645, + "nauc_precision_at_100_std": -0.252293, + "nauc_precision_at_100_diff1": 0.002874, + "nauc_precision_at_1000_max": -0.170671, + "nauc_precision_at_1000_std": -0.186155, + "nauc_precision_at_1000_diff1": -0.132087, + "nauc_mrr_at_1_max": 0.116386, + "nauc_mrr_at_1_std": -0.182271, + "nauc_mrr_at_1_diff1": 0.287297, + "nauc_mrr_at_3_max": 0.073893, + "nauc_mrr_at_3_std": -0.196117, + "nauc_mrr_at_3_diff1": 0.243636, + "nauc_mrr_at_5_max": 0.060251, + "nauc_mrr_at_5_std": -0.198362, + "nauc_mrr_at_5_diff1": 0.25338, + "nauc_mrr_at_10_max": 0.050737, + "nauc_mrr_at_10_std": -0.211005, + "nauc_mrr_at_10_diff1": 0.232874, + "nauc_mrr_at_20_max": 0.038864, + "nauc_mrr_at_20_std": -0.21875, + "nauc_mrr_at_20_diff1": 0.224909, + "nauc_mrr_at_100_max": 0.041611, + "nauc_mrr_at_100_std": -0.217334, + "nauc_mrr_at_100_diff1": 0.229154, + "nauc_mrr_at_1000_max": 0.043175, + "nauc_mrr_at_1000_std": -0.216416, + "nauc_mrr_at_1000_diff1": 0.229244, + "main_score": 0.22112, + "hf_subset": "Biology", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.38961, + "ndcg_at_3": 0.41235, + "ndcg_at_5": 0.44392, + "ndcg_at_10": 0.48655, + "ndcg_at_20": 0.52089, + "ndcg_at_100": 0.57485, + "ndcg_at_1000": 0.58654, + "map_at_1": 0.19258, + "map_at_3": 0.30669, + "map_at_5": 0.35538, + "map_at_10": 0.3871, + "map_at_20": 0.40444, + "map_at_100": 0.41992, + "map_at_1000": 0.42072, + "recall_at_1": 0.19258, + "recall_at_3": 0.37973, + "recall_at_5": 0.50272, + "recall_at_10": 0.6258, + "recall_at_20": 0.7145, + "recall_at_100": 0.91674, + "recall_at_1000": 0.98083, + "precision_at_1": 0.38961, + "precision_at_3": 0.29437, + "precision_at_5": 0.23636, + "precision_at_10": 0.15974, + "precision_at_20": 0.09805, + "precision_at_100": 0.02675, + "precision_at_1000": 0.00291, + "mrr_at_1": 0.38961, + "mrr_at_3": 0.480519, + "mrr_at_5": 0.501948, + "mrr_at_10": 0.515636, + "mrr_at_20": 0.51835, + "mrr_at_100": 0.521431, + "mrr_at_1000": 0.52167, + "nauc_ndcg_at_1_max": 0.009762, + "nauc_ndcg_at_1_std": -0.02234, + "nauc_ndcg_at_1_diff1": 0.044845, + "nauc_ndcg_at_3_max": 0.033503, + "nauc_ndcg_at_3_std": -0.084173, + "nauc_ndcg_at_3_diff1": 0.098786, + "nauc_ndcg_at_5_max": 0.128874, + "nauc_ndcg_at_5_std": -0.114573, + "nauc_ndcg_at_5_diff1": 0.192554, + "nauc_ndcg_at_10_max": 0.1428, + "nauc_ndcg_at_10_std": -0.08994, + "nauc_ndcg_at_10_diff1": 0.173611, + "nauc_ndcg_at_20_max": 0.150406, + "nauc_ndcg_at_20_std": -0.093771, + "nauc_ndcg_at_20_diff1": 0.134506, + "nauc_ndcg_at_100_max": 0.114404, + "nauc_ndcg_at_100_std": -0.061728, + "nauc_ndcg_at_100_diff1": 0.099582, + "nauc_ndcg_at_1000_max": 0.11154, + "nauc_ndcg_at_1000_std": -0.065739, + "nauc_ndcg_at_1000_diff1": 0.100912, + "nauc_map_at_1_max": -0.062917, + "nauc_map_at_1_std": -0.082236, + "nauc_map_at_1_diff1": 0.188435, + "nauc_map_at_3_max": 0.022475, + "nauc_map_at_3_std": -0.100189, + "nauc_map_at_3_diff1": 0.172096, + "nauc_map_at_5_max": 0.110505, + "nauc_map_at_5_std": -0.108405, + "nauc_map_at_5_diff1": 0.223792, + "nauc_map_at_10_max": 0.104654, + "nauc_map_at_10_std": -0.108569, + "nauc_map_at_10_diff1": 0.207034, + "nauc_map_at_20_max": 0.10832, + "nauc_map_at_20_std": -0.114956, + "nauc_map_at_20_diff1": 0.183718, + "nauc_map_at_100_max": 0.100521, + "nauc_map_at_100_std": -0.105174, + "nauc_map_at_100_diff1": 0.16881, + "nauc_map_at_1000_max": 0.099985, + "nauc_map_at_1000_std": -0.10531, + "nauc_map_at_1000_diff1": 0.168308, + "nauc_recall_at_1_max": -0.062917, + "nauc_recall_at_1_std": -0.082236, + "nauc_recall_at_1_diff1": 0.188435, + "nauc_recall_at_3_max": 0.050582, + "nauc_recall_at_3_std": -0.144184, + "nauc_recall_at_3_diff1": 0.159858, + "nauc_recall_at_5_max": 0.24295, + "nauc_recall_at_5_std": -0.158944, + "nauc_recall_at_5_diff1": 0.276873, + "nauc_recall_at_10_max": 0.26211, + "nauc_recall_at_10_std": -0.062708, + "nauc_recall_at_10_diff1": 0.253082, + "nauc_recall_at_20_max": 0.299862, + "nauc_recall_at_20_std": -0.083643, + "nauc_recall_at_20_diff1": 0.182142, + "nauc_recall_at_100_max": 0.178387, + "nauc_recall_at_100_std": 0.12399, + "nauc_recall_at_100_diff1": 0.123328, + "nauc_recall_at_1000_max": -0.321321, + "nauc_recall_at_1000_std": -0.144707, + "nauc_recall_at_1000_diff1": -0.053992, + "nauc_precision_at_1_max": 0.009762, + "nauc_precision_at_1_std": -0.02234, + "nauc_precision_at_1_diff1": 0.044845, + "nauc_precision_at_3_max": 0.096393, + "nauc_precision_at_3_std": -0.052822, + "nauc_precision_at_3_diff1": -0.001057, + "nauc_precision_at_5_max": 0.206021, + "nauc_precision_at_5_std": -0.060449, + "nauc_precision_at_5_diff1": 0.04605, + "nauc_precision_at_10_max": 0.125038, + "nauc_precision_at_10_std": -0.013316, + "nauc_precision_at_10_diff1": -0.066664, + "nauc_precision_at_20_max": 0.11797, + "nauc_precision_at_20_std": 0.001186, + "nauc_precision_at_20_diff1": -0.165704, + "nauc_precision_at_100_max": -0.007827, + "nauc_precision_at_100_std": 0.081874, + "nauc_precision_at_100_diff1": -0.241877, + "nauc_precision_at_1000_max": 0.018207, + "nauc_precision_at_1000_std": 0.120618, + "nauc_precision_at_1000_diff1": -0.207064, + "nauc_mrr_at_1_max": 0.009762, + "nauc_mrr_at_1_std": -0.02234, + "nauc_mrr_at_1_diff1": 0.044845, + "nauc_mrr_at_3_max": 0.065116, + "nauc_mrr_at_3_std": -0.027081, + "nauc_mrr_at_3_diff1": 0.037305, + "nauc_mrr_at_5_max": 0.092019, + "nauc_mrr_at_5_std": -0.026855, + "nauc_mrr_at_5_diff1": 0.041456, + "nauc_mrr_at_10_max": 0.085075, + "nauc_mrr_at_10_std": -0.019784, + "nauc_mrr_at_10_diff1": 0.032202, + "nauc_mrr_at_20_max": 0.087526, + "nauc_mrr_at_20_std": -0.016706, + "nauc_mrr_at_20_diff1": 0.034878, + "nauc_mrr_at_100_max": 0.084823, + "nauc_mrr_at_100_std": -0.014472, + "nauc_mrr_at_100_diff1": 0.034415, + "nauc_mrr_at_1000_max": 0.084989, + "nauc_mrr_at_1000_std": -0.014549, + "nauc_mrr_at_1000_diff1": 0.034666, + "main_score": 0.48655, + "hf_subset": "Bioinformatics", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.31818, + "ndcg_at_3": 0.37593, + "ndcg_at_5": 0.39631, + "ndcg_at_10": 0.458, + "ndcg_at_20": 0.49889, + "ndcg_at_100": 0.54766, + "ndcg_at_1000": 0.56235, + "map_at_1": 0.19802, + "map_at_3": 0.30674, + "map_at_5": 0.32851, + "map_at_10": 0.36076, + "map_at_20": 0.37963, + "map_at_100": 0.3925, + "map_at_1000": 0.39382, + "recall_at_1": 0.19802, + "recall_at_3": 0.38983, + "recall_at_5": 0.45016, + "recall_at_10": 0.60747, + "recall_at_20": 0.71695, + "recall_at_100": 0.8936, + "recall_at_1000": 0.97017, + "precision_at_1": 0.31818, + "precision_at_3": 0.25, + "precision_at_5": 0.18864, + "precision_at_10": 0.13636, + "precision_at_20": 0.0875, + "precision_at_100": 0.0242, + "precision_at_1000": 0.00272, + "mrr_at_1": 0.318182, + "mrr_at_3": 0.418561, + "mrr_at_5": 0.444129, + "mrr_at_10": 0.469922, + "mrr_at_20": 0.474314, + "mrr_at_100": 0.475563, + "mrr_at_1000": 0.475692, + "nauc_ndcg_at_1_max": 0.248292, + "nauc_ndcg_at_1_std": 0.101909, + "nauc_ndcg_at_1_diff1": 0.065065, + "nauc_ndcg_at_3_max": 0.366767, + "nauc_ndcg_at_3_std": 0.062784, + "nauc_ndcg_at_3_diff1": 0.168717, + "nauc_ndcg_at_5_max": 0.316035, + "nauc_ndcg_at_5_std": 0.003251, + "nauc_ndcg_at_5_diff1": 0.227304, + "nauc_ndcg_at_10_max": 0.348186, + "nauc_ndcg_at_10_std": -0.010666, + "nauc_ndcg_at_10_diff1": 0.222295, + "nauc_ndcg_at_20_max": 0.345301, + "nauc_ndcg_at_20_std": -0.022709, + "nauc_ndcg_at_20_diff1": 0.18887, + "nauc_ndcg_at_100_max": 0.330936, + "nauc_ndcg_at_100_std": 0.029318, + "nauc_ndcg_at_100_diff1": 0.163865, + "nauc_ndcg_at_1000_max": 0.321536, + "nauc_ndcg_at_1000_std": 0.043373, + "nauc_ndcg_at_1000_diff1": 0.155376, + "nauc_map_at_1_max": 0.064422, + "nauc_map_at_1_std": -0.109003, + "nauc_map_at_1_diff1": 0.220761, + "nauc_map_at_3_max": 0.289976, + "nauc_map_at_3_std": -0.00289, + "nauc_map_at_3_diff1": 0.190792, + "nauc_map_at_5_max": 0.269063, + "nauc_map_at_5_std": -0.014795, + "nauc_map_at_5_diff1": 0.214251, + "nauc_map_at_10_max": 0.288075, + "nauc_map_at_10_std": -0.015879, + "nauc_map_at_10_diff1": 0.208987, + "nauc_map_at_20_max": 0.29571, + "nauc_map_at_20_std": -0.019544, + "nauc_map_at_20_diff1": 0.194129, + "nauc_map_at_100_max": 0.291657, + "nauc_map_at_100_std": -0.008117, + "nauc_map_at_100_diff1": 0.18869, + "nauc_map_at_1000_max": 0.291123, + "nauc_map_at_1000_std": -0.007329, + "nauc_map_at_1000_diff1": 0.187302, + "nauc_recall_at_1_max": 0.064422, + "nauc_recall_at_1_std": -0.109003, + "nauc_recall_at_1_diff1": 0.220761, + "nauc_recall_at_3_max": 0.383209, + "nauc_recall_at_3_std": -0.03075, + "nauc_recall_at_3_diff1": 0.251694, + "nauc_recall_at_5_max": 0.326659, + "nauc_recall_at_5_std": -0.076496, + "nauc_recall_at_5_diff1": 0.334733, + "nauc_recall_at_10_max": 0.399261, + "nauc_recall_at_10_std": -0.122401, + "nauc_recall_at_10_diff1": 0.321424, + "nauc_recall_at_20_max": 0.393222, + "nauc_recall_at_20_std": -0.185554, + "nauc_recall_at_20_diff1": 0.247997, + "nauc_recall_at_100_max": 0.356262, + "nauc_recall_at_100_std": -0.043914, + "nauc_recall_at_100_diff1": 0.196441, + "nauc_recall_at_1000_max": 0.122114, + "nauc_recall_at_1000_std": 0.306796, + "nauc_recall_at_1000_diff1": 0.236385, + "nauc_precision_at_1_max": 0.248292, + "nauc_precision_at_1_std": 0.101909, + "nauc_precision_at_1_diff1": 0.065065, + "nauc_precision_at_3_max": 0.50596, + "nauc_precision_at_3_std": 0.271573, + "nauc_precision_at_3_diff1": 0.002836, + "nauc_precision_at_5_max": 0.364508, + "nauc_precision_at_5_std": 0.186616, + "nauc_precision_at_5_diff1": 0.060973, + "nauc_precision_at_10_max": 0.338822, + "nauc_precision_at_10_std": 0.155204, + "nauc_precision_at_10_diff1": -0.0566, + "nauc_precision_at_20_max": 0.218639, + "nauc_precision_at_20_std": 0.104667, + "nauc_precision_at_20_diff1": -0.170595, + "nauc_precision_at_100_max": 0.083989, + "nauc_precision_at_100_std": 0.243837, + "nauc_precision_at_100_diff1": -0.235011, + "nauc_precision_at_1000_max": -0.000291, + "nauc_precision_at_1000_std": 0.259818, + "nauc_precision_at_1000_diff1": -0.271337, + "nauc_mrr_at_1_max": 0.248292, + "nauc_mrr_at_1_std": 0.101909, + "nauc_mrr_at_1_diff1": 0.065065, + "nauc_mrr_at_3_max": 0.368471, + "nauc_mrr_at_3_std": 0.122406, + "nauc_mrr_at_3_diff1": 0.115514, + "nauc_mrr_at_5_max": 0.354827, + "nauc_mrr_at_5_std": 0.111453, + "nauc_mrr_at_5_diff1": 0.149289, + "nauc_mrr_at_10_max": 0.363906, + "nauc_mrr_at_10_std": 0.116463, + "nauc_mrr_at_10_diff1": 0.131636, + "nauc_mrr_at_20_max": 0.358043, + "nauc_mrr_at_20_std": 0.1161, + "nauc_mrr_at_20_diff1": 0.12534, + "nauc_mrr_at_100_max": 0.356188, + "nauc_mrr_at_100_std": 0.115767, + "nauc_mrr_at_100_diff1": 0.123878, + "nauc_mrr_at_1000_max": 0.356187, + "nauc_mrr_at_1000_std": 0.115856, + "nauc_mrr_at_1000_diff1": 0.123994, + "main_score": 0.458, + "hf_subset": "Medical-Sciences", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.1134, + "ndcg_at_3": 0.10843, + "ndcg_at_5": 0.11335, + "ndcg_at_10": 0.13552, + "ndcg_at_20": 0.16036, + "ndcg_at_100": 0.20675, + "ndcg_at_1000": 0.26282, + "map_at_1": 0.04512, + "map_at_3": 0.0717, + "map_at_5": 0.08195, + "map_at_10": 0.09251, + "map_at_20": 0.10005, + "map_at_100": 0.10746, + "map_at_1000": 0.11, + "recall_at_1": 0.04512, + "recall_at_3": 0.08913, + "recall_at_5": 0.12392, + "recall_at_10": 0.18741, + "recall_at_20": 0.25797, + "recall_at_100": 0.45432, + "recall_at_1000": 0.79253, + "precision_at_1": 0.1134, + "precision_at_3": 0.08247, + "precision_at_5": 0.06598, + "precision_at_10": 0.04845, + "precision_at_20": 0.03505, + "precision_at_100": 0.01237, + "precision_at_1000": 0.00228, + "mrr_at_1": 0.113402, + "mrr_at_3": 0.14433, + "mrr_at_5": 0.153608, + "mrr_at_10": 0.165574, + "mrr_at_20": 0.174453, + "mrr_at_100": 0.179298, + "mrr_at_1000": 0.180331, + "nauc_ndcg_at_1_max": 0.092664, + "nauc_ndcg_at_1_std": 0.133233, + "nauc_ndcg_at_1_diff1": -0.020062, + "nauc_ndcg_at_3_max": 0.132073, + "nauc_ndcg_at_3_std": 0.04423, + "nauc_ndcg_at_3_diff1": 0.113855, + "nauc_ndcg_at_5_max": 0.11165, + "nauc_ndcg_at_5_std": 0.090829, + "nauc_ndcg_at_5_diff1": 0.132278, + "nauc_ndcg_at_10_max": 0.090345, + "nauc_ndcg_at_10_std": 0.106675, + "nauc_ndcg_at_10_diff1": 0.090678, + "nauc_ndcg_at_20_max": 0.119243, + "nauc_ndcg_at_20_std": 0.112338, + "nauc_ndcg_at_20_diff1": 0.059053, + "nauc_ndcg_at_100_max": 0.153736, + "nauc_ndcg_at_100_std": 0.185588, + "nauc_ndcg_at_100_diff1": 0.064011, + "nauc_ndcg_at_1000_max": 0.178505, + "nauc_ndcg_at_1000_std": 0.194069, + "nauc_ndcg_at_1000_diff1": 0.063922, + "nauc_map_at_1_max": 0.098034, + "nauc_map_at_1_std": 0.064961, + "nauc_map_at_1_diff1": 0.212663, + "nauc_map_at_3_max": 0.167595, + "nauc_map_at_3_std": 0.038057, + "nauc_map_at_3_diff1": 0.186216, + "nauc_map_at_5_max": 0.149064, + "nauc_map_at_5_std": 0.079195, + "nauc_map_at_5_diff1": 0.182649, + "nauc_map_at_10_max": 0.126952, + "nauc_map_at_10_std": 0.084748, + "nauc_map_at_10_diff1": 0.146892, + "nauc_map_at_20_max": 0.139955, + "nauc_map_at_20_std": 0.088355, + "nauc_map_at_20_diff1": 0.130332, + "nauc_map_at_100_max": 0.144272, + "nauc_map_at_100_std": 0.105429, + "nauc_map_at_100_diff1": 0.126288, + "nauc_map_at_1000_max": 0.146019, + "nauc_map_at_1000_std": 0.106117, + "nauc_map_at_1000_diff1": 0.127385, + "nauc_recall_at_1_max": 0.098034, + "nauc_recall_at_1_std": 0.064961, + "nauc_recall_at_1_diff1": 0.212663, + "nauc_recall_at_3_max": 0.183917, + "nauc_recall_at_3_std": 0.029627, + "nauc_recall_at_3_diff1": 0.202784, + "nauc_recall_at_5_max": 0.115806, + "nauc_recall_at_5_std": 0.130281, + "nauc_recall_at_5_diff1": 0.194853, + "nauc_recall_at_10_max": 0.046165, + "nauc_recall_at_10_std": 0.111813, + "nauc_recall_at_10_diff1": 0.090336, + "nauc_recall_at_20_max": 0.105913, + "nauc_recall_at_20_std": 0.124761, + "nauc_recall_at_20_diff1": 0.006551, + "nauc_recall_at_100_max": 0.191818, + "nauc_recall_at_100_std": 0.324169, + "nauc_recall_at_100_diff1": 0.025517, + "nauc_recall_at_1000_max": 0.417311, + "nauc_recall_at_1000_std": 0.509482, + "nauc_recall_at_1000_diff1": -0.00121, + "nauc_precision_at_1_max": 0.092664, + "nauc_precision_at_1_std": 0.133233, + "nauc_precision_at_1_diff1": -0.020062, + "nauc_precision_at_3_max": 0.106692, + "nauc_precision_at_3_std": 0.019024, + "nauc_precision_at_3_diff1": 0.024437, + "nauc_precision_at_5_max": 0.052532, + "nauc_precision_at_5_std": 0.090322, + "nauc_precision_at_5_diff1": 0.005918, + "nauc_precision_at_10_max": 0.022449, + "nauc_precision_at_10_std": 0.12426, + "nauc_precision_at_10_diff1": -0.073442, + "nauc_precision_at_20_max": 0.081457, + "nauc_precision_at_20_std": 0.111336, + "nauc_precision_at_20_diff1": -0.098207, + "nauc_precision_at_100_max": 0.150202, + "nauc_precision_at_100_std": 0.227513, + "nauc_precision_at_100_diff1": -0.037579, + "nauc_precision_at_1000_max": 0.136536, + "nauc_precision_at_1000_std": 0.176741, + "nauc_precision_at_1000_diff1": -0.049265, + "nauc_mrr_at_1_max": 0.092664, + "nauc_mrr_at_1_std": 0.133233, + "nauc_mrr_at_1_diff1": -0.020062, + "nauc_mrr_at_3_max": 0.120133, + "nauc_mrr_at_3_std": 0.092988, + "nauc_mrr_at_3_diff1": 0.036344, + "nauc_mrr_at_5_max": 0.097343, + "nauc_mrr_at_5_std": 0.106911, + "nauc_mrr_at_5_diff1": 0.030369, + "nauc_mrr_at_10_max": 0.091746, + "nauc_mrr_at_10_std": 0.108484, + "nauc_mrr_at_10_diff1": 0.023639, + "nauc_mrr_at_20_max": 0.094217, + "nauc_mrr_at_20_std": 0.105535, + "nauc_mrr_at_20_diff1": 0.021647, + "nauc_mrr_at_100_max": 0.099156, + "nauc_mrr_at_100_std": 0.112068, + "nauc_mrr_at_100_diff1": 0.02202, + "nauc_mrr_at_1000_max": 0.099626, + "nauc_mrr_at_1000_std": 0.112286, + "nauc_mrr_at_1000_diff1": 0.022167, + "main_score": 0.13552, + "hf_subset": "MedXpertQA-Exam", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.17797, + "ndcg_at_3": 0.16009, + "ndcg_at_5": 0.17137, + "ndcg_at_10": 0.19856, + "ndcg_at_20": 0.2271, + "ndcg_at_100": 0.28376, + "ndcg_at_1000": 0.34369, + "map_at_1": 0.05734, + "map_at_3": 0.0959, + "map_at_5": 0.11942, + "map_at_10": 0.13864, + "map_at_20": 0.14943, + "map_at_100": 0.16186, + "map_at_1000": 0.16532, + "recall_at_1": 0.05734, + "recall_at_3": 0.11431, + "recall_at_5": 0.16879, + "recall_at_10": 0.23957, + "recall_at_20": 0.30715, + "recall_at_100": 0.50147, + "recall_at_1000": 0.81476, + "precision_at_1": 0.17797, + "precision_at_3": 0.13559, + "precision_at_5": 0.12034, + "precision_at_10": 0.08898, + "precision_at_20": 0.06186, + "precision_at_100": 0.02144, + "precision_at_1000": 0.00352, + "mrr_at_1": 0.177966, + "mrr_at_3": 0.238701, + "mrr_at_5": 0.250565, + "mrr_at_10": 0.26245, + "mrr_at_20": 0.269022, + "mrr_at_100": 0.272887, + "mrr_at_1000": 0.274048, + "nauc_ndcg_at_1_max": 0.018655, + "nauc_ndcg_at_1_std": -0.037852, + "nauc_ndcg_at_1_diff1": 0.173412, + "nauc_ndcg_at_3_max": 0.04859, + "nauc_ndcg_at_3_std": 0.020094, + "nauc_ndcg_at_3_diff1": 0.051825, + "nauc_ndcg_at_5_max": 0.086296, + "nauc_ndcg_at_5_std": 0.021666, + "nauc_ndcg_at_5_diff1": 0.035457, + "nauc_ndcg_at_10_max": 0.133147, + "nauc_ndcg_at_10_std": 0.08631, + "nauc_ndcg_at_10_diff1": 0.036447, + "nauc_ndcg_at_20_max": 0.139968, + "nauc_ndcg_at_20_std": 0.094497, + "nauc_ndcg_at_20_diff1": 0.030431, + "nauc_ndcg_at_100_max": 0.139447, + "nauc_ndcg_at_100_std": 0.113457, + "nauc_ndcg_at_100_diff1": 0.030387, + "nauc_ndcg_at_1000_max": 0.127072, + "nauc_ndcg_at_1000_std": 0.10991, + "nauc_ndcg_at_1000_diff1": 0.023028, + "nauc_map_at_1_max": 0.012091, + "nauc_map_at_1_std": -0.060597, + "nauc_map_at_1_diff1": 0.151255, + "nauc_map_at_3_max": 0.039097, + "nauc_map_at_3_std": 0.01154, + "nauc_map_at_3_diff1": 0.073742, + "nauc_map_at_5_max": 0.084776, + "nauc_map_at_5_std": 0.016287, + "nauc_map_at_5_diff1": 0.052381, + "nauc_map_at_10_max": 0.114535, + "nauc_map_at_10_std": 0.065199, + "nauc_map_at_10_diff1": 0.052878, + "nauc_map_at_20_max": 0.122492, + "nauc_map_at_20_std": 0.0765, + "nauc_map_at_20_diff1": 0.043059, + "nauc_map_at_100_max": 0.122853, + "nauc_map_at_100_std": 0.081911, + "nauc_map_at_100_diff1": 0.039698, + "nauc_map_at_1000_max": 0.12082, + "nauc_map_at_1000_std": 0.080266, + "nauc_map_at_1000_diff1": 0.038784, + "nauc_recall_at_1_max": 0.012091, + "nauc_recall_at_1_std": -0.060597, + "nauc_recall_at_1_diff1": 0.151255, + "nauc_recall_at_3_max": 0.071581, + "nauc_recall_at_3_std": 0.040455, + "nauc_recall_at_3_diff1": 0.045906, + "nauc_recall_at_5_max": 0.124599, + "nauc_recall_at_5_std": 0.039571, + "nauc_recall_at_5_diff1": 0.008774, + "nauc_recall_at_10_max": 0.176863, + "nauc_recall_at_10_std": 0.142271, + "nauc_recall_at_10_diff1": 0.011432, + "nauc_recall_at_20_max": 0.192809, + "nauc_recall_at_20_std": 0.160168, + "nauc_recall_at_20_diff1": -0.002825, + "nauc_recall_at_100_max": 0.21813, + "nauc_recall_at_100_std": 0.231787, + "nauc_recall_at_100_diff1": 0.039908, + "nauc_recall_at_1000_max": 0.30913, + "nauc_recall_at_1000_std": 0.407467, + "nauc_recall_at_1000_diff1": 0.02031, + "nauc_precision_at_1_max": 0.018655, + "nauc_precision_at_1_std": -0.037852, + "nauc_precision_at_1_diff1": 0.173412, + "nauc_precision_at_3_max": 0.084924, + "nauc_precision_at_3_std": 0.058931, + "nauc_precision_at_3_diff1": 0.002131, + "nauc_precision_at_5_max": 0.126534, + "nauc_precision_at_5_std": 0.063858, + "nauc_precision_at_5_diff1": -0.030545, + "nauc_precision_at_10_max": 0.165786, + "nauc_precision_at_10_std": 0.157803, + "nauc_precision_at_10_diff1": -0.027988, + "nauc_precision_at_20_max": 0.138217, + "nauc_precision_at_20_std": 0.128985, + "nauc_precision_at_20_diff1": -0.024417, + "nauc_precision_at_100_max": 0.055441, + "nauc_precision_at_100_std": 0.118647, + "nauc_precision_at_100_diff1": -0.048621, + "nauc_precision_at_1000_max": -0.077917, + "nauc_precision_at_1000_std": 0.030016, + "nauc_precision_at_1000_diff1": -0.069664, + "nauc_mrr_at_1_max": 0.018655, + "nauc_mrr_at_1_std": -0.037852, + "nauc_mrr_at_1_diff1": 0.173412, + "nauc_mrr_at_3_max": 0.046863, + "nauc_mrr_at_3_std": -0.000441, + "nauc_mrr_at_3_diff1": 0.084653, + "nauc_mrr_at_5_max": 0.049863, + "nauc_mrr_at_5_std": 0.00035, + "nauc_mrr_at_5_diff1": 0.078223, + "nauc_mrr_at_10_max": 0.06014, + "nauc_mrr_at_10_std": 0.008622, + "nauc_mrr_at_10_diff1": 0.076327, + "nauc_mrr_at_20_max": 0.056638, + "nauc_mrr_at_20_std": 0.005741, + "nauc_mrr_at_20_diff1": 0.078888, + "nauc_mrr_at_100_max": 0.057907, + "nauc_mrr_at_100_std": 0.006997, + "nauc_mrr_at_100_diff1": 0.079475, + "nauc_mrr_at_1000_max": 0.058383, + "nauc_mrr_at_1000_std": 0.007024, + "nauc_mrr_at_1000_diff1": 0.079382, + "main_score": 0.19856, + "hf_subset": "MedQA-Diag", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.34667, + "ndcg_at_3": 0.32839, + "ndcg_at_5": 0.3383, + "ndcg_at_10": 0.36663, + "ndcg_at_20": 0.38889, + "ndcg_at_100": 0.43525, + "ndcg_at_1000": 0.46616, + "map_at_1": 0.22233, + "map_at_3": 0.28141, + "map_at_5": 0.29462, + "map_at_10": 0.30852, + "map_at_20": 0.31515, + "map_at_100": 0.32413, + "map_at_1000": 0.32594, + "recall_at_1": 0.22233, + "recall_at_3": 0.31867, + "recall_at_5": 0.356, + "recall_at_10": 0.429, + "recall_at_20": 0.502, + "recall_at_100": 0.70511, + "recall_at_1000": 0.89622, + "precision_at_1": 0.34667, + "precision_at_3": 0.18889, + "precision_at_5": 0.132, + "precision_at_10": 0.08067, + "precision_at_20": 0.04833, + "precision_at_100": 0.01413, + "precision_at_1000": 0.00187, + "mrr_at_1": 0.346667, + "mrr_at_3": 0.403333, + "mrr_at_5": 0.414, + "mrr_at_10": 0.422934, + "mrr_at_20": 0.429082, + "mrr_at_100": 0.432583, + "mrr_at_1000": 0.433178, + "nauc_ndcg_at_1_max": 0.31736, + "nauc_ndcg_at_1_std": -0.095189, + "nauc_ndcg_at_1_diff1": 0.61528, + "nauc_ndcg_at_3_max": 0.279426, + "nauc_ndcg_at_3_std": -0.130107, + "nauc_ndcg_at_3_diff1": 0.481645, + "nauc_ndcg_at_5_max": 0.287026, + "nauc_ndcg_at_5_std": -0.124174, + "nauc_ndcg_at_5_diff1": 0.465419, + "nauc_ndcg_at_10_max": 0.265245, + "nauc_ndcg_at_10_std": -0.126409, + "nauc_ndcg_at_10_diff1": 0.446538, + "nauc_ndcg_at_20_max": 0.286375, + "nauc_ndcg_at_20_std": -0.1171, + "nauc_ndcg_at_20_diff1": 0.453705, + "nauc_ndcg_at_100_max": 0.300919, + "nauc_ndcg_at_100_std": -0.08211, + "nauc_ndcg_at_100_diff1": 0.454037, + "nauc_ndcg_at_1000_max": 0.310359, + "nauc_ndcg_at_1000_std": -0.089082, + "nauc_ndcg_at_1000_diff1": 0.467246, + "nauc_map_at_1_max": 0.226628, + "nauc_map_at_1_std": -0.175519, + "nauc_map_at_1_diff1": 0.496204, + "nauc_map_at_3_max": 0.262664, + "nauc_map_at_3_std": -0.144339, + "nauc_map_at_3_diff1": 0.48702, + "nauc_map_at_5_max": 0.278514, + "nauc_map_at_5_std": -0.133847, + "nauc_map_at_5_diff1": 0.475597, + "nauc_map_at_10_max": 0.275627, + "nauc_map_at_10_std": -0.134054, + "nauc_map_at_10_diff1": 0.468899, + "nauc_map_at_20_max": 0.283354, + "nauc_map_at_20_std": -0.130674, + "nauc_map_at_20_diff1": 0.472022, + "nauc_map_at_100_max": 0.287558, + "nauc_map_at_100_std": -0.123045, + "nauc_map_at_100_diff1": 0.472266, + "nauc_map_at_1000_max": 0.288602, + "nauc_map_at_1000_std": -0.123634, + "nauc_map_at_1000_diff1": 0.473504, + "nauc_recall_at_1_max": 0.226628, + "nauc_recall_at_1_std": -0.175519, + "nauc_recall_at_1_diff1": 0.496204, + "nauc_recall_at_3_max": 0.231394, + "nauc_recall_at_3_std": -0.14481, + "nauc_recall_at_3_diff1": 0.426049, + "nauc_recall_at_5_max": 0.241378, + "nauc_recall_at_5_std": -0.130384, + "nauc_recall_at_5_diff1": 0.380496, + "nauc_recall_at_10_max": 0.148217, + "nauc_recall_at_10_std": -0.141967, + "nauc_recall_at_10_diff1": 0.301956, + "nauc_recall_at_20_max": 0.191961, + "nauc_recall_at_20_std": -0.120568, + "nauc_recall_at_20_diff1": 0.304007, + "nauc_recall_at_100_max": 0.199412, + "nauc_recall_at_100_std": 0.071362, + "nauc_recall_at_100_diff1": 0.210625, + "nauc_recall_at_1000_max": 0.221164, + "nauc_recall_at_1000_std": 0.163585, + "nauc_recall_at_1000_diff1": 0.202991, + "nauc_precision_at_1_max": 0.31736, + "nauc_precision_at_1_std": -0.095189, + "nauc_precision_at_1_diff1": 0.61528, + "nauc_precision_at_3_max": 0.362637, + "nauc_precision_at_3_std": -0.036971, + "nauc_precision_at_3_diff1": 0.439752, + "nauc_precision_at_5_max": 0.416351, + "nauc_precision_at_5_std": -0.000903, + "nauc_precision_at_5_diff1": 0.36734, + "nauc_precision_at_10_max": 0.364451, + "nauc_precision_at_10_std": 0.027317, + "nauc_precision_at_10_diff1": 0.281673, + "nauc_precision_at_20_max": 0.419034, + "nauc_precision_at_20_std": 0.085074, + "nauc_precision_at_20_diff1": 0.267466, + "nauc_precision_at_100_max": 0.327914, + "nauc_precision_at_100_std": 0.212625, + "nauc_precision_at_100_diff1": 0.102006, + "nauc_precision_at_1000_max": 0.300349, + "nauc_precision_at_1000_std": 0.147483, + "nauc_precision_at_1000_diff1": 0.068676, + "nauc_mrr_at_1_max": 0.31736, + "nauc_mrr_at_1_std": -0.095189, + "nauc_mrr_at_1_diff1": 0.61528, + "nauc_mrr_at_3_max": 0.31788, + "nauc_mrr_at_3_std": -0.108365, + "nauc_mrr_at_3_diff1": 0.544479, + "nauc_mrr_at_5_max": 0.320993, + "nauc_mrr_at_5_std": -0.107319, + "nauc_mrr_at_5_diff1": 0.530688, + "nauc_mrr_at_10_max": 0.303271, + "nauc_mrr_at_10_std": -0.111546, + "nauc_mrr_at_10_diff1": 0.523274, + "nauc_mrr_at_20_max": 0.309933, + "nauc_mrr_at_20_std": -0.107255, + "nauc_mrr_at_20_diff1": 0.525724, + "nauc_mrr_at_100_max": 0.309948, + "nauc_mrr_at_100_std": -0.107427, + "nauc_mrr_at_100_diff1": 0.528414, + "nauc_mrr_at_1000_max": 0.309961, + "nauc_mrr_at_1000_std": -0.107311, + "nauc_mrr_at_1000_diff1": 0.528405, + "main_score": 0.36663, + "hf_subset": "PMC-Treatment", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.25439, + "ndcg_at_3": 0.24499, + "ndcg_at_5": 0.27904, + "ndcg_at_10": 0.3045, + "ndcg_at_20": 0.34046, + "ndcg_at_100": 0.39127, + "ndcg_at_1000": 0.42013, + "map_at_1": 0.13012, + "map_at_3": 0.19798, + "map_at_5": 0.21932, + "map_at_10": 0.2327, + "map_at_20": 0.24506, + "map_at_100": 0.25422, + "map_at_1000": 0.25598, + "recall_at_1": 0.13012, + "recall_at_3": 0.25, + "recall_at_5": 0.32602, + "recall_at_10": 0.39035, + "recall_at_20": 0.50731, + "recall_at_100": 0.72953, + "recall_at_1000": 0.90424, + "precision_at_1": 0.25439, + "precision_at_3": 0.17251, + "precision_at_5": 0.13684, + "precision_at_10": 0.08246, + "precision_at_20": 0.05351, + "precision_at_100": 0.01544, + "precision_at_1000": 0.00196, + "mrr_at_1": 0.254386, + "mrr_at_3": 0.320175, + "mrr_at_5": 0.346053, + "mrr_at_10": 0.353568, + "mrr_at_20": 0.360151, + "mrr_at_100": 0.365287, + "mrr_at_1000": 0.365775, + "nauc_ndcg_at_1_max": 0.24631, + "nauc_ndcg_at_1_std": -0.078998, + "nauc_ndcg_at_1_diff1": 0.384235, + "nauc_ndcg_at_3_max": 0.217423, + "nauc_ndcg_at_3_std": -0.076471, + "nauc_ndcg_at_3_diff1": 0.280978, + "nauc_ndcg_at_5_max": 0.232747, + "nauc_ndcg_at_5_std": -0.063571, + "nauc_ndcg_at_5_diff1": 0.268939, + "nauc_ndcg_at_10_max": 0.208519, + "nauc_ndcg_at_10_std": -0.061699, + "nauc_ndcg_at_10_diff1": 0.227552, + "nauc_ndcg_at_20_max": 0.26482, + "nauc_ndcg_at_20_std": -0.001721, + "nauc_ndcg_at_20_diff1": 0.244126, + "nauc_ndcg_at_100_max": 0.240489, + "nauc_ndcg_at_100_std": -0.029319, + "nauc_ndcg_at_100_diff1": 0.257747, + "nauc_ndcg_at_1000_max": 0.2419, + "nauc_ndcg_at_1000_std": -0.028556, + "nauc_ndcg_at_1000_diff1": 0.264374, + "nauc_map_at_1_max": 0.226515, + "nauc_map_at_1_std": 0.007603, + "nauc_map_at_1_diff1": 0.350172, + "nauc_map_at_3_max": 0.227277, + "nauc_map_at_3_std": -0.072572, + "nauc_map_at_3_diff1": 0.309225, + "nauc_map_at_5_max": 0.229965, + "nauc_map_at_5_std": -0.072884, + "nauc_map_at_5_diff1": 0.297166, + "nauc_map_at_10_max": 0.213803, + "nauc_map_at_10_std": -0.075262, + "nauc_map_at_10_diff1": 0.274246, + "nauc_map_at_20_max": 0.241524, + "nauc_map_at_20_std": -0.045987, + "nauc_map_at_20_diff1": 0.279368, + "nauc_map_at_100_max": 0.23505, + "nauc_map_at_100_std": -0.050169, + "nauc_map_at_100_diff1": 0.281804, + "nauc_map_at_1000_max": 0.234621, + "nauc_map_at_1000_std": -0.049147, + "nauc_map_at_1000_diff1": 0.281819, + "nauc_recall_at_1_max": 0.226515, + "nauc_recall_at_1_std": 0.007603, + "nauc_recall_at_1_diff1": 0.350172, + "nauc_recall_at_3_max": 0.170415, + "nauc_recall_at_3_std": -0.095274, + "nauc_recall_at_3_diff1": 0.242571, + "nauc_recall_at_5_max": 0.166773, + "nauc_recall_at_5_std": -0.078027, + "nauc_recall_at_5_diff1": 0.19618, + "nauc_recall_at_10_max": 0.093298, + "nauc_recall_at_10_std": -0.085202, + "nauc_recall_at_10_diff1": 0.090313, + "nauc_recall_at_20_max": 0.225738, + "nauc_recall_at_20_std": 0.06813, + "nauc_recall_at_20_diff1": 0.130283, + "nauc_recall_at_100_max": 0.123151, + "nauc_recall_at_100_std": -0.040118, + "nauc_recall_at_100_diff1": 0.173231, + "nauc_recall_at_1000_max": 0.11268, + "nauc_recall_at_1000_std": -0.05351, + "nauc_recall_at_1000_diff1": 0.251423, + "nauc_precision_at_1_max": 0.24631, + "nauc_precision_at_1_std": -0.078998, + "nauc_precision_at_1_diff1": 0.384235, + "nauc_precision_at_3_max": 0.207394, + "nauc_precision_at_3_std": -0.135411, + "nauc_precision_at_3_diff1": 0.217327, + "nauc_precision_at_5_max": 0.243294, + "nauc_precision_at_5_std": -0.071897, + "nauc_precision_at_5_diff1": 0.142353, + "nauc_precision_at_10_max": 0.171286, + "nauc_precision_at_10_std": -0.055365, + "nauc_precision_at_10_diff1": 0.049555, + "nauc_precision_at_20_max": 0.28933, + "nauc_precision_at_20_std": 0.110688, + "nauc_precision_at_20_diff1": 0.056197, + "nauc_precision_at_100_max": 0.191069, + "nauc_precision_at_100_std": 0.045188, + "nauc_precision_at_100_diff1": 0.001976, + "nauc_precision_at_1000_max": 0.115871, + "nauc_precision_at_1000_std": 0.017514, + "nauc_precision_at_1000_diff1": -0.05959, + "nauc_mrr_at_1_max": 0.24631, + "nauc_mrr_at_1_std": -0.078998, + "nauc_mrr_at_1_diff1": 0.384235, + "nauc_mrr_at_3_max": 0.253771, + "nauc_mrr_at_3_std": -0.056164, + "nauc_mrr_at_3_diff1": 0.300971, + "nauc_mrr_at_5_max": 0.269927, + "nauc_mrr_at_5_std": -0.028637, + "nauc_mrr_at_5_diff1": 0.284567, + "nauc_mrr_at_10_max": 0.263344, + "nauc_mrr_at_10_std": -0.027431, + "nauc_mrr_at_10_diff1": 0.275758, + "nauc_mrr_at_20_max": 0.268994, + "nauc_mrr_at_20_std": -0.026719, + "nauc_mrr_at_20_diff1": 0.284359, + "nauc_mrr_at_100_max": 0.265272, + "nauc_mrr_at_100_std": -0.031061, + "nauc_mrr_at_100_diff1": 0.288316, + "nauc_mrr_at_1000_max": 0.265119, + "nauc_mrr_at_1000_std": -0.030753, + "nauc_mrr_at_1000_diff1": 0.288455, + "main_score": 0.3045, + "hf_subset": "PMC-Clinical", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.13953, + "ndcg_at_3": 0.12997, + "ndcg_at_5": 0.14222, + "ndcg_at_10": 0.19062, + "ndcg_at_20": 0.24606, + "ndcg_at_100": 0.34177, + "ndcg_at_1000": 0.37908, + "map_at_1": 0.04483, + "map_at_3": 0.07261, + "map_at_5": 0.08801, + "map_at_10": 0.1118, + "map_at_20": 0.13576, + "map_at_100": 0.15663, + "map_at_1000": 0.15946, + "recall_at_1": 0.04483, + "recall_at_3": 0.10491, + "recall_at_5": 0.14987, + "recall_at_10": 0.2584, + "recall_at_20": 0.40452, + "recall_at_100": 0.76072, + "recall_at_1000": 0.96163, + "precision_at_1": 0.13953, + "precision_at_3": 0.11628, + "precision_at_5": 0.10543, + "precision_at_10": 0.09225, + "precision_at_20": 0.07287, + "precision_at_100": 0.02736, + "precision_at_1000": 0.00344, + "mrr_at_1": 0.139535, + "mrr_at_3": 0.210594, + "mrr_at_5": 0.228424, + "mrr_at_10": 0.251037, + "mrr_at_20": 0.259679, + "mrr_at_100": 0.265743, + "mrr_at_1000": 0.266081, + "nauc_ndcg_at_1_max": 0.025957, + "nauc_ndcg_at_1_std": 0.155869, + "nauc_ndcg_at_1_diff1": 0.199266, + "nauc_ndcg_at_3_max": 0.068096, + "nauc_ndcg_at_3_std": 0.088974, + "nauc_ndcg_at_3_diff1": 0.106216, + "nauc_ndcg_at_5_max": 0.125343, + "nauc_ndcg_at_5_std": 0.076723, + "nauc_ndcg_at_5_diff1": 0.075463, + "nauc_ndcg_at_10_max": 0.100738, + "nauc_ndcg_at_10_std": 0.075556, + "nauc_ndcg_at_10_diff1": 0.053337, + "nauc_ndcg_at_20_max": 0.126047, + "nauc_ndcg_at_20_std": 0.034811, + "nauc_ndcg_at_20_diff1": 0.080113, + "nauc_ndcg_at_100_max": 0.107642, + "nauc_ndcg_at_100_std": 0.191137, + "nauc_ndcg_at_100_diff1": 0.073998, + "nauc_ndcg_at_1000_max": 0.118298, + "nauc_ndcg_at_1000_std": 0.177873, + "nauc_ndcg_at_1000_diff1": 0.023834, + "nauc_map_at_1_max": -0.014153, + "nauc_map_at_1_std": 0.041599, + "nauc_map_at_1_diff1": 0.168698, + "nauc_map_at_3_max": 0.030649, + "nauc_map_at_3_std": 0.050095, + "nauc_map_at_3_diff1": 0.1109, + "nauc_map_at_5_max": 0.086417, + "nauc_map_at_5_std": 0.065241, + "nauc_map_at_5_diff1": 0.093924, + "nauc_map_at_10_max": 0.076969, + "nauc_map_at_10_std": 0.060282, + "nauc_map_at_10_diff1": 0.07797, + "nauc_map_at_20_max": 0.092832, + "nauc_map_at_20_std": 0.040185, + "nauc_map_at_20_diff1": 0.076563, + "nauc_map_at_100_max": 0.08891, + "nauc_map_at_100_std": 0.082125, + "nauc_map_at_100_diff1": 0.080044, + "nauc_map_at_1000_max": 0.091414, + "nauc_map_at_1000_std": 0.082569, + "nauc_map_at_1000_diff1": 0.075386, + "nauc_recall_at_1_max": -0.014153, + "nauc_recall_at_1_std": 0.041599, + "nauc_recall_at_1_diff1": 0.168698, + "nauc_recall_at_3_max": 0.062071, + "nauc_recall_at_3_std": 0.013108, + "nauc_recall_at_3_diff1": 0.007541, + "nauc_recall_at_5_max": 0.148101, + "nauc_recall_at_5_std": 0.037093, + "nauc_recall_at_5_diff1": -0.001931, + "nauc_recall_at_10_max": 0.074119, + "nauc_recall_at_10_std": 0.010031, + "nauc_recall_at_10_diff1": -0.014423, + "nauc_recall_at_20_max": 0.118216, + "nauc_recall_at_20_std": -0.083851, + "nauc_recall_at_20_diff1": 0.057325, + "nauc_recall_at_100_max": 0.082008, + "nauc_recall_at_100_std": 0.368483, + "nauc_recall_at_100_diff1": 0.061559, + "nauc_recall_at_1000_max": 0.129674, + "nauc_recall_at_1000_std": 0.773182, + "nauc_recall_at_1000_diff1": -0.78334, + "nauc_precision_at_1_max": 0.025957, + "nauc_precision_at_1_std": 0.155869, + "nauc_precision_at_1_diff1": 0.199266, + "nauc_precision_at_3_max": 0.158231, + "nauc_precision_at_3_std": 0.140321, + "nauc_precision_at_3_diff1": 0.083702, + "nauc_precision_at_5_max": 0.242642, + "nauc_precision_at_5_std": 0.112771, + "nauc_precision_at_5_diff1": 0.046767, + "nauc_precision_at_10_max": 0.167255, + "nauc_precision_at_10_std": 0.131275, + "nauc_precision_at_10_diff1": -0.00693, + "nauc_precision_at_20_max": 0.172127, + "nauc_precision_at_20_std": 0.06856, + "nauc_precision_at_20_diff1": 0.032686, + "nauc_precision_at_100_max": 0.088556, + "nauc_precision_at_100_std": 0.353855, + "nauc_precision_at_100_diff1": -0.007498, + "nauc_precision_at_1000_max": 0.115321, + "nauc_precision_at_1000_std": 0.308769, + "nauc_precision_at_1000_diff1": -0.188543, + "nauc_mrr_at_1_max": 0.025957, + "nauc_mrr_at_1_std": 0.155869, + "nauc_mrr_at_1_diff1": 0.199266, + "nauc_mrr_at_3_max": 0.076721, + "nauc_mrr_at_3_std": 0.119348, + "nauc_mrr_at_3_diff1": 0.126364, + "nauc_mrr_at_5_max": 0.098046, + "nauc_mrr_at_5_std": 0.103518, + "nauc_mrr_at_5_diff1": 0.128071, + "nauc_mrr_at_10_max": 0.087578, + "nauc_mrr_at_10_std": 0.121834, + "nauc_mrr_at_10_diff1": 0.119542, + "nauc_mrr_at_20_max": 0.093956, + "nauc_mrr_at_20_std": 0.117767, + "nauc_mrr_at_20_diff1": 0.132532, + "nauc_mrr_at_100_max": 0.091776, + "nauc_mrr_at_100_std": 0.127456, + "nauc_mrr_at_100_diff1": 0.126176, + "nauc_mrr_at_1000_max": 0.09144, + "nauc_mrr_at_1000_std": 0.126647, + "nauc_mrr_at_1000_diff1": 0.126093, + "main_score": 0.19062, + "hf_subset": "IIYi-Clinical", + "languages": [ + "eng-Latn" + ] + } + ] + }, + "evaluation_time": 5735.03715801239, + "kg_co2_emissions": null +} \ No newline at end of file diff --git a/results/Salesforce__SFR-Embedding-Mistral/938c560d1c236aa563b2dbdf084f28ab28bccb11/R2MEDRetrieval.json b/results/Salesforce__SFR-Embedding-Mistral/938c560d1c236aa563b2dbdf084f28ab28bccb11/R2MEDRetrieval.json new file mode 100644 index 0000000000..ff34f6aea0 --- /dev/null +++ b/results/Salesforce__SFR-Embedding-Mistral/938c560d1c236aa563b2dbdf084f28ab28bccb11/R2MEDRetrieval.json @@ -0,0 +1,1187 @@ +{ + "dataset_revision": "1.0", + "task_name": "R2MEDRetrieval", + "mteb_version": "1.38.20", + "scores": { + "test": [ + { + "ndcg_at_1": 0.19417, + "ndcg_at_3": 0.15951, + "ndcg_at_5": 0.16824, + "ndcg_at_10": 0.19484, + "ndcg_at_20": 0.22301, + "ndcg_at_100": 0.28313, + "ndcg_at_1000": 0.34225, + "map_at_1": 0.0511, + "map_at_3": 0.08931, + "map_at_5": 0.10898, + "map_at_10": 0.13249, + "map_at_20": 0.14393, + "map_at_100": 0.15585, + "map_at_1000": 0.15959, + "recall_at_1": 0.0511, + "recall_at_3": 0.11183, + "recall_at_5": 0.15765, + "recall_at_10": 0.23051, + "recall_at_20": 0.31211, + "recall_at_100": 0.5391, + "recall_at_1000": 0.86486, + "precision_at_1": 0.19417, + "precision_at_3": 0.13592, + "precision_at_5": 0.12039, + "precision_at_10": 0.09515, + "precision_at_20": 0.06165, + "precision_at_100": 0.02068, + "precision_at_1000": 0.00323, + "mrr_at_1": 0.194175, + "mrr_at_3": 0.234628, + "mrr_at_5": 0.245307, + "mrr_at_10": 0.258811, + "mrr_at_20": 0.265774, + "mrr_at_100": 0.2706, + "mrr_at_1000": 0.271487, + "nauc_ndcg_at_1_max": -0.000643, + "nauc_ndcg_at_1_std": -0.324714, + "nauc_ndcg_at_1_diff1": 0.129867, + "nauc_ndcg_at_3_max": -0.032873, + "nauc_ndcg_at_3_std": -0.339745, + "nauc_ndcg_at_3_diff1": 0.109224, + "nauc_ndcg_at_5_max": -0.014514, + "nauc_ndcg_at_5_std": -0.355715, + "nauc_ndcg_at_5_diff1": 0.122091, + "nauc_ndcg_at_10_max": -0.004276, + "nauc_ndcg_at_10_std": -0.324787, + "nauc_ndcg_at_10_diff1": 0.166259, + "nauc_ndcg_at_20_max": -0.017963, + "nauc_ndcg_at_20_std": -0.339509, + "nauc_ndcg_at_20_diff1": 0.166565, + "nauc_ndcg_at_100_max": -0.013395, + "nauc_ndcg_at_100_std": -0.331457, + "nauc_ndcg_at_100_diff1": 0.176311, + "nauc_ndcg_at_1000_max": -0.021686, + "nauc_ndcg_at_1000_std": -0.332081, + "nauc_ndcg_at_1000_diff1": 0.164291, + "nauc_map_at_1_max": 0.014273, + "nauc_map_at_1_std": -0.340221, + "nauc_map_at_1_diff1": 0.184189, + "nauc_map_at_3_max": -0.004401, + "nauc_map_at_3_std": -0.356147, + "nauc_map_at_3_diff1": 0.162624, + "nauc_map_at_5_max": 0.010125, + "nauc_map_at_5_std": -0.344657, + "nauc_map_at_5_diff1": 0.164792, + "nauc_map_at_10_max": 0.010422, + "nauc_map_at_10_std": -0.32834, + "nauc_map_at_10_diff1": 0.188881, + "nauc_map_at_20_max": -0.001558, + "nauc_map_at_20_std": -0.341036, + "nauc_map_at_20_diff1": 0.18044, + "nauc_map_at_100_max": -0.00538, + "nauc_map_at_100_std": -0.338027, + "nauc_map_at_100_diff1": 0.176909, + "nauc_map_at_1000_max": -0.007747, + "nauc_map_at_1000_std": -0.339396, + "nauc_map_at_1000_diff1": 0.175322, + "nauc_recall_at_1_max": 0.014273, + "nauc_recall_at_1_std": -0.340221, + "nauc_recall_at_1_diff1": 0.184189, + "nauc_recall_at_3_max": 0.002073, + "nauc_recall_at_3_std": -0.352102, + "nauc_recall_at_3_diff1": 0.136959, + "nauc_recall_at_5_max": 0.024754, + "nauc_recall_at_5_std": -0.333931, + "nauc_recall_at_5_diff1": 0.134785, + "nauc_recall_at_10_max": -0.002663, + "nauc_recall_at_10_std": -0.284968, + "nauc_recall_at_10_diff1": 0.162852, + "nauc_recall_at_20_max": -0.017476, + "nauc_recall_at_20_std": -0.292532, + "nauc_recall_at_20_diff1": 0.166391, + "nauc_recall_at_100_max": 0.018706, + "nauc_recall_at_100_std": -0.244442, + "nauc_recall_at_100_diff1": 0.233412, + "nauc_recall_at_1000_max": 0.018539, + "nauc_recall_at_1000_std": -0.103199, + "nauc_recall_at_1000_diff1": 0.236866, + "nauc_precision_at_1_max": -0.000643, + "nauc_precision_at_1_std": -0.324714, + "nauc_precision_at_1_diff1": 0.129867, + "nauc_precision_at_3_max": -0.058577, + "nauc_precision_at_3_std": -0.343746, + "nauc_precision_at_3_diff1": 0.105385, + "nauc_precision_at_5_max": -0.030293, + "nauc_precision_at_5_std": -0.33474, + "nauc_precision_at_5_diff1": 0.118051, + "nauc_precision_at_10_max": -0.070811, + "nauc_precision_at_10_std": -0.294152, + "nauc_precision_at_10_diff1": 0.142212, + "nauc_precision_at_20_max": -0.119193, + "nauc_precision_at_20_std": -0.321058, + "nauc_precision_at_20_diff1": 0.124079, + "nauc_precision_at_100_max": -0.104183, + "nauc_precision_at_100_std": -0.237714, + "nauc_precision_at_100_diff1": 0.09815, + "nauc_precision_at_1000_max": -0.139287, + "nauc_precision_at_1000_std": -0.188939, + "nauc_precision_at_1000_diff1": 0.022146, + "nauc_mrr_at_1_max": -0.000643, + "nauc_mrr_at_1_std": -0.324714, + "nauc_mrr_at_1_diff1": 0.129867, + "nauc_mrr_at_3_max": 0.025353, + "nauc_mrr_at_3_std": -0.323891, + "nauc_mrr_at_3_diff1": 0.125283, + "nauc_mrr_at_5_max": 0.022148, + "nauc_mrr_at_5_std": -0.330803, + "nauc_mrr_at_5_diff1": 0.119914, + "nauc_mrr_at_10_max": 0.002258, + "nauc_mrr_at_10_std": -0.327823, + "nauc_mrr_at_10_diff1": 0.119088, + "nauc_mrr_at_20_max": -0.000624, + "nauc_mrr_at_20_std": -0.328588, + "nauc_mrr_at_20_diff1": 0.113905, + "nauc_mrr_at_100_max": 0.00081, + "nauc_mrr_at_100_std": -0.331579, + "nauc_mrr_at_100_diff1": 0.114749, + "nauc_mrr_at_1000_max": 0.000503, + "nauc_mrr_at_1000_std": -0.331287, + "nauc_mrr_at_1000_diff1": 0.11396, + "main_score": 0.19484, + "hf_subset": "Biology", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.31169, + "ndcg_at_3": 0.34253, + "ndcg_at_5": 0.36354, + "ndcg_at_10": 0.40307, + "ndcg_at_20": 0.44654, + "ndcg_at_100": 0.50619, + "ndcg_at_1000": 0.52482, + "map_at_1": 0.15207, + "map_at_3": 0.25173, + "map_at_5": 0.28823, + "map_at_10": 0.31636, + "map_at_20": 0.33307, + "map_at_100": 0.34811, + "map_at_1000": 0.34943, + "recall_at_1": 0.15207, + "recall_at_3": 0.32914, + "recall_at_5": 0.42059, + "recall_at_10": 0.5231, + "recall_at_20": 0.65118, + "recall_at_100": 0.87083, + "recall_at_1000": 0.98268, + "precision_at_1": 0.31169, + "precision_at_3": 0.24675, + "precision_at_5": 0.19481, + "precision_at_10": 0.13247, + "precision_at_20": 0.08636, + "precision_at_100": 0.02571, + "precision_at_1000": 0.00292, + "mrr_at_1": 0.311688, + "mrr_at_3": 0.400433, + "mrr_at_5": 0.419264, + "mrr_at_10": 0.433849, + "mrr_at_20": 0.44088, + "mrr_at_100": 0.443775, + "mrr_at_1000": 0.444085, + "nauc_ndcg_at_1_max": 0.031029, + "nauc_ndcg_at_1_std": -0.075842, + "nauc_ndcg_at_1_diff1": 0.087602, + "nauc_ndcg_at_3_max": 0.099158, + "nauc_ndcg_at_3_std": -0.021593, + "nauc_ndcg_at_3_diff1": 0.161385, + "nauc_ndcg_at_5_max": 0.16271, + "nauc_ndcg_at_5_std": -0.034072, + "nauc_ndcg_at_5_diff1": 0.15492, + "nauc_ndcg_at_10_max": 0.206292, + "nauc_ndcg_at_10_std": -0.031123, + "nauc_ndcg_at_10_diff1": 0.152533, + "nauc_ndcg_at_20_max": 0.197685, + "nauc_ndcg_at_20_std": -0.017483, + "nauc_ndcg_at_20_diff1": 0.133437, + "nauc_ndcg_at_100_max": 0.179833, + "nauc_ndcg_at_100_std": 0.011836, + "nauc_ndcg_at_100_diff1": 0.084723, + "nauc_ndcg_at_1000_max": 0.16736, + "nauc_ndcg_at_1000_std": -0.013104, + "nauc_ndcg_at_1000_diff1": 0.110979, + "nauc_map_at_1_max": -0.053278, + "nauc_map_at_1_std": -0.106497, + "nauc_map_at_1_diff1": 0.203465, + "nauc_map_at_3_max": 0.064328, + "nauc_map_at_3_std": -0.063618, + "nauc_map_at_3_diff1": 0.205162, + "nauc_map_at_5_max": 0.142502, + "nauc_map_at_5_std": -0.039058, + "nauc_map_at_5_diff1": 0.174106, + "nauc_map_at_10_max": 0.164349, + "nauc_map_at_10_std": -0.047366, + "nauc_map_at_10_diff1": 0.169633, + "nauc_map_at_20_max": 0.159453, + "nauc_map_at_20_std": -0.042518, + "nauc_map_at_20_diff1": 0.165979, + "nauc_map_at_100_max": 0.155469, + "nauc_map_at_100_std": -0.033343, + "nauc_map_at_100_diff1": 0.155706, + "nauc_map_at_1000_max": 0.154089, + "nauc_map_at_1000_std": -0.034593, + "nauc_map_at_1000_diff1": 0.156206, + "nauc_recall_at_1_max": -0.053278, + "nauc_recall_at_1_std": -0.106497, + "nauc_recall_at_1_diff1": 0.203465, + "nauc_recall_at_3_max": 0.10747, + "nauc_recall_at_3_std": -0.040706, + "nauc_recall_at_3_diff1": 0.22099, + "nauc_recall_at_5_max": 0.216195, + "nauc_recall_at_5_std": -0.033959, + "nauc_recall_at_5_diff1": 0.162498, + "nauc_recall_at_10_max": 0.311365, + "nauc_recall_at_10_std": -0.004916, + "nauc_recall_at_10_diff1": 0.153544, + "nauc_recall_at_20_max": 0.322835, + "nauc_recall_at_20_std": 0.064041, + "nauc_recall_at_20_diff1": 0.089192, + "nauc_recall_at_100_max": 0.417611, + "nauc_recall_at_100_std": 0.393289, + "nauc_recall_at_100_diff1": -0.316067, + "nauc_recall_at_1000_max": 0.055714, + "nauc_recall_at_1000_std": -0.281621, + "nauc_recall_at_1000_diff1": -0.560444, + "nauc_precision_at_1_max": 0.031029, + "nauc_precision_at_1_std": -0.075842, + "nauc_precision_at_1_diff1": 0.087602, + "nauc_precision_at_3_max": 0.217141, + "nauc_precision_at_3_std": 0.064948, + "nauc_precision_at_3_diff1": 0.029343, + "nauc_precision_at_5_max": 0.32996, + "nauc_precision_at_5_std": 0.090688, + "nauc_precision_at_5_diff1": -0.041489, + "nauc_precision_at_10_max": 0.295274, + "nauc_precision_at_10_std": 0.071624, + "nauc_precision_at_10_diff1": -0.029136, + "nauc_precision_at_20_max": 0.186901, + "nauc_precision_at_20_std": 0.063908, + "nauc_precision_at_20_diff1": -0.075253, + "nauc_precision_at_100_max": 0.076318, + "nauc_precision_at_100_std": 0.095501, + "nauc_precision_at_100_diff1": -0.133921, + "nauc_precision_at_1000_max": 0.069882, + "nauc_precision_at_1000_std": 0.070954, + "nauc_precision_at_1000_diff1": -0.058984, + "nauc_mrr_at_1_max": 0.031029, + "nauc_mrr_at_1_std": -0.075842, + "nauc_mrr_at_1_diff1": 0.087602, + "nauc_mrr_at_3_max": 0.099177, + "nauc_mrr_at_3_std": -0.039946, + "nauc_mrr_at_3_diff1": 0.121283, + "nauc_mrr_at_5_max": 0.110691, + "nauc_mrr_at_5_std": -0.051173, + "nauc_mrr_at_5_diff1": 0.120327, + "nauc_mrr_at_10_max": 0.118367, + "nauc_mrr_at_10_std": -0.033363, + "nauc_mrr_at_10_diff1": 0.110848, + "nauc_mrr_at_20_max": 0.11186, + "nauc_mrr_at_20_std": -0.037883, + "nauc_mrr_at_20_diff1": 0.10506, + "nauc_mrr_at_100_max": 0.106846, + "nauc_mrr_at_100_std": -0.038089, + "nauc_mrr_at_100_diff1": 0.100534, + "nauc_mrr_at_1000_max": 0.106837, + "nauc_mrr_at_1000_std": -0.038524, + "nauc_mrr_at_1000_diff1": 0.101473, + "main_score": 0.40307, + "hf_subset": "Bioinformatics", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.28409, + "ndcg_at_3": 0.3567, + "ndcg_at_5": 0.38268, + "ndcg_at_10": 0.42443, + "ndcg_at_20": 0.47689, + "ndcg_at_100": 0.52494, + "ndcg_at_1000": 0.54345, + "map_at_1": 0.16393, + "map_at_3": 0.27764, + "map_at_5": 0.30766, + "map_at_10": 0.33391, + "map_at_20": 0.35639, + "map_at_100": 0.36875, + "map_at_1000": 0.37036, + "recall_at_1": 0.16393, + "recall_at_3": 0.37393, + "recall_at_5": 0.45352, + "recall_at_10": 0.56177, + "recall_at_20": 0.71161, + "recall_at_100": 0.88041, + "recall_at_1000": 0.98295, + "precision_at_1": 0.28409, + "precision_at_3": 0.24242, + "precision_at_5": 0.18636, + "precision_at_10": 0.12841, + "precision_at_20": 0.08636, + "precision_at_100": 0.02386, + "precision_at_1000": 0.00273, + "mrr_at_1": 0.284091, + "mrr_at_3": 0.407197, + "mrr_at_5": 0.426515, + "mrr_at_10": 0.441112, + "mrr_at_20": 0.450309, + "mrr_at_100": 0.451858, + "mrr_at_1000": 0.452051, + "nauc_ndcg_at_1_max": 0.271554, + "nauc_ndcg_at_1_std": 0.03701, + "nauc_ndcg_at_1_diff1": 0.121477, + "nauc_ndcg_at_3_max": 0.350682, + "nauc_ndcg_at_3_std": -0.014741, + "nauc_ndcg_at_3_diff1": 0.12322, + "nauc_ndcg_at_5_max": 0.36455, + "nauc_ndcg_at_5_std": -0.001117, + "nauc_ndcg_at_5_diff1": 0.136797, + "nauc_ndcg_at_10_max": 0.332961, + "nauc_ndcg_at_10_std": -0.033292, + "nauc_ndcg_at_10_diff1": 0.135335, + "nauc_ndcg_at_20_max": 0.332739, + "nauc_ndcg_at_20_std": -0.044894, + "nauc_ndcg_at_20_diff1": 0.156565, + "nauc_ndcg_at_100_max": 0.354098, + "nauc_ndcg_at_100_std": 0.027781, + "nauc_ndcg_at_100_diff1": 0.138331, + "nauc_ndcg_at_1000_max": 0.34846, + "nauc_ndcg_at_1000_std": 0.025363, + "nauc_ndcg_at_1000_diff1": 0.145287, + "nauc_map_at_1_max": 0.167324, + "nauc_map_at_1_std": -0.084492, + "nauc_map_at_1_diff1": 0.242873, + "nauc_map_at_3_max": 0.302759, + "nauc_map_at_3_std": -0.037193, + "nauc_map_at_3_diff1": 0.125679, + "nauc_map_at_5_max": 0.328257, + "nauc_map_at_5_std": 0.001464, + "nauc_map_at_5_diff1": 0.137357, + "nauc_map_at_10_max": 0.320267, + "nauc_map_at_10_std": -0.010769, + "nauc_map_at_10_diff1": 0.139462, + "nauc_map_at_20_max": 0.31979, + "nauc_map_at_20_std": -0.018079, + "nauc_map_at_20_diff1": 0.148704, + "nauc_map_at_100_max": 0.325989, + "nauc_map_at_100_std": -8.4e-05, + "nauc_map_at_100_diff1": 0.142833, + "nauc_map_at_1000_max": 0.325397, + "nauc_map_at_1000_std": -0.000236, + "nauc_map_at_1000_diff1": 0.14314, + "nauc_recall_at_1_max": 0.167324, + "nauc_recall_at_1_std": -0.084492, + "nauc_recall_at_1_diff1": 0.242873, + "nauc_recall_at_3_max": 0.298909, + "nauc_recall_at_3_std": -0.126262, + "nauc_recall_at_3_diff1": 0.087313, + "nauc_recall_at_5_max": 0.362109, + "nauc_recall_at_5_std": -0.076389, + "nauc_recall_at_5_diff1": 0.133458, + "nauc_recall_at_10_max": 0.280922, + "nauc_recall_at_10_std": -0.154515, + "nauc_recall_at_10_diff1": 0.117144, + "nauc_recall_at_20_max": 0.264613, + "nauc_recall_at_20_std": -0.254229, + "nauc_recall_at_20_diff1": 0.185627, + "nauc_recall_at_100_max": 0.388606, + "nauc_recall_at_100_std": 0.013816, + "nauc_recall_at_100_diff1": 0.117272, + "nauc_recall_at_1000_max": 0.620445, + "nauc_recall_at_1000_std": -0.496814, + "nauc_recall_at_1000_diff1": 0.609212, + "nauc_precision_at_1_max": 0.271554, + "nauc_precision_at_1_std": 0.03701, + "nauc_precision_at_1_diff1": 0.121477, + "nauc_precision_at_3_max": 0.453155, + "nauc_precision_at_3_std": 0.179964, + "nauc_precision_at_3_diff1": 0.017081, + "nauc_precision_at_5_max": 0.440309, + "nauc_precision_at_5_std": 0.228438, + "nauc_precision_at_5_diff1": 0.029907, + "nauc_precision_at_10_max": 0.275676, + "nauc_precision_at_10_std": 0.131055, + "nauc_precision_at_10_diff1": 0.050446, + "nauc_precision_at_20_max": 0.175361, + "nauc_precision_at_20_std": 0.112927, + "nauc_precision_at_20_diff1": 0.053764, + "nauc_precision_at_100_max": 0.135458, + "nauc_precision_at_100_std": 0.274538, + "nauc_precision_at_100_diff1": -0.014459, + "nauc_precision_at_1000_max": 0.056989, + "nauc_precision_at_1000_std": 0.255034, + "nauc_precision_at_1000_diff1": -0.008338, + "nauc_mrr_at_1_max": 0.271554, + "nauc_mrr_at_1_std": 0.03701, + "nauc_mrr_at_1_diff1": 0.121477, + "nauc_mrr_at_3_max": 0.349853, + "nauc_mrr_at_3_std": 0.03133, + "nauc_mrr_at_3_diff1": 0.103531, + "nauc_mrr_at_5_max": 0.351523, + "nauc_mrr_at_5_std": 0.023734, + "nauc_mrr_at_5_diff1": 0.107179, + "nauc_mrr_at_10_max": 0.334517, + "nauc_mrr_at_10_std": 0.015718, + "nauc_mrr_at_10_diff1": 0.106972, + "nauc_mrr_at_20_max": 0.337417, + "nauc_mrr_at_20_std": 0.025191, + "nauc_mrr_at_20_diff1": 0.112898, + "nauc_mrr_at_100_max": 0.33529, + "nauc_mrr_at_100_std": 0.024261, + "nauc_mrr_at_100_diff1": 0.111472, + "nauc_mrr_at_1000_max": 0.335367, + "nauc_mrr_at_1000_std": 0.024345, + "nauc_mrr_at_1000_diff1": 0.111508, + "main_score": 0.42443, + "hf_subset": "Medical-Sciences", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.08247, + "ndcg_at_3": 0.10212, + "ndcg_at_5": 0.11525, + "ndcg_at_10": 0.12827, + "ndcg_at_20": 0.15003, + "ndcg_at_100": 0.18985, + "ndcg_at_1000": 0.24095, + "map_at_1": 0.03679, + "map_at_3": 0.06554, + "map_at_5": 0.07975, + "map_at_10": 0.08675, + "map_at_20": 0.09391, + "map_at_100": 0.10007, + "map_at_1000": 0.10229, + "recall_at_1": 0.03679, + "recall_at_3": 0.08887, + "recall_at_5": 0.13321, + "recall_at_10": 0.17223, + "recall_at_20": 0.23968, + "recall_at_100": 0.40866, + "recall_at_1000": 0.71217, + "precision_at_1": 0.08247, + "precision_at_3": 0.08247, + "precision_at_5": 0.0701, + "precision_at_10": 0.04639, + "precision_at_20": 0.03144, + "precision_at_100": 0.01082, + "precision_at_1000": 0.00203, + "mrr_at_1": 0.082474, + "mrr_at_3": 0.139175, + "mrr_at_5": 0.152062, + "mrr_at_10": 0.15972, + "mrr_at_20": 0.164501, + "mrr_at_100": 0.169366, + "mrr_at_1000": 0.170739, + "nauc_ndcg_at_1_max": 0.052355, + "nauc_ndcg_at_1_std": 0.238216, + "nauc_ndcg_at_1_diff1": 0.057014, + "nauc_ndcg_at_3_max": -0.023306, + "nauc_ndcg_at_3_std": 0.146929, + "nauc_ndcg_at_3_diff1": 0.015919, + "nauc_ndcg_at_5_max": -0.01403, + "nauc_ndcg_at_5_std": 0.185567, + "nauc_ndcg_at_5_diff1": 0.066398, + "nauc_ndcg_at_10_max": -0.02144, + "nauc_ndcg_at_10_std": 0.162518, + "nauc_ndcg_at_10_diff1": 0.043957, + "nauc_ndcg_at_20_max": 0.04367, + "nauc_ndcg_at_20_std": 0.189735, + "nauc_ndcg_at_20_diff1": 0.079758, + "nauc_ndcg_at_100_max": 0.106885, + "nauc_ndcg_at_100_std": 0.236591, + "nauc_ndcg_at_100_diff1": 0.070022, + "nauc_ndcg_at_1000_max": 0.115198, + "nauc_ndcg_at_1000_std": 0.270547, + "nauc_ndcg_at_1000_diff1": 0.082039, + "nauc_map_at_1_max": -0.128592, + "nauc_map_at_1_std": 0.103072, + "nauc_map_at_1_diff1": 0.066106, + "nauc_map_at_3_max": -0.131889, + "nauc_map_at_3_std": 0.142411, + "nauc_map_at_3_diff1": 0.00629, + "nauc_map_at_5_max": -0.09597, + "nauc_map_at_5_std": 0.160986, + "nauc_map_at_5_diff1": 0.04535, + "nauc_map_at_10_max": -0.086443, + "nauc_map_at_10_std": 0.151273, + "nauc_map_at_10_diff1": 0.03727, + "nauc_map_at_20_max": -0.040703, + "nauc_map_at_20_std": 0.172558, + "nauc_map_at_20_diff1": 0.047451, + "nauc_map_at_100_max": -0.028907, + "nauc_map_at_100_std": 0.178272, + "nauc_map_at_100_diff1": 0.045076, + "nauc_map_at_1000_max": -0.0281, + "nauc_map_at_1000_std": 0.178929, + "nauc_map_at_1000_diff1": 0.046673, + "nauc_recall_at_1_max": -0.128592, + "nauc_recall_at_1_std": 0.103072, + "nauc_recall_at_1_diff1": 0.066106, + "nauc_recall_at_3_max": -0.127328, + "nauc_recall_at_3_std": 0.136531, + "nauc_recall_at_3_diff1": -0.037446, + "nauc_recall_at_5_max": -0.017231, + "nauc_recall_at_5_std": 0.184873, + "nauc_recall_at_5_diff1": 0.085748, + "nauc_recall_at_10_max": -0.028514, + "nauc_recall_at_10_std": 0.118467, + "nauc_recall_at_10_diff1": 0.046856, + "nauc_recall_at_20_max": 0.092281, + "nauc_recall_at_20_std": 0.167381, + "nauc_recall_at_20_diff1": 0.142202, + "nauc_recall_at_100_max": 0.256143, + "nauc_recall_at_100_std": 0.310368, + "nauc_recall_at_100_diff1": 0.106511, + "nauc_recall_at_1000_max": 0.407576, + "nauc_recall_at_1000_std": 0.579549, + "nauc_recall_at_1000_diff1": 0.152335, + "nauc_precision_at_1_max": 0.052355, + "nauc_precision_at_1_std": 0.238216, + "nauc_precision_at_1_diff1": 0.057014, + "nauc_precision_at_3_max": 0.029669, + "nauc_precision_at_3_std": 0.167782, + "nauc_precision_at_3_diff1": 0.006543, + "nauc_precision_at_5_max": 0.06777, + "nauc_precision_at_5_std": 0.214762, + "nauc_precision_at_5_diff1": 0.069877, + "nauc_precision_at_10_max": 0.071432, + "nauc_precision_at_10_std": 0.152574, + "nauc_precision_at_10_diff1": 0.051339, + "nauc_precision_at_20_max": 0.190337, + "nauc_precision_at_20_std": 0.201637, + "nauc_precision_at_20_diff1": 0.077611, + "nauc_precision_at_100_max": 0.300398, + "nauc_precision_at_100_std": 0.266573, + "nauc_precision_at_100_diff1": 0.044497, + "nauc_precision_at_1000_max": 0.209242, + "nauc_precision_at_1000_std": 0.264428, + "nauc_precision_at_1000_diff1": 0.099646, + "nauc_mrr_at_1_max": 0.052355, + "nauc_mrr_at_1_std": 0.238216, + "nauc_mrr_at_1_diff1": 0.057014, + "nauc_mrr_at_3_max": 0.060026, + "nauc_mrr_at_3_std": 0.1993, + "nauc_mrr_at_3_diff1": 0.00586, + "nauc_mrr_at_5_max": 0.090596, + "nauc_mrr_at_5_std": 0.223983, + "nauc_mrr_at_5_diff1": 0.051295, + "nauc_mrr_at_10_max": 0.08217, + "nauc_mrr_at_10_std": 0.210395, + "nauc_mrr_at_10_diff1": 0.037527, + "nauc_mrr_at_20_max": 0.083567, + "nauc_mrr_at_20_std": 0.205527, + "nauc_mrr_at_20_diff1": 0.048475, + "nauc_mrr_at_100_max": 0.086525, + "nauc_mrr_at_100_std": 0.207764, + "nauc_mrr_at_100_diff1": 0.047401, + "nauc_mrr_at_1000_max": 0.086601, + "nauc_mrr_at_1000_std": 0.208065, + "nauc_mrr_at_1000_diff1": 0.047005, + "main_score": 0.12827, + "hf_subset": "MedXpertQA-Exam", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.14407, + "ndcg_at_3": 0.12489, + "ndcg_at_5": 0.12895, + "ndcg_at_10": 0.16451, + "ndcg_at_20": 0.18228, + "ndcg_at_100": 0.2457, + "ndcg_at_1000": 0.29924, + "map_at_1": 0.04309, + "map_at_3": 0.07348, + "map_at_5": 0.08571, + "map_at_10": 0.10719, + "map_at_20": 0.11435, + "map_at_100": 0.1264, + "map_at_1000": 0.12944, + "recall_at_1": 0.04309, + "recall_at_3": 0.09754, + "recall_at_5": 0.12603, + "recall_at_10": 0.20977, + "recall_at_20": 0.2541, + "recall_at_100": 0.47476, + "recall_at_1000": 0.76075, + "precision_at_1": 0.14407, + "precision_at_3": 0.10452, + "precision_at_5": 0.08983, + "precision_at_10": 0.07627, + "precision_at_20": 0.04831, + "precision_at_100": 0.01949, + "precision_at_1000": 0.00319, + "mrr_at_1": 0.144068, + "mrr_at_3": 0.190678, + "mrr_at_5": 0.204237, + "mrr_at_10": 0.218664, + "mrr_at_20": 0.222502, + "mrr_at_100": 0.228999, + "mrr_at_1000": 0.229705, + "nauc_ndcg_at_1_max": 0.058261, + "nauc_ndcg_at_1_std": 0.101492, + "nauc_ndcg_at_1_diff1": 0.060038, + "nauc_ndcg_at_3_max": 0.116251, + "nauc_ndcg_at_3_std": 0.139136, + "nauc_ndcg_at_3_diff1": 0.064018, + "nauc_ndcg_at_5_max": 0.135593, + "nauc_ndcg_at_5_std": 0.131092, + "nauc_ndcg_at_5_diff1": 0.040698, + "nauc_ndcg_at_10_max": 0.209136, + "nauc_ndcg_at_10_std": 0.171819, + "nauc_ndcg_at_10_diff1": 0.062378, + "nauc_ndcg_at_20_max": 0.21309, + "nauc_ndcg_at_20_std": 0.175588, + "nauc_ndcg_at_20_diff1": 0.069851, + "nauc_ndcg_at_100_max": 0.219203, + "nauc_ndcg_at_100_std": 0.198125, + "nauc_ndcg_at_100_diff1": 0.060005, + "nauc_ndcg_at_1000_max": 0.202366, + "nauc_ndcg_at_1000_std": 0.190935, + "nauc_ndcg_at_1000_diff1": 0.087665, + "nauc_map_at_1_max": 0.077926, + "nauc_map_at_1_std": 0.066619, + "nauc_map_at_1_diff1": 0.086078, + "nauc_map_at_3_max": 0.065993, + "nauc_map_at_3_std": 0.097907, + "nauc_map_at_3_diff1": 0.009969, + "nauc_map_at_5_max": 0.105335, + "nauc_map_at_5_std": 0.10493, + "nauc_map_at_5_diff1": 0.007751, + "nauc_map_at_10_max": 0.177483, + "nauc_map_at_10_std": 0.150416, + "nauc_map_at_10_diff1": 0.031198, + "nauc_map_at_20_max": 0.180666, + "nauc_map_at_20_std": 0.154069, + "nauc_map_at_20_diff1": 0.027309, + "nauc_map_at_100_max": 0.19232, + "nauc_map_at_100_std": 0.163621, + "nauc_map_at_100_diff1": 0.035906, + "nauc_map_at_1000_max": 0.190423, + "nauc_map_at_1000_std": 0.162691, + "nauc_map_at_1000_diff1": 0.037213, + "nauc_recall_at_1_max": 0.077926, + "nauc_recall_at_1_std": 0.066619, + "nauc_recall_at_1_diff1": 0.086078, + "nauc_recall_at_3_max": 0.101321, + "nauc_recall_at_3_std": 0.146687, + "nauc_recall_at_3_diff1": 0.025893, + "nauc_recall_at_5_max": 0.136086, + "nauc_recall_at_5_std": 0.136715, + "nauc_recall_at_5_diff1": 0.007142, + "nauc_recall_at_10_max": 0.227417, + "nauc_recall_at_10_std": 0.176561, + "nauc_recall_at_10_diff1": 0.053938, + "nauc_recall_at_20_max": 0.224216, + "nauc_recall_at_20_std": 0.183796, + "nauc_recall_at_20_diff1": 0.053083, + "nauc_recall_at_100_max": 0.233691, + "nauc_recall_at_100_std": 0.247184, + "nauc_recall_at_100_diff1": 0.001869, + "nauc_recall_at_1000_max": 0.202538, + "nauc_recall_at_1000_std": 0.328823, + "nauc_recall_at_1000_diff1": 0.098547, + "nauc_precision_at_1_max": 0.058261, + "nauc_precision_at_1_std": 0.101492, + "nauc_precision_at_1_diff1": 0.060038, + "nauc_precision_at_3_max": 0.181547, + "nauc_precision_at_3_std": 0.199976, + "nauc_precision_at_3_diff1": 0.090074, + "nauc_precision_at_5_max": 0.207331, + "nauc_precision_at_5_std": 0.173287, + "nauc_precision_at_5_diff1": 0.053051, + "nauc_precision_at_10_max": 0.313357, + "nauc_precision_at_10_std": 0.236911, + "nauc_precision_at_10_diff1": 0.107886, + "nauc_precision_at_20_max": 0.311995, + "nauc_precision_at_20_std": 0.221184, + "nauc_precision_at_20_diff1": 0.145055, + "nauc_precision_at_100_max": 0.201742, + "nauc_precision_at_100_std": 0.186442, + "nauc_precision_at_100_diff1": 0.10301, + "nauc_precision_at_1000_max": 0.05381, + "nauc_precision_at_1000_std": 0.04723, + "nauc_precision_at_1000_diff1": 0.155696, + "nauc_mrr_at_1_max": 0.058261, + "nauc_mrr_at_1_std": 0.101492, + "nauc_mrr_at_1_diff1": 0.060038, + "nauc_mrr_at_3_max": 0.13575, + "nauc_mrr_at_3_std": 0.140176, + "nauc_mrr_at_3_diff1": 0.103901, + "nauc_mrr_at_5_max": 0.142899, + "nauc_mrr_at_5_std": 0.136478, + "nauc_mrr_at_5_diff1": 0.09346, + "nauc_mrr_at_10_max": 0.147365, + "nauc_mrr_at_10_std": 0.136239, + "nauc_mrr_at_10_diff1": 0.104875, + "nauc_mrr_at_20_max": 0.148137, + "nauc_mrr_at_20_std": 0.133063, + "nauc_mrr_at_20_diff1": 0.112513, + "nauc_mrr_at_100_max": 0.146725, + "nauc_mrr_at_100_std": 0.13266, + "nauc_mrr_at_100_diff1": 0.105852, + "nauc_mrr_at_1000_max": 0.14736, + "nauc_mrr_at_1000_std": 0.133258, + "nauc_mrr_at_1000_diff1": 0.106695, + "main_score": 0.16451, + "hf_subset": "MedQA-Diag", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.33333, + "ndcg_at_3": 0.30397, + "ndcg_at_5": 0.31515, + "ndcg_at_10": 0.33586, + "ndcg_at_20": 0.35912, + "ndcg_at_100": 0.39361, + "ndcg_at_1000": 0.42994, + "map_at_1": 0.20533, + "map_at_3": 0.25552, + "map_at_5": 0.27007, + "map_at_10": 0.2799, + "map_at_20": 0.28754, + "map_at_100": 0.29336, + "map_at_1000": 0.29522, + "recall_at_1": 0.20533, + "recall_at_3": 0.29256, + "recall_at_5": 0.33078, + "recall_at_10": 0.38167, + "recall_at_20": 0.46011, + "recall_at_100": 0.61456, + "recall_at_1000": 0.84733, + "precision_at_1": 0.33333, + "precision_at_3": 0.17333, + "precision_at_5": 0.124, + "precision_at_10": 0.074, + "precision_at_20": 0.04467, + "precision_at_100": 0.01227, + "precision_at_1000": 0.00177, + "mrr_at_1": 0.333333, + "mrr_at_3": 0.387778, + "mrr_at_5": 0.396444, + "mrr_at_10": 0.403889, + "mrr_at_20": 0.409331, + "mrr_at_100": 0.412988, + "mrr_at_1000": 0.413557, + "nauc_ndcg_at_1_max": 0.39938, + "nauc_ndcg_at_1_std": -0.054036, + "nauc_ndcg_at_1_diff1": 0.642765, + "nauc_ndcg_at_3_max": 0.380847, + "nauc_ndcg_at_3_std": -0.127918, + "nauc_ndcg_at_3_diff1": 0.533892, + "nauc_ndcg_at_5_max": 0.364748, + "nauc_ndcg_at_5_std": -0.113026, + "nauc_ndcg_at_5_diff1": 0.516911, + "nauc_ndcg_at_10_max": 0.362836, + "nauc_ndcg_at_10_std": -0.094392, + "nauc_ndcg_at_10_diff1": 0.52176, + "nauc_ndcg_at_20_max": 0.367331, + "nauc_ndcg_at_20_std": -0.090255, + "nauc_ndcg_at_20_diff1": 0.512836, + "nauc_ndcg_at_100_max": 0.365672, + "nauc_ndcg_at_100_std": -0.065161, + "nauc_ndcg_at_100_diff1": 0.503384, + "nauc_ndcg_at_1000_max": 0.379946, + "nauc_ndcg_at_1000_std": -0.063663, + "nauc_ndcg_at_1000_diff1": 0.526437, + "nauc_map_at_1_max": 0.240516, + "nauc_map_at_1_std": -0.168307, + "nauc_map_at_1_diff1": 0.494423, + "nauc_map_at_3_max": 0.322553, + "nauc_map_at_3_std": -0.164489, + "nauc_map_at_3_diff1": 0.513723, + "nauc_map_at_5_max": 0.340476, + "nauc_map_at_5_std": -0.138333, + "nauc_map_at_5_diff1": 0.516633, + "nauc_map_at_10_max": 0.342031, + "nauc_map_at_10_std": -0.12505, + "nauc_map_at_10_diff1": 0.521107, + "nauc_map_at_20_max": 0.346807, + "nauc_map_at_20_std": -0.121658, + "nauc_map_at_20_diff1": 0.517284, + "nauc_map_at_100_max": 0.348512, + "nauc_map_at_100_std": -0.11795, + "nauc_map_at_100_diff1": 0.515237, + "nauc_map_at_1000_max": 0.350096, + "nauc_map_at_1000_std": -0.117174, + "nauc_map_at_1000_diff1": 0.516366, + "nauc_recall_at_1_max": 0.240516, + "nauc_recall_at_1_std": -0.168307, + "nauc_recall_at_1_diff1": 0.494423, + "nauc_recall_at_3_max": 0.297527, + "nauc_recall_at_3_std": -0.173624, + "nauc_recall_at_3_diff1": 0.439658, + "nauc_recall_at_5_max": 0.304282, + "nauc_recall_at_5_std": -0.135933, + "nauc_recall_at_5_diff1": 0.424478, + "nauc_recall_at_10_max": 0.28081, + "nauc_recall_at_10_std": -0.098019, + "nauc_recall_at_10_diff1": 0.42406, + "nauc_recall_at_20_max": 0.240922, + "nauc_recall_at_20_std": -0.081661, + "nauc_recall_at_20_diff1": 0.351379, + "nauc_recall_at_100_max": 0.15332, + "nauc_recall_at_100_std": 0.041584, + "nauc_recall_at_100_diff1": 0.239154, + "nauc_recall_at_1000_max": 0.150618, + "nauc_recall_at_1000_std": 0.100762, + "nauc_recall_at_1000_diff1": 0.379113, + "nauc_precision_at_1_max": 0.39938, + "nauc_precision_at_1_std": -0.054036, + "nauc_precision_at_1_diff1": 0.642765, + "nauc_precision_at_3_max": 0.566737, + "nauc_precision_at_3_std": -0.016574, + "nauc_precision_at_3_diff1": 0.567772, + "nauc_precision_at_5_max": 0.528771, + "nauc_precision_at_5_std": 0.045841, + "nauc_precision_at_5_diff1": 0.486417, + "nauc_precision_at_10_max": 0.503206, + "nauc_precision_at_10_std": 0.101893, + "nauc_precision_at_10_diff1": 0.469775, + "nauc_precision_at_20_max": 0.501423, + "nauc_precision_at_20_std": 0.100889, + "nauc_precision_at_20_diff1": 0.394819, + "nauc_precision_at_100_max": 0.420724, + "nauc_precision_at_100_std": 0.199097, + "nauc_precision_at_100_diff1": 0.24232, + "nauc_precision_at_1000_max": 0.335774, + "nauc_precision_at_1000_std": 0.177835, + "nauc_precision_at_1000_diff1": 0.204168, + "nauc_mrr_at_1_max": 0.39938, + "nauc_mrr_at_1_std": -0.054036, + "nauc_mrr_at_1_diff1": 0.642765, + "nauc_mrr_at_3_max": 0.460972, + "nauc_mrr_at_3_std": -0.0393, + "nauc_mrr_at_3_diff1": 0.617592, + "nauc_mrr_at_5_max": 0.446716, + "nauc_mrr_at_5_std": -0.042063, + "nauc_mrr_at_5_diff1": 0.60457, + "nauc_mrr_at_10_max": 0.443933, + "nauc_mrr_at_10_std": -0.041219, + "nauc_mrr_at_10_diff1": 0.604538, + "nauc_mrr_at_20_max": 0.444118, + "nauc_mrr_at_20_std": -0.042026, + "nauc_mrr_at_20_diff1": 0.606212, + "nauc_mrr_at_100_max": 0.441947, + "nauc_mrr_at_100_std": -0.041084, + "nauc_mrr_at_100_diff1": 0.605371, + "nauc_mrr_at_1000_max": 0.442421, + "nauc_mrr_at_1000_std": -0.040916, + "nauc_mrr_at_1000_diff1": 0.60576, + "main_score": 0.33586, + "hf_subset": "PMC-Treatment", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.17544, + "ndcg_at_3": 0.21398, + "ndcg_at_5": 0.24533, + "ndcg_at_10": 0.27828, + "ndcg_at_20": 0.30679, + "ndcg_at_100": 0.35758, + "ndcg_at_1000": 0.39195, + "map_at_1": 0.08333, + "map_at_3": 0.16118, + "map_at_5": 0.18238, + "map_at_10": 0.19943, + "map_at_20": 0.20884, + "map_at_100": 0.21932, + "map_at_1000": 0.22119, + "recall_at_1": 0.08333, + "recall_at_3": 0.23977, + "recall_at_5": 0.30848, + "recall_at_10": 0.38596, + "recall_at_20": 0.4788, + "recall_at_100": 0.69225, + "recall_at_1000": 0.90643, + "precision_at_1": 0.17544, + "precision_at_3": 0.16082, + "precision_at_5": 0.12456, + "precision_at_10": 0.08158, + "precision_at_20": 0.05044, + "precision_at_100": 0.01482, + "precision_at_1000": 0.00197, + "mrr_at_1": 0.175439, + "mrr_at_3": 0.280702, + "mrr_at_5": 0.298246, + "mrr_at_10": 0.308149, + "mrr_at_20": 0.315612, + "mrr_at_100": 0.319671, + "mrr_at_1000": 0.320368, + "nauc_ndcg_at_1_max": 0.184639, + "nauc_ndcg_at_1_std": -0.147622, + "nauc_ndcg_at_1_diff1": 0.466726, + "nauc_ndcg_at_3_max": 0.170041, + "nauc_ndcg_at_3_std": -0.145152, + "nauc_ndcg_at_3_diff1": 0.32648, + "nauc_ndcg_at_5_max": 0.173629, + "nauc_ndcg_at_5_std": -0.126703, + "nauc_ndcg_at_5_diff1": 0.354439, + "nauc_ndcg_at_10_max": 0.229224, + "nauc_ndcg_at_10_std": -0.098236, + "nauc_ndcg_at_10_diff1": 0.324916, + "nauc_ndcg_at_20_max": 0.178841, + "nauc_ndcg_at_20_std": -0.078739, + "nauc_ndcg_at_20_diff1": 0.304914, + "nauc_ndcg_at_100_max": 0.181615, + "nauc_ndcg_at_100_std": -0.084867, + "nauc_ndcg_at_100_diff1": 0.282607, + "nauc_ndcg_at_1000_max": 0.185761, + "nauc_ndcg_at_1000_std": -0.10583, + "nauc_ndcg_at_1000_diff1": 0.312806, + "nauc_map_at_1_max": 0.133985, + "nauc_map_at_1_std": -0.111385, + "nauc_map_at_1_diff1": 0.390154, + "nauc_map_at_3_max": 0.174553, + "nauc_map_at_3_std": -0.145397, + "nauc_map_at_3_diff1": 0.330484, + "nauc_map_at_5_max": 0.169697, + "nauc_map_at_5_std": -0.130005, + "nauc_map_at_5_diff1": 0.354501, + "nauc_map_at_10_max": 0.207001, + "nauc_map_at_10_std": -0.115086, + "nauc_map_at_10_diff1": 0.340637, + "nauc_map_at_20_max": 0.187428, + "nauc_map_at_20_std": -0.10722, + "nauc_map_at_20_diff1": 0.331523, + "nauc_map_at_100_max": 0.188222, + "nauc_map_at_100_std": -0.109495, + "nauc_map_at_100_diff1": 0.327307, + "nauc_map_at_1000_max": 0.187427, + "nauc_map_at_1000_std": -0.110725, + "nauc_map_at_1000_diff1": 0.328322, + "nauc_recall_at_1_max": 0.133985, + "nauc_recall_at_1_std": -0.111385, + "nauc_recall_at_1_diff1": 0.390154, + "nauc_recall_at_3_max": 0.146757, + "nauc_recall_at_3_std": -0.130989, + "nauc_recall_at_3_diff1": 0.239544, + "nauc_recall_at_5_max": 0.140308, + "nauc_recall_at_5_std": -0.091238, + "nauc_recall_at_5_diff1": 0.28616, + "nauc_recall_at_10_max": 0.222437, + "nauc_recall_at_10_std": -0.032404, + "nauc_recall_at_10_diff1": 0.204122, + "nauc_recall_at_20_max": 0.095654, + "nauc_recall_at_20_std": 0.010677, + "nauc_recall_at_20_diff1": 0.140945, + "nauc_recall_at_100_max": 0.07336, + "nauc_recall_at_100_std": 0.018982, + "nauc_recall_at_100_diff1": 0.022073, + "nauc_recall_at_1000_max": 0.079421, + "nauc_recall_at_1000_std": -0.096352, + "nauc_recall_at_1000_diff1": 0.192975, + "nauc_precision_at_1_max": 0.184639, + "nauc_precision_at_1_std": -0.147622, + "nauc_precision_at_1_diff1": 0.466726, + "nauc_precision_at_3_max": 0.226255, + "nauc_precision_at_3_std": -0.192372, + "nauc_precision_at_3_diff1": 0.32561, + "nauc_precision_at_5_max": 0.20107, + "nauc_precision_at_5_std": -0.12764, + "nauc_precision_at_5_diff1": 0.321476, + "nauc_precision_at_10_max": 0.291921, + "nauc_precision_at_10_std": -0.033659, + "nauc_precision_at_10_diff1": 0.197726, + "nauc_precision_at_20_max": 0.164776, + "nauc_precision_at_20_std": 0.0257, + "nauc_precision_at_20_diff1": 0.140487, + "nauc_precision_at_100_max": 0.150108, + "nauc_precision_at_100_std": 0.026385, + "nauc_precision_at_100_diff1": 0.012674, + "nauc_precision_at_1000_max": 0.117517, + "nauc_precision_at_1000_std": -0.05001, + "nauc_precision_at_1000_diff1": 0.029165, + "nauc_mrr_at_1_max": 0.184639, + "nauc_mrr_at_1_std": -0.147622, + "nauc_mrr_at_1_diff1": 0.466726, + "nauc_mrr_at_3_max": 0.180695, + "nauc_mrr_at_3_std": -0.144208, + "nauc_mrr_at_3_diff1": 0.393847, + "nauc_mrr_at_5_max": 0.188024, + "nauc_mrr_at_5_std": -0.144252, + "nauc_mrr_at_5_diff1": 0.402625, + "nauc_mrr_at_10_max": 0.199498, + "nauc_mrr_at_10_std": -0.135966, + "nauc_mrr_at_10_diff1": 0.394146, + "nauc_mrr_at_20_max": 0.187016, + "nauc_mrr_at_20_std": -0.132906, + "nauc_mrr_at_20_diff1": 0.393915, + "nauc_mrr_at_100_max": 0.188548, + "nauc_mrr_at_100_std": -0.135424, + "nauc_mrr_at_100_diff1": 0.394467, + "nauc_mrr_at_1000_max": 0.188931, + "nauc_mrr_at_1000_std": -0.135641, + "nauc_mrr_at_1000_diff1": 0.395256, + "main_score": 0.27828, + "hf_subset": "PMC-Clinical", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.17829, + "ndcg_at_3": 0.15964, + "ndcg_at_5": 0.17115, + "ndcg_at_10": 0.222, + "ndcg_at_20": 0.26658, + "ndcg_at_100": 0.36029, + "ndcg_at_1000": 0.39635, + "map_at_1": 0.05504, + "map_at_3": 0.09186, + "map_at_5": 0.11186, + "map_at_10": 0.13904, + "map_at_20": 0.15571, + "map_at_100": 0.17716, + "map_at_1000": 0.17995, + "recall_at_1": 0.05504, + "recall_at_3": 0.11809, + "recall_at_5": 0.17506, + "recall_at_10": 0.29561, + "recall_at_20": 0.41434, + "recall_at_100": 0.7624, + "recall_at_1000": 0.95168, + "precision_at_1": 0.17829, + "precision_at_3": 0.13695, + "precision_at_5": 0.12248, + "precision_at_10": 0.10233, + "precision_at_20": 0.07364, + "precision_at_100": 0.02698, + "precision_at_1000": 0.00339, + "mrr_at_1": 0.178295, + "mrr_at_3": 0.245478, + "mrr_at_5": 0.268734, + "mrr_at_10": 0.288495, + "mrr_at_20": 0.297328, + "mrr_at_100": 0.303014, + "mrr_at_1000": 0.30323, + "nauc_ndcg_at_1_max": 0.065525, + "nauc_ndcg_at_1_std": 0.246587, + "nauc_ndcg_at_1_diff1": 0.222716, + "nauc_ndcg_at_3_max": 0.096594, + "nauc_ndcg_at_3_std": 0.123122, + "nauc_ndcg_at_3_diff1": 0.136653, + "nauc_ndcg_at_5_max": 0.137872, + "nauc_ndcg_at_5_std": 0.13035, + "nauc_ndcg_at_5_diff1": 0.146379, + "nauc_ndcg_at_10_max": 0.185943, + "nauc_ndcg_at_10_std": 0.09492, + "nauc_ndcg_at_10_diff1": 0.132858, + "nauc_ndcg_at_20_max": 0.180261, + "nauc_ndcg_at_20_std": 0.104528, + "nauc_ndcg_at_20_diff1": 0.104225, + "nauc_ndcg_at_100_max": 0.141699, + "nauc_ndcg_at_100_std": 0.200282, + "nauc_ndcg_at_100_diff1": 0.053483, + "nauc_ndcg_at_1000_max": 0.155594, + "nauc_ndcg_at_1000_std": 0.220288, + "nauc_ndcg_at_1000_diff1": 0.076308, + "nauc_map_at_1_max": -0.034193, + "nauc_map_at_1_std": 0.110923, + "nauc_map_at_1_diff1": 0.250879, + "nauc_map_at_3_max": 0.044378, + "nauc_map_at_3_std": 0.098588, + "nauc_map_at_3_diff1": 0.177921, + "nauc_map_at_5_max": 0.101107, + "nauc_map_at_5_std": 0.125027, + "nauc_map_at_5_diff1": 0.170605, + "nauc_map_at_10_max": 0.161035, + "nauc_map_at_10_std": 0.099145, + "nauc_map_at_10_diff1": 0.168807, + "nauc_map_at_20_max": 0.15603, + "nauc_map_at_20_std": 0.107909, + "nauc_map_at_20_diff1": 0.144886, + "nauc_map_at_100_max": 0.145948, + "nauc_map_at_100_std": 0.135498, + "nauc_map_at_100_diff1": 0.131981, + "nauc_map_at_1000_max": 0.148463, + "nauc_map_at_1000_std": 0.138522, + "nauc_map_at_1000_diff1": 0.135087, + "nauc_recall_at_1_max": -0.034193, + "nauc_recall_at_1_std": 0.110923, + "nauc_recall_at_1_diff1": 0.250879, + "nauc_recall_at_3_max": 0.03365, + "nauc_recall_at_3_std": 0.026484, + "nauc_recall_at_3_diff1": 0.084044, + "nauc_recall_at_5_max": 0.150416, + "nauc_recall_at_5_std": 0.061191, + "nauc_recall_at_5_diff1": 0.110713, + "nauc_recall_at_10_max": 0.180744, + "nauc_recall_at_10_std": -0.011272, + "nauc_recall_at_10_diff1": 0.073469, + "nauc_recall_at_20_max": 0.166469, + "nauc_recall_at_20_std": -0.001739, + "nauc_recall_at_20_diff1": 0.022126, + "nauc_recall_at_100_max": -0.012796, + "nauc_recall_at_100_std": 0.210838, + "nauc_recall_at_100_diff1": -0.211399, + "nauc_recall_at_1000_max": -0.12055, + "nauc_recall_at_1000_std": 0.74937, + "nauc_recall_at_1000_diff1": -0.525096, + "nauc_precision_at_1_max": 0.065525, + "nauc_precision_at_1_std": 0.246587, + "nauc_precision_at_1_diff1": 0.222716, + "nauc_precision_at_3_max": 0.165642, + "nauc_precision_at_3_std": 0.133096, + "nauc_precision_at_3_diff1": 0.111577, + "nauc_precision_at_5_max": 0.244374, + "nauc_precision_at_5_std": 0.193746, + "nauc_precision_at_5_diff1": 0.114463, + "nauc_precision_at_10_max": 0.299093, + "nauc_precision_at_10_std": 0.126857, + "nauc_precision_at_10_diff1": 0.063373, + "nauc_precision_at_20_max": 0.243811, + "nauc_precision_at_20_std": 0.137523, + "nauc_precision_at_20_diff1": -0.004373, + "nauc_precision_at_100_max": 0.143313, + "nauc_precision_at_100_std": 0.329418, + "nauc_precision_at_100_diff1": -0.103975, + "nauc_precision_at_1000_max": 0.156369, + "nauc_precision_at_1000_std": 0.36021, + "nauc_precision_at_1000_diff1": -0.077973, + "nauc_mrr_at_1_max": 0.065525, + "nauc_mrr_at_1_std": 0.246587, + "nauc_mrr_at_1_diff1": 0.222716, + "nauc_mrr_at_3_max": 0.109156, + "nauc_mrr_at_3_std": 0.154709, + "nauc_mrr_at_3_diff1": 0.141625, + "nauc_mrr_at_5_max": 0.127699, + "nauc_mrr_at_5_std": 0.152015, + "nauc_mrr_at_5_diff1": 0.150456, + "nauc_mrr_at_10_max": 0.125245, + "nauc_mrr_at_10_std": 0.160099, + "nauc_mrr_at_10_diff1": 0.139873, + "nauc_mrr_at_20_max": 0.127378, + "nauc_mrr_at_20_std": 0.163131, + "nauc_mrr_at_20_diff1": 0.142274, + "nauc_mrr_at_100_max": 0.123349, + "nauc_mrr_at_100_std": 0.168725, + "nauc_mrr_at_100_diff1": 0.13864, + "nauc_mrr_at_1000_max": 0.123246, + "nauc_mrr_at_1000_std": 0.168338, + "nauc_mrr_at_1000_diff1": 0.139077, + "main_score": 0.222, + "hf_subset": "IIYi-Clinical", + "languages": [ + "eng-Latn" + ] + } + ] + }, + "evaluation_time": 3345.7441053390503, + "kg_co2_emissions": null +} \ No newline at end of file diff --git a/results/infly__inf-retriever-v1-1.5b/c9c05c2dd50707a486966ba81703021ae2094a06/R2MEDRetrieval.json b/results/infly__inf-retriever-v1-1.5b/c9c05c2dd50707a486966ba81703021ae2094a06/R2MEDRetrieval.json new file mode 100644 index 0000000000..598193fbbb --- /dev/null +++ b/results/infly__inf-retriever-v1-1.5b/c9c05c2dd50707a486966ba81703021ae2094a06/R2MEDRetrieval.json @@ -0,0 +1,1187 @@ +{ + "dataset_revision": "1.0", + "task_name": "R2MEDRetrieval", + "mteb_version": "1.38.20", + "scores": { + "test": [ + { + "ndcg_at_1": 0.1165, + "ndcg_at_3": 0.12481, + "ndcg_at_5": 0.12322, + "ndcg_at_10": 0.14151, + "ndcg_at_20": 0.16623, + "ndcg_at_100": 0.23417, + "ndcg_at_1000": 0.30183, + "map_at_1": 0.02844, + "map_at_3": 0.06915, + "map_at_5": 0.07723, + "map_at_10": 0.09098, + "map_at_20": 0.10117, + "map_at_100": 0.11389, + "map_at_1000": 0.11769, + "recall_at_1": 0.02844, + "recall_at_3": 0.09719, + "recall_at_5": 0.11907, + "recall_at_10": 0.17672, + "recall_at_20": 0.23899, + "recall_at_100": 0.51504, + "recall_at_1000": 0.892, + "precision_at_1": 0.1165, + "precision_at_3": 0.11327, + "precision_at_5": 0.08738, + "precision_at_10": 0.06505, + "precision_at_20": 0.0466, + "precision_at_100": 0.01845, + "precision_at_1000": 0.00318, + "mrr_at_1": 0.116505, + "mrr_at_3": 0.171521, + "mrr_at_5": 0.18123, + "mrr_at_10": 0.192699, + "mrr_at_20": 0.197426, + "mrr_at_100": 0.203049, + "mrr_at_1000": 0.204282, + "nauc_ndcg_at_1_max": -0.090139, + "nauc_ndcg_at_1_std": -0.250793, + "nauc_ndcg_at_1_diff1": -0.081726, + "nauc_ndcg_at_3_max": 0.005014, + "nauc_ndcg_at_3_std": -0.212483, + "nauc_ndcg_at_3_diff1": -0.101094, + "nauc_ndcg_at_5_max": 0.021358, + "nauc_ndcg_at_5_std": -0.235587, + "nauc_ndcg_at_5_diff1": -0.105728, + "nauc_ndcg_at_10_max": 0.082814, + "nauc_ndcg_at_10_std": -0.226581, + "nauc_ndcg_at_10_diff1": -0.101969, + "nauc_ndcg_at_20_max": 0.056684, + "nauc_ndcg_at_20_std": -0.259554, + "nauc_ndcg_at_20_diff1": -0.133493, + "nauc_ndcg_at_100_max": 0.036553, + "nauc_ndcg_at_100_std": -0.232114, + "nauc_ndcg_at_100_diff1": -0.12829, + "nauc_ndcg_at_1000_max": 0.056389, + "nauc_ndcg_at_1000_std": -0.196754, + "nauc_ndcg_at_1000_diff1": -0.113402, + "nauc_map_at_1_max": 0.053636, + "nauc_map_at_1_std": -0.21742, + "nauc_map_at_1_diff1": 0.001436, + "nauc_map_at_3_max": 0.130984, + "nauc_map_at_3_std": -0.208909, + "nauc_map_at_3_diff1": -0.040982, + "nauc_map_at_5_max": 0.112843, + "nauc_map_at_5_std": -0.219422, + "nauc_map_at_5_diff1": -0.069518, + "nauc_map_at_10_max": 0.125605, + "nauc_map_at_10_std": -0.214372, + "nauc_map_at_10_diff1": -0.090231, + "nauc_map_at_20_max": 0.094185, + "nauc_map_at_20_std": -0.238729, + "nauc_map_at_20_diff1": -0.1212, + "nauc_map_at_100_max": 0.082961, + "nauc_map_at_100_std": -0.234192, + "nauc_map_at_100_diff1": -0.131169, + "nauc_map_at_1000_max": 0.082502, + "nauc_map_at_1000_std": -0.23123, + "nauc_map_at_1000_diff1": -0.12944, + "nauc_recall_at_1_max": 0.053636, + "nauc_recall_at_1_std": -0.21742, + "nauc_recall_at_1_diff1": 0.001436, + "nauc_recall_at_3_max": 0.138396, + "nauc_recall_at_3_std": -0.215419, + "nauc_recall_at_3_diff1": -0.02923, + "nauc_recall_at_5_max": 0.100547, + "nauc_recall_at_5_std": -0.244824, + "nauc_recall_at_5_diff1": -0.068577, + "nauc_recall_at_10_max": 0.160233, + "nauc_recall_at_10_std": -0.228861, + "nauc_recall_at_10_diff1": -0.10207, + "nauc_recall_at_20_max": 0.10876, + "nauc_recall_at_20_std": -0.273002, + "nauc_recall_at_20_diff1": -0.151707, + "nauc_recall_at_100_max": 0.040701, + "nauc_recall_at_100_std": -0.153377, + "nauc_recall_at_100_diff1": -0.093847, + "nauc_recall_at_1000_max": 0.310884, + "nauc_recall_at_1000_std": 0.352327, + "nauc_recall_at_1000_diff1": 0.168487, + "nauc_precision_at_1_max": -0.090139, + "nauc_precision_at_1_std": -0.250793, + "nauc_precision_at_1_diff1": -0.081726, + "nauc_precision_at_3_max": -0.044661, + "nauc_precision_at_3_std": -0.203957, + "nauc_precision_at_3_diff1": -0.103394, + "nauc_precision_at_5_max": -0.059271, + "nauc_precision_at_5_std": -0.225712, + "nauc_precision_at_5_diff1": -0.154784, + "nauc_precision_at_10_max": -0.040155, + "nauc_precision_at_10_std": -0.212558, + "nauc_precision_at_10_diff1": -0.205837, + "nauc_precision_at_20_max": -0.091704, + "nauc_precision_at_20_std": -0.246798, + "nauc_precision_at_20_diff1": -0.239017, + "nauc_precision_at_100_max": -0.098932, + "nauc_precision_at_100_std": -0.156984, + "nauc_precision_at_100_diff1": -0.218362, + "nauc_precision_at_1000_max": -0.098381, + "nauc_precision_at_1000_std": -0.063549, + "nauc_precision_at_1000_diff1": -0.225352, + "nauc_mrr_at_1_max": -0.090139, + "nauc_mrr_at_1_std": -0.250793, + "nauc_mrr_at_1_diff1": -0.081726, + "nauc_mrr_at_3_max": -0.04087, + "nauc_mrr_at_3_std": -0.20925, + "nauc_mrr_at_3_diff1": -0.063858, + "nauc_mrr_at_5_max": -0.041217, + "nauc_mrr_at_5_std": -0.223769, + "nauc_mrr_at_5_diff1": -0.061376, + "nauc_mrr_at_10_max": -0.033798, + "nauc_mrr_at_10_std": -0.23285, + "nauc_mrr_at_10_diff1": -0.073903, + "nauc_mrr_at_20_max": -0.027804, + "nauc_mrr_at_20_std": -0.234902, + "nauc_mrr_at_20_diff1": -0.073161, + "nauc_mrr_at_100_max": -0.030573, + "nauc_mrr_at_100_std": -0.235672, + "nauc_mrr_at_100_diff1": -0.072238, + "nauc_mrr_at_1000_max": -0.030814, + "nauc_mrr_at_1000_std": -0.235072, + "nauc_mrr_at_1000_diff1": -0.072299, + "main_score": 0.14151, + "hf_subset": "Biology", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.37662, + "ndcg_at_3": 0.3503, + "ndcg_at_5": 0.37996, + "ndcg_at_10": 0.42845, + "ndcg_at_20": 0.46601, + "ndcg_at_100": 0.53025, + "ndcg_at_1000": 0.5488, + "map_at_1": 0.19828, + "map_at_3": 0.26524, + "map_at_5": 0.30189, + "map_at_10": 0.33706, + "map_at_20": 0.35364, + "map_at_100": 0.37025, + "map_at_1000": 0.37177, + "recall_at_1": 0.19828, + "recall_at_3": 0.3166, + "recall_at_5": 0.40764, + "recall_at_10": 0.53636, + "recall_at_20": 0.64151, + "recall_at_100": 0.89193, + "recall_at_1000": 0.99567, + "precision_at_1": 0.37662, + "precision_at_3": 0.22944, + "precision_at_5": 0.19481, + "precision_at_10": 0.14026, + "precision_at_20": 0.08896, + "precision_at_100": 0.02571, + "precision_at_1000": 0.00294, + "mrr_at_1": 0.376623, + "mrr_at_3": 0.4329, + "mrr_at_5": 0.451732, + "mrr_at_10": 0.473371, + "mrr_at_20": 0.476608, + "mrr_at_100": 0.481088, + "mrr_at_1000": 0.481204, + "nauc_ndcg_at_1_max": -0.013729, + "nauc_ndcg_at_1_std": -0.045758, + "nauc_ndcg_at_1_diff1": 0.085272, + "nauc_ndcg_at_3_max": -0.045057, + "nauc_ndcg_at_3_std": -0.143725, + "nauc_ndcg_at_3_diff1": 0.080505, + "nauc_ndcg_at_5_max": -0.023853, + "nauc_ndcg_at_5_std": -0.13571, + "nauc_ndcg_at_5_diff1": 0.074693, + "nauc_ndcg_at_10_max": 0.026752, + "nauc_ndcg_at_10_std": -0.151271, + "nauc_ndcg_at_10_diff1": 0.065599, + "nauc_ndcg_at_20_max": 0.053792, + "nauc_ndcg_at_20_std": -0.116791, + "nauc_ndcg_at_20_diff1": 0.047283, + "nauc_ndcg_at_100_max": 0.059841, + "nauc_ndcg_at_100_std": -0.075827, + "nauc_ndcg_at_100_diff1": 0.057913, + "nauc_ndcg_at_1000_max": 0.044191, + "nauc_ndcg_at_1000_std": -0.061519, + "nauc_ndcg_at_1000_diff1": 0.052003, + "nauc_map_at_1_max": 0.021927, + "nauc_map_at_1_std": -0.151584, + "nauc_map_at_1_diff1": 0.209683, + "nauc_map_at_3_max": -0.00051, + "nauc_map_at_3_std": -0.211286, + "nauc_map_at_3_diff1": 0.183556, + "nauc_map_at_5_max": 0.000488, + "nauc_map_at_5_std": -0.183095, + "nauc_map_at_5_diff1": 0.143988, + "nauc_map_at_10_max": 0.008501, + "nauc_map_at_10_std": -0.174447, + "nauc_map_at_10_diff1": 0.120297, + "nauc_map_at_20_max": 0.020564, + "nauc_map_at_20_std": -0.157518, + "nauc_map_at_20_diff1": 0.110603, + "nauc_map_at_100_max": 0.028104, + "nauc_map_at_100_std": -0.140181, + "nauc_map_at_100_diff1": 0.107905, + "nauc_map_at_1000_max": 0.02613, + "nauc_map_at_1000_std": -0.139359, + "nauc_map_at_1000_diff1": 0.106861, + "nauc_recall_at_1_max": 0.021927, + "nauc_recall_at_1_std": -0.151584, + "nauc_recall_at_1_diff1": 0.209683, + "nauc_recall_at_3_max": 0.004589, + "nauc_recall_at_3_std": -0.249581, + "nauc_recall_at_3_diff1": 0.152878, + "nauc_recall_at_5_max": 0.00773, + "nauc_recall_at_5_std": -0.219562, + "nauc_recall_at_5_diff1": 0.078477, + "nauc_recall_at_10_max": 0.089725, + "nauc_recall_at_10_std": -0.229095, + "nauc_recall_at_10_diff1": 0.018466, + "nauc_recall_at_20_max": 0.157497, + "nauc_recall_at_20_std": -0.191103, + "nauc_recall_at_20_diff1": -0.039213, + "nauc_recall_at_100_max": 0.273226, + "nauc_recall_at_100_std": -0.173251, + "nauc_recall_at_100_diff1": 0.153828, + "nauc_recall_at_1000_max": 0.125638, + "nauc_recall_at_1000_std": -1.164365, + "nauc_recall_at_1000_diff1": 0.722603, + "nauc_precision_at_1_max": -0.013729, + "nauc_precision_at_1_std": -0.045758, + "nauc_precision_at_1_diff1": 0.085272, + "nauc_precision_at_3_max": -0.096818, + "nauc_precision_at_3_std": -0.090682, + "nauc_precision_at_3_diff1": -0.071517, + "nauc_precision_at_5_max": -0.072448, + "nauc_precision_at_5_std": 0.052715, + "nauc_precision_at_5_diff1": -0.127984, + "nauc_precision_at_10_max": -0.002656, + "nauc_precision_at_10_std": 0.116563, + "nauc_precision_at_10_diff1": -0.166618, + "nauc_precision_at_20_max": 0.085097, + "nauc_precision_at_20_std": 0.254736, + "nauc_precision_at_20_diff1": -0.184265, + "nauc_precision_at_100_max": 0.094284, + "nauc_precision_at_100_std": 0.401001, + "nauc_precision_at_100_diff1": -0.167649, + "nauc_precision_at_1000_max": 0.072889, + "nauc_precision_at_1000_std": 0.459128, + "nauc_precision_at_1000_diff1": -0.145241, + "nauc_mrr_at_1_max": -0.013729, + "nauc_mrr_at_1_std": -0.045758, + "nauc_mrr_at_1_diff1": 0.085272, + "nauc_mrr_at_3_max": -0.018071, + "nauc_mrr_at_3_std": -0.057778, + "nauc_mrr_at_3_diff1": 0.009839, + "nauc_mrr_at_5_max": -0.016805, + "nauc_mrr_at_5_std": -0.053879, + "nauc_mrr_at_5_diff1": 0.017054, + "nauc_mrr_at_10_max": -0.000731, + "nauc_mrr_at_10_std": -0.044219, + "nauc_mrr_at_10_diff1": 0.015814, + "nauc_mrr_at_20_max": -0.002394, + "nauc_mrr_at_20_std": -0.041827, + "nauc_mrr_at_20_diff1": 0.013425, + "nauc_mrr_at_100_max": -0.006286, + "nauc_mrr_at_100_std": -0.045096, + "nauc_mrr_at_100_diff1": 0.014344, + "nauc_mrr_at_1000_max": -0.006564, + "nauc_mrr_at_1000_std": -0.045255, + "nauc_mrr_at_1000_diff1": 0.014168, + "main_score": 0.42845, + "hf_subset": "Bioinformatics", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.35227, + "ndcg_at_3": 0.33966, + "ndcg_at_5": 0.37311, + "ndcg_at_10": 0.40939, + "ndcg_at_20": 0.44864, + "ndcg_at_100": 0.51243, + "ndcg_at_1000": 0.53628, + "map_at_1": 0.22265, + "map_at_3": 0.28462, + "map_at_5": 0.31095, + "map_at_10": 0.33398, + "map_at_20": 0.34998, + "map_at_100": 0.36481, + "map_at_1000": 0.36635, + "recall_at_1": 0.22265, + "recall_at_3": 0.32976, + "recall_at_5": 0.41314, + "recall_at_10": 0.49899, + "recall_at_20": 0.60981, + "recall_at_100": 0.85022, + "recall_at_1000": 0.98674, + "precision_at_1": 0.35227, + "precision_at_3": 0.19697, + "precision_at_5": 0.16364, + "precision_at_10": 0.10909, + "precision_at_20": 0.07273, + "precision_at_100": 0.02295, + "precision_at_1000": 0.00275, + "mrr_at_1": 0.352273, + "mrr_at_3": 0.407197, + "mrr_at_5": 0.439583, + "mrr_at_10": 0.449288, + "mrr_at_20": 0.455925, + "mrr_at_100": 0.459558, + "mrr_at_1000": 0.459938, + "nauc_ndcg_at_1_max": 0.35785, + "nauc_ndcg_at_1_std": 0.115245, + "nauc_ndcg_at_1_diff1": 0.176133, + "nauc_ndcg_at_3_max": 0.349124, + "nauc_ndcg_at_3_std": 0.027053, + "nauc_ndcg_at_3_diff1": 0.230256, + "nauc_ndcg_at_5_max": 0.339616, + "nauc_ndcg_at_5_std": -0.00517, + "nauc_ndcg_at_5_diff1": 0.260244, + "nauc_ndcg_at_10_max": 0.342785, + "nauc_ndcg_at_10_std": -0.020028, + "nauc_ndcg_at_10_diff1": 0.227808, + "nauc_ndcg_at_20_max": 0.364522, + "nauc_ndcg_at_20_std": 0.006868, + "nauc_ndcg_at_20_diff1": 0.249259, + "nauc_ndcg_at_100_max": 0.406589, + "nauc_ndcg_at_100_std": 0.062779, + "nauc_ndcg_at_100_diff1": 0.25118, + "nauc_ndcg_at_1000_max": 0.396177, + "nauc_ndcg_at_1000_std": 0.048899, + "nauc_ndcg_at_1000_diff1": 0.260673, + "nauc_map_at_1_max": 0.233169, + "nauc_map_at_1_std": -0.142452, + "nauc_map_at_1_diff1": 0.267223, + "nauc_map_at_3_max": 0.299677, + "nauc_map_at_3_std": -0.043793, + "nauc_map_at_3_diff1": 0.261912, + "nauc_map_at_5_max": 0.304279, + "nauc_map_at_5_std": -0.037122, + "nauc_map_at_5_diff1": 0.273489, + "nauc_map_at_10_max": 0.314165, + "nauc_map_at_10_std": -0.034127, + "nauc_map_at_10_diff1": 0.250909, + "nauc_map_at_20_max": 0.329801, + "nauc_map_at_20_std": -0.020264, + "nauc_map_at_20_diff1": 0.251023, + "nauc_map_at_100_max": 0.344072, + "nauc_map_at_100_std": -0.00858, + "nauc_map_at_100_diff1": 0.257857, + "nauc_map_at_1000_max": 0.34314, + "nauc_map_at_1000_std": -0.009111, + "nauc_map_at_1000_diff1": 0.258458, + "nauc_recall_at_1_max": 0.233169, + "nauc_recall_at_1_std": -0.142452, + "nauc_recall_at_1_diff1": 0.267223, + "nauc_recall_at_3_max": 0.298026, + "nauc_recall_at_3_std": -0.052294, + "nauc_recall_at_3_diff1": 0.270787, + "nauc_recall_at_5_max": 0.26162, + "nauc_recall_at_5_std": -0.0698, + "nauc_recall_at_5_diff1": 0.26815, + "nauc_recall_at_10_max": 0.266982, + "nauc_recall_at_10_std": -0.093914, + "nauc_recall_at_10_diff1": 0.18522, + "nauc_recall_at_20_max": 0.297353, + "nauc_recall_at_20_std": -0.06513, + "nauc_recall_at_20_diff1": 0.263017, + "nauc_recall_at_100_max": 0.485072, + "nauc_recall_at_100_std": 0.201069, + "nauc_recall_at_100_diff1": 0.19265, + "nauc_recall_at_1000_max": 0.536536, + "nauc_recall_at_1000_std": -0.311413, + "nauc_recall_at_1000_diff1": 0.669291, + "nauc_precision_at_1_max": 0.35785, + "nauc_precision_at_1_std": 0.115245, + "nauc_precision_at_1_diff1": 0.176133, + "nauc_precision_at_3_max": 0.419554, + "nauc_precision_at_3_std": 0.263901, + "nauc_precision_at_3_diff1": 0.096393, + "nauc_precision_at_5_max": 0.443675, + "nauc_precision_at_5_std": 0.256107, + "nauc_precision_at_5_diff1": 0.140765, + "nauc_precision_at_10_max": 0.397919, + "nauc_precision_at_10_std": 0.15768, + "nauc_precision_at_10_diff1": 0.032889, + "nauc_precision_at_20_max": 0.379335, + "nauc_precision_at_20_std": 0.241185, + "nauc_precision_at_20_diff1": 0.04018, + "nauc_precision_at_100_max": 0.309274, + "nauc_precision_at_100_std": 0.350503, + "nauc_precision_at_100_diff1": -0.001836, + "nauc_precision_at_1000_max": 0.178894, + "nauc_precision_at_1000_std": 0.269065, + "nauc_precision_at_1000_diff1": 0.006554, + "nauc_mrr_at_1_max": 0.35785, + "nauc_mrr_at_1_std": 0.115245, + "nauc_mrr_at_1_diff1": 0.176133, + "nauc_mrr_at_3_max": 0.402743, + "nauc_mrr_at_3_std": 0.102939, + "nauc_mrr_at_3_diff1": 0.193957, + "nauc_mrr_at_5_max": 0.416236, + "nauc_mrr_at_5_std": 0.094619, + "nauc_mrr_at_5_diff1": 0.192756, + "nauc_mrr_at_10_max": 0.408229, + "nauc_mrr_at_10_std": 0.085073, + "nauc_mrr_at_10_diff1": 0.192703, + "nauc_mrr_at_20_max": 0.407837, + "nauc_mrr_at_20_std": 0.095811, + "nauc_mrr_at_20_diff1": 0.209692, + "nauc_mrr_at_100_max": 0.408374, + "nauc_mrr_at_100_std": 0.096666, + "nauc_mrr_at_100_diff1": 0.203919, + "nauc_mrr_at_1000_max": 0.407927, + "nauc_mrr_at_1000_std": 0.096189, + "nauc_mrr_at_1000_diff1": 0.203798, + "main_score": 0.40939, + "hf_subset": "Medical-Sciences", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.07216, + "ndcg_at_3": 0.07635, + "ndcg_at_5": 0.07635, + "ndcg_at_10": 0.08115, + "ndcg_at_20": 0.10195, + "ndcg_at_100": 0.13748, + "ndcg_at_1000": 0.19841, + "map_at_1": 0.036, + "map_at_3": 0.05515, + "map_at_5": 0.05721, + "map_at_10": 0.05922, + "map_at_20": 0.06567, + "map_at_100": 0.07083, + "map_at_1000": 0.07297, + "recall_at_1": 0.036, + "recall_at_3": 0.07132, + "recall_at_5": 0.08163, + "recall_at_10": 0.09461, + "recall_at_20": 0.16027, + "recall_at_100": 0.31161, + "recall_at_1000": 0.68801, + "precision_at_1": 0.07216, + "precision_at_3": 0.05155, + "precision_at_5": 0.03711, + "precision_at_10": 0.02371, + "precision_at_20": 0.01959, + "precision_at_100": 0.00773, + "precision_at_1000": 0.00191, + "mrr_at_1": 0.072165, + "mrr_at_3": 0.101375, + "mrr_at_5": 0.10756, + "mrr_at_10": 0.112682, + "mrr_at_20": 0.117505, + "mrr_at_100": 0.122807, + "mrr_at_1000": 0.124249, + "nauc_ndcg_at_1_max": 0.20364, + "nauc_ndcg_at_1_std": -0.039051, + "nauc_ndcg_at_1_diff1": 0.287334, + "nauc_ndcg_at_3_max": 0.029618, + "nauc_ndcg_at_3_std": 0.046643, + "nauc_ndcg_at_3_diff1": 0.108438, + "nauc_ndcg_at_5_max": 0.062437, + "nauc_ndcg_at_5_std": 0.133266, + "nauc_ndcg_at_5_diff1": 0.135818, + "nauc_ndcg_at_10_max": 0.056848, + "nauc_ndcg_at_10_std": 0.1255, + "nauc_ndcg_at_10_diff1": 0.149408, + "nauc_ndcg_at_20_max": 0.051286, + "nauc_ndcg_at_20_std": 0.145383, + "nauc_ndcg_at_20_diff1": 0.127933, + "nauc_ndcg_at_100_max": 0.06053, + "nauc_ndcg_at_100_std": 0.168072, + "nauc_ndcg_at_100_diff1": 0.145787, + "nauc_ndcg_at_1000_max": 0.130021, + "nauc_ndcg_at_1000_std": 0.171496, + "nauc_ndcg_at_1000_diff1": 0.164136, + "nauc_map_at_1_max": 0.068176, + "nauc_map_at_1_std": 0.135315, + "nauc_map_at_1_diff1": 0.33058, + "nauc_map_at_3_max": 0.045348, + "nauc_map_at_3_std": 0.121099, + "nauc_map_at_3_diff1": 0.181053, + "nauc_map_at_5_max": 0.053767, + "nauc_map_at_5_std": 0.14889, + "nauc_map_at_5_diff1": 0.185377, + "nauc_map_at_10_max": 0.057339, + "nauc_map_at_10_std": 0.144885, + "nauc_map_at_10_diff1": 0.194272, + "nauc_map_at_20_max": 0.062051, + "nauc_map_at_20_std": 0.145685, + "nauc_map_at_20_diff1": 0.187621, + "nauc_map_at_100_max": 0.06233, + "nauc_map_at_100_std": 0.157305, + "nauc_map_at_100_diff1": 0.1873, + "nauc_map_at_1000_max": 0.065241, + "nauc_map_at_1000_std": 0.155363, + "nauc_map_at_1000_diff1": 0.189107, + "nauc_recall_at_1_max": 0.068176, + "nauc_recall_at_1_std": 0.135315, + "nauc_recall_at_1_diff1": 0.33058, + "nauc_recall_at_3_max": -0.016036, + "nauc_recall_at_3_std": 0.137678, + "nauc_recall_at_3_diff1": 0.05123, + "nauc_recall_at_5_max": 0.019781, + "nauc_recall_at_5_std": 0.234295, + "nauc_recall_at_5_diff1": 0.077733, + "nauc_recall_at_10_max": 0.004831, + "nauc_recall_at_10_std": 0.192275, + "nauc_recall_at_10_diff1": 0.091016, + "nauc_recall_at_20_max": 0.002645, + "nauc_recall_at_20_std": 0.218638, + "nauc_recall_at_20_diff1": 0.074316, + "nauc_recall_at_100_max": 0.042382, + "nauc_recall_at_100_std": 0.21614, + "nauc_recall_at_100_diff1": 0.107428, + "nauc_recall_at_1000_max": 0.289574, + "nauc_recall_at_1000_std": 0.349355, + "nauc_recall_at_1000_diff1": 0.176235, + "nauc_precision_at_1_max": 0.20364, + "nauc_precision_at_1_std": -0.039051, + "nauc_precision_at_1_diff1": 0.287334, + "nauc_precision_at_3_max": 0.084862, + "nauc_precision_at_3_std": -0.085993, + "nauc_precision_at_3_diff1": 0.062707, + "nauc_precision_at_5_max": 0.158482, + "nauc_precision_at_5_std": 0.069832, + "nauc_precision_at_5_diff1": 0.118772, + "nauc_precision_at_10_max": 0.099888, + "nauc_precision_at_10_std": 0.034853, + "nauc_precision_at_10_diff1": 0.149968, + "nauc_precision_at_20_max": 0.070042, + "nauc_precision_at_20_std": 0.087039, + "nauc_precision_at_20_diff1": 0.067859, + "nauc_precision_at_100_max": 0.074405, + "nauc_precision_at_100_std": 0.117803, + "nauc_precision_at_100_diff1": 0.12459, + "nauc_precision_at_1000_max": 0.208949, + "nauc_precision_at_1000_std": -0.017934, + "nauc_precision_at_1000_diff1": 0.061722, + "nauc_mrr_at_1_max": 0.20364, + "nauc_mrr_at_1_std": -0.039051, + "nauc_mrr_at_1_diff1": 0.287334, + "nauc_mrr_at_3_max": 0.082067, + "nauc_mrr_at_3_std": -0.019544, + "nauc_mrr_at_3_diff1": 0.105687, + "nauc_mrr_at_5_max": 0.106265, + "nauc_mrr_at_5_std": 0.028702, + "nauc_mrr_at_5_diff1": 0.122263, + "nauc_mrr_at_10_max": 0.082855, + "nauc_mrr_at_10_std": 0.018981, + "nauc_mrr_at_10_diff1": 0.122411, + "nauc_mrr_at_20_max": 0.078231, + "nauc_mrr_at_20_std": 0.023124, + "nauc_mrr_at_20_diff1": 0.11408, + "nauc_mrr_at_100_max": 0.078256, + "nauc_mrr_at_100_std": 0.025286, + "nauc_mrr_at_100_diff1": 0.11631, + "nauc_mrr_at_1000_max": 0.080264, + "nauc_mrr_at_1000_std": 0.025476, + "nauc_mrr_at_1000_diff1": 0.117205, + "main_score": 0.08115, + "hf_subset": "MedXpertQA-Exam", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.08475, + "ndcg_at_3": 0.07448, + "ndcg_at_5": 0.08367, + "ndcg_at_10": 0.10296, + "ndcg_at_20": 0.12388, + "ndcg_at_100": 0.1755, + "ndcg_at_1000": 0.23415, + "map_at_1": 0.02536, + "map_at_3": 0.04065, + "map_at_5": 0.0531, + "map_at_10": 0.06416, + "map_at_20": 0.07101, + "map_at_100": 0.07942, + "map_at_1000": 0.08243, + "recall_at_1": 0.02536, + "recall_at_3": 0.05258, + "recall_at_5": 0.09158, + "recall_at_10": 0.14215, + "recall_at_20": 0.19655, + "recall_at_100": 0.38045, + "recall_at_1000": 0.68962, + "precision_at_1": 0.08475, + "precision_at_3": 0.0678, + "precision_at_5": 0.06271, + "precision_at_10": 0.04661, + "precision_at_20": 0.03475, + "precision_at_100": 0.015, + "precision_at_1000": 0.00287, + "mrr_at_1": 0.084746, + "mrr_at_3": 0.108757, + "mrr_at_5": 0.125282, + "mrr_at_10": 0.132812, + "mrr_at_20": 0.138822, + "mrr_at_100": 0.144915, + "mrr_at_1000": 0.146031, + "nauc_ndcg_at_1_max": 0.430119, + "nauc_ndcg_at_1_std": 0.044202, + "nauc_ndcg_at_1_diff1": 0.174591, + "nauc_ndcg_at_3_max": 0.386158, + "nauc_ndcg_at_3_std": 0.034376, + "nauc_ndcg_at_3_diff1": -0.007349, + "nauc_ndcg_at_5_max": 0.322547, + "nauc_ndcg_at_5_std": 0.017059, + "nauc_ndcg_at_5_diff1": -0.010279, + "nauc_ndcg_at_10_max": 0.270025, + "nauc_ndcg_at_10_std": 0.065855, + "nauc_ndcg_at_10_diff1": -0.014998, + "nauc_ndcg_at_20_max": 0.28436, + "nauc_ndcg_at_20_std": 0.099044, + "nauc_ndcg_at_20_diff1": 0.01502, + "nauc_ndcg_at_100_max": 0.325009, + "nauc_ndcg_at_100_std": 0.176222, + "nauc_ndcg_at_100_diff1": 0.07245, + "nauc_ndcg_at_1000_max": 0.331579, + "nauc_ndcg_at_1000_std": 0.157686, + "nauc_ndcg_at_1000_diff1": 0.058439, + "nauc_map_at_1_max": 0.343243, + "nauc_map_at_1_std": -0.073725, + "nauc_map_at_1_diff1": 0.217844, + "nauc_map_at_3_max": 0.363936, + "nauc_map_at_3_std": -0.005038, + "nauc_map_at_3_diff1": 0.039557, + "nauc_map_at_5_max": 0.367895, + "nauc_map_at_5_std": 0.007415, + "nauc_map_at_5_diff1": -0.013734, + "nauc_map_at_10_max": 0.326933, + "nauc_map_at_10_std": 0.037623, + "nauc_map_at_10_diff1": -0.016658, + "nauc_map_at_20_max": 0.326426, + "nauc_map_at_20_std": 0.055315, + "nauc_map_at_20_diff1": -0.008946, + "nauc_map_at_100_max": 0.333395, + "nauc_map_at_100_std": 0.080662, + "nauc_map_at_100_diff1": 0.001267, + "nauc_map_at_1000_max": 0.333148, + "nauc_map_at_1000_std": 0.079788, + "nauc_map_at_1000_diff1": 0.004887, + "nauc_recall_at_1_max": 0.343243, + "nauc_recall_at_1_std": -0.073725, + "nauc_recall_at_1_diff1": 0.217844, + "nauc_recall_at_3_max": 0.315323, + "nauc_recall_at_3_std": 0.026537, + "nauc_recall_at_3_diff1": -0.064353, + "nauc_recall_at_5_max": 0.22051, + "nauc_recall_at_5_std": 0.03009, + "nauc_recall_at_5_diff1": -0.064823, + "nauc_recall_at_10_max": 0.159616, + "nauc_recall_at_10_std": 0.093292, + "nauc_recall_at_10_diff1": -0.047139, + "nauc_recall_at_20_max": 0.20192, + "nauc_recall_at_20_std": 0.167877, + "nauc_recall_at_20_diff1": 0.008408, + "nauc_recall_at_100_max": 0.306012, + "nauc_recall_at_100_std": 0.318201, + "nauc_recall_at_100_diff1": 0.1363, + "nauc_recall_at_1000_max": 0.356257, + "nauc_recall_at_1000_std": 0.354549, + "nauc_recall_at_1000_diff1": 0.056173, + "nauc_precision_at_1_max": 0.430119, + "nauc_precision_at_1_std": 0.044202, + "nauc_precision_at_1_diff1": 0.174591, + "nauc_precision_at_3_max": 0.396876, + "nauc_precision_at_3_std": 0.059066, + "nauc_precision_at_3_diff1": -0.09461, + "nauc_precision_at_5_max": 0.348043, + "nauc_precision_at_5_std": 0.046912, + "nauc_precision_at_5_diff1": -0.0773, + "nauc_precision_at_10_max": 0.27737, + "nauc_precision_at_10_std": 0.116291, + "nauc_precision_at_10_diff1": -0.072646, + "nauc_precision_at_20_max": 0.302763, + "nauc_precision_at_20_std": 0.12938, + "nauc_precision_at_20_diff1": 0.025387, + "nauc_precision_at_100_max": 0.360128, + "nauc_precision_at_100_std": 0.249724, + "nauc_precision_at_100_diff1": 0.165665, + "nauc_precision_at_1000_max": 0.27635, + "nauc_precision_at_1000_std": 0.09272, + "nauc_precision_at_1000_diff1": 0.105775, + "nauc_mrr_at_1_max": 0.430119, + "nauc_mrr_at_1_std": 0.044202, + "nauc_mrr_at_1_diff1": 0.174591, + "nauc_mrr_at_3_max": 0.378172, + "nauc_mrr_at_3_std": 0.021199, + "nauc_mrr_at_3_diff1": 0.037787, + "nauc_mrr_at_5_max": 0.33799, + "nauc_mrr_at_5_std": 0.02316, + "nauc_mrr_at_5_diff1": 0.06416, + "nauc_mrr_at_10_max": 0.329574, + "nauc_mrr_at_10_std": 0.042294, + "nauc_mrr_at_10_diff1": 0.062461, + "nauc_mrr_at_20_max": 0.331038, + "nauc_mrr_at_20_std": 0.041417, + "nauc_mrr_at_20_diff1": 0.070854, + "nauc_mrr_at_100_max": 0.330641, + "nauc_mrr_at_100_std": 0.046153, + "nauc_mrr_at_100_diff1": 0.073836, + "nauc_mrr_at_1000_max": 0.330888, + "nauc_mrr_at_1000_std": 0.044285, + "nauc_mrr_at_1000_diff1": 0.072201, + "main_score": 0.10296, + "hf_subset": "MedQA-Diag", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.36667, + "ndcg_at_3": 0.369, + "ndcg_at_5": 0.37953, + "ndcg_at_10": 0.40461, + "ndcg_at_20": 0.42399, + "ndcg_at_100": 0.46317, + "ndcg_at_1000": 0.49188, + "map_at_1": 0.21478, + "map_at_3": 0.30502, + "map_at_5": 0.31996, + "map_at_10": 0.33441, + "map_at_20": 0.34204, + "map_at_100": 0.34958, + "map_at_1000": 0.35104, + "recall_at_1": 0.21478, + "recall_at_3": 0.37233, + "recall_at_5": 0.41878, + "recall_at_10": 0.47878, + "recall_at_20": 0.53844, + "recall_at_100": 0.70878, + "recall_at_1000": 0.897, + "precision_at_1": 0.36667, + "precision_at_3": 0.22444, + "precision_at_5": 0.156, + "precision_at_10": 0.09333, + "precision_at_20": 0.05333, + "precision_at_100": 0.01447, + "precision_at_1000": 0.00186, + "mrr_at_1": 0.366667, + "mrr_at_3": 0.447778, + "mrr_at_5": 0.461778, + "mrr_at_10": 0.468111, + "mrr_at_20": 0.472797, + "mrr_at_100": 0.475735, + "mrr_at_1000": 0.476157, + "nauc_ndcg_at_1_max": 0.334769, + "nauc_ndcg_at_1_std": 0.060487, + "nauc_ndcg_at_1_diff1": 0.503414, + "nauc_ndcg_at_3_max": 0.269945, + "nauc_ndcg_at_3_std": 0.096334, + "nauc_ndcg_at_3_diff1": 0.437268, + "nauc_ndcg_at_5_max": 0.248256, + "nauc_ndcg_at_5_std": 0.074008, + "nauc_ndcg_at_5_diff1": 0.412462, + "nauc_ndcg_at_10_max": 0.24081, + "nauc_ndcg_at_10_std": 0.07983, + "nauc_ndcg_at_10_diff1": 0.416117, + "nauc_ndcg_at_20_max": 0.242087, + "nauc_ndcg_at_20_std": 0.107944, + "nauc_ndcg_at_20_diff1": 0.415891, + "nauc_ndcg_at_100_max": 0.267823, + "nauc_ndcg_at_100_std": 0.137606, + "nauc_ndcg_at_100_diff1": 0.411322, + "nauc_ndcg_at_1000_max": 0.275991, + "nauc_ndcg_at_1000_std": 0.128673, + "nauc_ndcg_at_1000_diff1": 0.413261, + "nauc_map_at_1_max": 0.225407, + "nauc_map_at_1_std": 0.021342, + "nauc_map_at_1_diff1": 0.487723, + "nauc_map_at_3_max": 0.242353, + "nauc_map_at_3_std": 0.082068, + "nauc_map_at_3_diff1": 0.434216, + "nauc_map_at_5_max": 0.237703, + "nauc_map_at_5_std": 0.07324, + "nauc_map_at_5_diff1": 0.413633, + "nauc_map_at_10_max": 0.238492, + "nauc_map_at_10_std": 0.078036, + "nauc_map_at_10_diff1": 0.415274, + "nauc_map_at_20_max": 0.240163, + "nauc_map_at_20_std": 0.087455, + "nauc_map_at_20_diff1": 0.415519, + "nauc_map_at_100_max": 0.247455, + "nauc_map_at_100_std": 0.096327, + "nauc_map_at_100_diff1": 0.415869, + "nauc_map_at_1000_max": 0.247468, + "nauc_map_at_1000_std": 0.096022, + "nauc_map_at_1000_diff1": 0.41544, + "nauc_recall_at_1_max": 0.225407, + "nauc_recall_at_1_std": 0.021342, + "nauc_recall_at_1_diff1": 0.487723, + "nauc_recall_at_3_max": 0.191567, + "nauc_recall_at_3_std": 0.092496, + "nauc_recall_at_3_diff1": 0.400706, + "nauc_recall_at_5_max": 0.158466, + "nauc_recall_at_5_std": 0.048366, + "nauc_recall_at_5_diff1": 0.34007, + "nauc_recall_at_10_max": 0.122314, + "nauc_recall_at_10_std": 0.053626, + "nauc_recall_at_10_diff1": 0.33427, + "nauc_recall_at_20_max": 0.120597, + "nauc_recall_at_20_std": 0.135338, + "nauc_recall_at_20_diff1": 0.325141, + "nauc_recall_at_100_max": 0.189192, + "nauc_recall_at_100_std": 0.271513, + "nauc_recall_at_100_diff1": 0.264124, + "nauc_recall_at_1000_max": 0.314453, + "nauc_recall_at_1000_std": 0.353943, + "nauc_recall_at_1000_diff1": 0.195586, + "nauc_precision_at_1_max": 0.334769, + "nauc_precision_at_1_std": 0.060487, + "nauc_precision_at_1_diff1": 0.503414, + "nauc_precision_at_3_max": 0.333153, + "nauc_precision_at_3_std": 0.176189, + "nauc_precision_at_3_diff1": 0.299751, + "nauc_precision_at_5_max": 0.308622, + "nauc_precision_at_5_std": 0.132123, + "nauc_precision_at_5_diff1": 0.225182, + "nauc_precision_at_10_max": 0.272302, + "nauc_precision_at_10_std": 0.128709, + "nauc_precision_at_10_diff1": 0.232869, + "nauc_precision_at_20_max": 0.24367, + "nauc_precision_at_20_std": 0.210224, + "nauc_precision_at_20_diff1": 0.201862, + "nauc_precision_at_100_max": 0.264481, + "nauc_precision_at_100_std": 0.244457, + "nauc_precision_at_100_diff1": 0.091753, + "nauc_precision_at_1000_max": 0.219959, + "nauc_precision_at_1000_std": 0.146037, + "nauc_precision_at_1000_diff1": -0.005036, + "nauc_mrr_at_1_max": 0.334769, + "nauc_mrr_at_1_std": 0.060487, + "nauc_mrr_at_1_diff1": 0.503414, + "nauc_mrr_at_3_max": 0.338496, + "nauc_mrr_at_3_std": 0.105806, + "nauc_mrr_at_3_diff1": 0.474501, + "nauc_mrr_at_5_max": 0.328795, + "nauc_mrr_at_5_std": 0.082958, + "nauc_mrr_at_5_diff1": 0.470242, + "nauc_mrr_at_10_max": 0.321243, + "nauc_mrr_at_10_std": 0.080675, + "nauc_mrr_at_10_diff1": 0.468289, + "nauc_mrr_at_20_max": 0.320815, + "nauc_mrr_at_20_std": 0.087165, + "nauc_mrr_at_20_diff1": 0.467737, + "nauc_mrr_at_100_max": 0.322162, + "nauc_mrr_at_100_std": 0.089, + "nauc_mrr_at_100_diff1": 0.466273, + "nauc_mrr_at_1000_max": 0.322149, + "nauc_mrr_at_1000_std": 0.088815, + "nauc_mrr_at_1000_diff1": 0.466379, + "main_score": 0.40461, + "hf_subset": "PMC-Treatment", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.20175, + "ndcg_at_3": 0.19118, + "ndcg_at_5": 0.22583, + "ndcg_at_10": 0.26851, + "ndcg_at_20": 0.29166, + "ndcg_at_100": 0.33592, + "ndcg_at_1000": 0.37365, + "map_at_1": 0.09357, + "map_at_3": 0.14717, + "map_at_5": 0.17108, + "map_at_10": 0.19045, + "map_at_20": 0.19811, + "map_at_100": 0.20621, + "map_at_1000": 0.2081, + "recall_at_1": 0.09357, + "recall_at_3": 0.19298, + "recall_at_5": 0.27412, + "recall_at_10": 0.38377, + "recall_at_20": 0.45541, + "recall_at_100": 0.64181, + "recall_at_1000": 0.88523, + "precision_at_1": 0.20175, + "precision_at_3": 0.1345, + "precision_at_5": 0.10877, + "precision_at_10": 0.07632, + "precision_at_20": 0.04693, + "precision_at_100": 0.01386, + "precision_at_1000": 0.00193, + "mrr_at_1": 0.201754, + "mrr_at_3": 0.266082, + "mrr_at_5": 0.286696, + "mrr_at_10": 0.304832, + "mrr_at_20": 0.309488, + "mrr_at_100": 0.313911, + "mrr_at_1000": 0.314508, + "nauc_ndcg_at_1_max": 0.170767, + "nauc_ndcg_at_1_std": 0.003036, + "nauc_ndcg_at_1_diff1": 0.167342, + "nauc_ndcg_at_3_max": 0.117824, + "nauc_ndcg_at_3_std": 0.05392, + "nauc_ndcg_at_3_diff1": 0.080573, + "nauc_ndcg_at_5_max": 0.210045, + "nauc_ndcg_at_5_std": 0.071624, + "nauc_ndcg_at_5_diff1": 0.079356, + "nauc_ndcg_at_10_max": 0.238605, + "nauc_ndcg_at_10_std": 0.049646, + "nauc_ndcg_at_10_diff1": 0.105037, + "nauc_ndcg_at_20_max": 0.248189, + "nauc_ndcg_at_20_std": 0.032812, + "nauc_ndcg_at_20_diff1": 0.154697, + "nauc_ndcg_at_100_max": 0.245721, + "nauc_ndcg_at_100_std": 0.096591, + "nauc_ndcg_at_100_diff1": 0.144973, + "nauc_ndcg_at_1000_max": 0.244494, + "nauc_ndcg_at_1000_std": 0.063085, + "nauc_ndcg_at_1000_diff1": 0.141657, + "nauc_map_at_1_max": 0.174434, + "nauc_map_at_1_std": -0.034871, + "nauc_map_at_1_diff1": 0.060583, + "nauc_map_at_3_max": 0.135705, + "nauc_map_at_3_std": 0.035791, + "nauc_map_at_3_diff1": 0.054685, + "nauc_map_at_5_max": 0.191059, + "nauc_map_at_5_std": 0.043324, + "nauc_map_at_5_diff1": 0.068122, + "nauc_map_at_10_max": 0.219659, + "nauc_map_at_10_std": 0.035067, + "nauc_map_at_10_diff1": 0.075855, + "nauc_map_at_20_max": 0.220282, + "nauc_map_at_20_std": 0.027824, + "nauc_map_at_20_diff1": 0.09511, + "nauc_map_at_100_max": 0.222996, + "nauc_map_at_100_std": 0.042372, + "nauc_map_at_100_diff1": 0.09231, + "nauc_map_at_1000_max": 0.222652, + "nauc_map_at_1000_std": 0.040494, + "nauc_map_at_1000_diff1": 0.091992, + "nauc_recall_at_1_max": 0.174434, + "nauc_recall_at_1_std": -0.034871, + "nauc_recall_at_1_diff1": 0.060583, + "nauc_recall_at_3_max": 0.085325, + "nauc_recall_at_3_std": 0.073648, + "nauc_recall_at_3_diff1": 0.024275, + "nauc_recall_at_5_max": 0.227858, + "nauc_recall_at_5_std": 0.102194, + "nauc_recall_at_5_diff1": 0.028115, + "nauc_recall_at_10_max": 0.252416, + "nauc_recall_at_10_std": 0.042692, + "nauc_recall_at_10_diff1": 0.074824, + "nauc_recall_at_20_max": 0.263952, + "nauc_recall_at_20_std": -0.004078, + "nauc_recall_at_20_diff1": 0.197025, + "nauc_recall_at_100_max": 0.230615, + "nauc_recall_at_100_std": 0.238621, + "nauc_recall_at_100_diff1": 0.174302, + "nauc_recall_at_1000_max": 0.286542, + "nauc_recall_at_1000_std": 0.038366, + "nauc_recall_at_1000_diff1": 0.155572, + "nauc_precision_at_1_max": 0.170767, + "nauc_precision_at_1_std": 0.003036, + "nauc_precision_at_1_diff1": 0.167342, + "nauc_precision_at_3_max": 0.100432, + "nauc_precision_at_3_std": 0.05456, + "nauc_precision_at_3_diff1": 0.089334, + "nauc_precision_at_5_max": 0.227391, + "nauc_precision_at_5_std": 0.07576, + "nauc_precision_at_5_diff1": 0.107545, + "nauc_precision_at_10_max": 0.271093, + "nauc_precision_at_10_std": 0.031069, + "nauc_precision_at_10_diff1": 0.151339, + "nauc_precision_at_20_max": 0.268698, + "nauc_precision_at_20_std": -0.020115, + "nauc_precision_at_20_diff1": 0.25161, + "nauc_precision_at_100_max": 0.215504, + "nauc_precision_at_100_std": 0.151501, + "nauc_precision_at_100_diff1": 0.160556, + "nauc_precision_at_1000_max": 0.127249, + "nauc_precision_at_1000_std": 0.015537, + "nauc_precision_at_1000_diff1": 0.151298, + "nauc_mrr_at_1_max": 0.170767, + "nauc_mrr_at_1_std": 0.003036, + "nauc_mrr_at_1_diff1": 0.167342, + "nauc_mrr_at_3_max": 0.132385, + "nauc_mrr_at_3_std": 0.055067, + "nauc_mrr_at_3_diff1": 0.152712, + "nauc_mrr_at_5_max": 0.182951, + "nauc_mrr_at_5_std": 0.075813, + "nauc_mrr_at_5_diff1": 0.143346, + "nauc_mrr_at_10_max": 0.181261, + "nauc_mrr_at_10_std": 0.064451, + "nauc_mrr_at_10_diff1": 0.165608, + "nauc_mrr_at_20_max": 0.188191, + "nauc_mrr_at_20_std": 0.066543, + "nauc_mrr_at_20_diff1": 0.173897, + "nauc_mrr_at_100_max": 0.185725, + "nauc_mrr_at_100_std": 0.069832, + "nauc_mrr_at_100_diff1": 0.173671, + "nauc_mrr_at_1000_max": 0.185385, + "nauc_mrr_at_1000_std": 0.069102, + "nauc_mrr_at_1000_diff1": 0.173067, + "main_score": 0.26851, + "hf_subset": "PMC-Clinical", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.16279, + "ndcg_at_3": 0.1622, + "ndcg_at_5": 0.17755, + "ndcg_at_10": 0.22157, + "ndcg_at_20": 0.28292, + "ndcg_at_100": 0.36758, + "ndcg_at_1000": 0.40983, + "map_at_1": 0.05078, + "map_at_3": 0.0896, + "map_at_5": 0.10807, + "map_at_10": 0.13334, + "map_at_20": 0.1584, + "map_at_100": 0.17916, + "map_at_1000": 0.18252, + "recall_at_1": 0.05078, + "recall_at_3": 0.13049, + "recall_at_5": 0.18902, + "recall_at_10": 0.28773, + "recall_at_20": 0.45375, + "recall_at_100": 0.75801, + "recall_at_1000": 0.98346, + "precision_at_1": 0.16279, + "precision_at_3": 0.13953, + "precision_at_5": 0.13333, + "precision_at_10": 0.10388, + "precision_at_20": 0.08101, + "precision_at_100": 0.02713, + "precision_at_1000": 0.00349, + "mrr_at_1": 0.162791, + "mrr_at_3": 0.254522, + "mrr_at_5": 0.287855, + "mrr_at_10": 0.301212, + "mrr_at_20": 0.311312, + "mrr_at_100": 0.316725, + "mrr_at_1000": 0.317103, + "nauc_ndcg_at_1_max": 0.183509, + "nauc_ndcg_at_1_std": 0.15541, + "nauc_ndcg_at_1_diff1": 0.012311, + "nauc_ndcg_at_3_max": 0.113731, + "nauc_ndcg_at_3_std": 0.101971, + "nauc_ndcg_at_3_diff1": -0.068442, + "nauc_ndcg_at_5_max": 0.092644, + "nauc_ndcg_at_5_std": 0.122906, + "nauc_ndcg_at_5_diff1": -0.059765, + "nauc_ndcg_at_10_max": 0.147393, + "nauc_ndcg_at_10_std": 0.111311, + "nauc_ndcg_at_10_diff1": -0.029566, + "nauc_ndcg_at_20_max": 0.170615, + "nauc_ndcg_at_20_std": 0.160393, + "nauc_ndcg_at_20_diff1": -0.028224, + "nauc_ndcg_at_100_max": 0.169599, + "nauc_ndcg_at_100_std": 0.235601, + "nauc_ndcg_at_100_diff1": -0.059926, + "nauc_ndcg_at_1000_max": 0.134996, + "nauc_ndcg_at_1000_std": 0.242137, + "nauc_ndcg_at_1000_diff1": -0.088178, + "nauc_map_at_1_max": 0.119172, + "nauc_map_at_1_std": -0.026583, + "nauc_map_at_1_diff1": 0.112207, + "nauc_map_at_3_max": 0.103681, + "nauc_map_at_3_std": 0.002216, + "nauc_map_at_3_diff1": 0.026856, + "nauc_map_at_5_max": 0.088557, + "nauc_map_at_5_std": 0.048533, + "nauc_map_at_5_diff1": 0.004606, + "nauc_map_at_10_max": 0.13843, + "nauc_map_at_10_std": 0.051412, + "nauc_map_at_10_diff1": 0.02033, + "nauc_map_at_20_max": 0.135658, + "nauc_map_at_20_std": 0.088702, + "nauc_map_at_20_diff1": 0.009145, + "nauc_map_at_100_max": 0.139195, + "nauc_map_at_100_std": 0.114666, + "nauc_map_at_100_diff1": -0.011143, + "nauc_map_at_1000_max": 0.13655, + "nauc_map_at_1000_std": 0.11895, + "nauc_map_at_1000_diff1": -0.013475, + "nauc_recall_at_1_max": 0.119172, + "nauc_recall_at_1_std": -0.026583, + "nauc_recall_at_1_diff1": 0.112207, + "nauc_recall_at_3_max": 0.079929, + "nauc_recall_at_3_std": -0.011202, + "nauc_recall_at_3_diff1": -0.011012, + "nauc_recall_at_5_max": 0.028742, + "nauc_recall_at_5_std": 0.082939, + "nauc_recall_at_5_diff1": -0.049322, + "nauc_recall_at_10_max": 0.124547, + "nauc_recall_at_10_std": 0.062471, + "nauc_recall_at_10_diff1": 0.006434, + "nauc_recall_at_20_max": 0.155919, + "nauc_recall_at_20_std": 0.117399, + "nauc_recall_at_20_diff1": 0.034113, + "nauc_recall_at_100_max": 0.173473, + "nauc_recall_at_100_std": 0.273805, + "nauc_recall_at_100_diff1": 0.053054, + "nauc_recall_at_1000_max": -1.306089, + "nauc_recall_at_1000_std": 0.963204, + "nauc_recall_at_1000_diff1": -0.078643, + "nauc_precision_at_1_max": 0.183509, + "nauc_precision_at_1_std": 0.15541, + "nauc_precision_at_1_diff1": 0.012311, + "nauc_precision_at_3_max": 0.172643, + "nauc_precision_at_3_std": 0.192709, + "nauc_precision_at_3_diff1": -0.117457, + "nauc_precision_at_5_max": 0.074208, + "nauc_precision_at_5_std": 0.246189, + "nauc_precision_at_5_diff1": -0.150913, + "nauc_precision_at_10_max": 0.154191, + "nauc_precision_at_10_std": 0.188788, + "nauc_precision_at_10_diff1": -0.083837, + "nauc_precision_at_20_max": 0.156403, + "nauc_precision_at_20_std": 0.272283, + "nauc_precision_at_20_diff1": -0.102573, + "nauc_precision_at_100_max": 0.106201, + "nauc_precision_at_100_std": 0.382976, + "nauc_precision_at_100_diff1": -0.175799, + "nauc_precision_at_1000_max": 0.012963, + "nauc_precision_at_1000_std": 0.385123, + "nauc_precision_at_1000_diff1": -0.266688, + "nauc_mrr_at_1_max": 0.183509, + "nauc_mrr_at_1_std": 0.15541, + "nauc_mrr_at_1_diff1": 0.012311, + "nauc_mrr_at_3_max": 0.190771, + "nauc_mrr_at_3_std": 0.168296, + "nauc_mrr_at_3_diff1": -0.088324, + "nauc_mrr_at_5_max": 0.154421, + "nauc_mrr_at_5_std": 0.183435, + "nauc_mrr_at_5_diff1": -0.106915, + "nauc_mrr_at_10_max": 0.156513, + "nauc_mrr_at_10_std": 0.186536, + "nauc_mrr_at_10_diff1": -0.098482, + "nauc_mrr_at_20_max": 0.169158, + "nauc_mrr_at_20_std": 0.190612, + "nauc_mrr_at_20_diff1": -0.096347, + "nauc_mrr_at_100_max": 0.16451, + "nauc_mrr_at_100_std": 0.196776, + "nauc_mrr_at_100_diff1": -0.098142, + "nauc_mrr_at_1000_max": 0.164088, + "nauc_mrr_at_1000_std": 0.195898, + "nauc_mrr_at_1000_diff1": -0.098183, + "main_score": 0.22157, + "hf_subset": "IIYi-Clinical", + "languages": [ + "eng-Latn" + ] + } + ] + }, + "evaluation_time": 4226.834891319275, + "kg_co2_emissions": null +} \ No newline at end of file diff --git a/results/infly__inf-retriever-v1/cb70ca7c31dfa866b2eff2dad229c144d8ddfd91/R2MEDRetrieval.json b/results/infly__inf-retriever-v1/cb70ca7c31dfa866b2eff2dad229c144d8ddfd91/R2MEDRetrieval.json new file mode 100644 index 0000000000..537d01af42 --- /dev/null +++ b/results/infly__inf-retriever-v1/cb70ca7c31dfa866b2eff2dad229c144d8ddfd91/R2MEDRetrieval.json @@ -0,0 +1,1187 @@ +{ + "dataset_revision": "1.0", + "task_name": "R2MEDRetrieval", + "mteb_version": "1.38.20", + "scores": { + "test": [ + { + "ndcg_at_1": 0.13592, + "ndcg_at_3": 0.12878, + "ndcg_at_5": 0.13597, + "ndcg_at_10": 0.15365, + "ndcg_at_20": 0.17871, + "ndcg_at_100": 0.24301, + "ndcg_at_1000": 0.31039, + "map_at_1": 0.03351, + "map_at_3": 0.07044, + "map_at_5": 0.08349, + "map_at_10": 0.09667, + "map_at_20": 0.10799, + "map_at_100": 0.1211, + "map_at_1000": 0.12513, + "recall_at_1": 0.03351, + "recall_at_3": 0.09515, + "recall_at_5": 0.13297, + "recall_at_10": 0.18799, + "recall_at_20": 0.25296, + "recall_at_100": 0.49812, + "recall_at_1000": 0.8705, + "precision_at_1": 0.13592, + "precision_at_3": 0.1165, + "precision_at_5": 0.10291, + "precision_at_10": 0.07379, + "precision_at_20": 0.05, + "precision_at_100": 0.01883, + "precision_at_1000": 0.00319, + "mrr_at_1": 0.135922, + "mrr_at_3": 0.192557, + "mrr_at_5": 0.203722, + "mrr_at_10": 0.216289, + "mrr_at_20": 0.221484, + "mrr_at_100": 0.227231, + "mrr_at_1000": 0.228686, + "nauc_ndcg_at_1_max": -0.005316, + "nauc_ndcg_at_1_std": -0.281925, + "nauc_ndcg_at_1_diff1": 0.213453, + "nauc_ndcg_at_3_max": 0.040575, + "nauc_ndcg_at_3_std": -0.193059, + "nauc_ndcg_at_3_diff1": 0.147737, + "nauc_ndcg_at_5_max": 0.027477, + "nauc_ndcg_at_5_std": -0.225794, + "nauc_ndcg_at_5_diff1": 0.088574, + "nauc_ndcg_at_10_max": 0.044223, + "nauc_ndcg_at_10_std": -0.225268, + "nauc_ndcg_at_10_diff1": 0.140662, + "nauc_ndcg_at_20_max": 0.067333, + "nauc_ndcg_at_20_std": -0.245734, + "nauc_ndcg_at_20_diff1": 0.13687, + "nauc_ndcg_at_100_max": 0.02763, + "nauc_ndcg_at_100_std": -0.253677, + "nauc_ndcg_at_100_diff1": 0.156597, + "nauc_ndcg_at_1000_max": 0.075743, + "nauc_ndcg_at_1000_std": -0.20809, + "nauc_ndcg_at_1000_diff1": 0.156174, + "nauc_map_at_1_max": 0.053962, + "nauc_map_at_1_std": -0.336746, + "nauc_map_at_1_diff1": 0.292981, + "nauc_map_at_3_max": 0.079441, + "nauc_map_at_3_std": -0.206858, + "nauc_map_at_3_diff1": 0.195482, + "nauc_map_at_5_max": 0.049937, + "nauc_map_at_5_std": -0.213094, + "nauc_map_at_5_diff1": 0.137567, + "nauc_map_at_10_max": 0.060508, + "nauc_map_at_10_std": -0.231962, + "nauc_map_at_10_diff1": 0.144353, + "nauc_map_at_20_max": 0.077235, + "nauc_map_at_20_std": -0.247208, + "nauc_map_at_20_diff1": 0.135853, + "nauc_map_at_100_max": 0.072883, + "nauc_map_at_100_std": -0.254806, + "nauc_map_at_100_diff1": 0.133803, + "nauc_map_at_1000_max": 0.073821, + "nauc_map_at_1000_std": -0.252515, + "nauc_map_at_1000_diff1": 0.130764, + "nauc_recall_at_1_max": 0.053962, + "nauc_recall_at_1_std": -0.336746, + "nauc_recall_at_1_diff1": 0.292981, + "nauc_recall_at_3_max": 0.079615, + "nauc_recall_at_3_std": -0.162268, + "nauc_recall_at_3_diff1": 0.159991, + "nauc_recall_at_5_max": 0.022622, + "nauc_recall_at_5_std": -0.157289, + "nauc_recall_at_5_diff1": 0.048574, + "nauc_recall_at_10_max": 0.046804, + "nauc_recall_at_10_std": -0.175665, + "nauc_recall_at_10_diff1": 0.115756, + "nauc_recall_at_20_max": 0.100334, + "nauc_recall_at_20_std": -0.203801, + "nauc_recall_at_20_diff1": 0.105666, + "nauc_recall_at_100_max": -0.020883, + "nauc_recall_at_100_std": -0.182364, + "nauc_recall_at_100_diff1": 0.199777, + "nauc_recall_at_1000_max": 0.321416, + "nauc_recall_at_1000_std": 0.271065, + "nauc_recall_at_1000_diff1": 0.372193, + "nauc_precision_at_1_max": -0.005316, + "nauc_precision_at_1_std": -0.281925, + "nauc_precision_at_1_diff1": 0.213453, + "nauc_precision_at_3_max": 0.036519, + "nauc_precision_at_3_std": -0.141008, + "nauc_precision_at_3_diff1": 0.148135, + "nauc_precision_at_5_max": 0.00124, + "nauc_precision_at_5_std": -0.198807, + "nauc_precision_at_5_diff1": 0.022873, + "nauc_precision_at_10_max": 0.020285, + "nauc_precision_at_10_std": -0.260238, + "nauc_precision_at_10_diff1": 0.041767, + "nauc_precision_at_20_max": 0.033329, + "nauc_precision_at_20_std": -0.280684, + "nauc_precision_at_20_diff1": 0.028224, + "nauc_precision_at_100_max": -0.052561, + "nauc_precision_at_100_std": -0.248566, + "nauc_precision_at_100_diff1": 0.009129, + "nauc_precision_at_1000_max": -0.003523, + "nauc_precision_at_1000_std": -0.105417, + "nauc_precision_at_1000_diff1": -0.084207, + "nauc_mrr_at_1_max": -0.005316, + "nauc_mrr_at_1_std": -0.309186, + "nauc_mrr_at_1_diff1": 0.213453, + "nauc_mrr_at_3_max": 0.046535, + "nauc_mrr_at_3_std": -0.231568, + "nauc_mrr_at_3_diff1": 0.173452, + "nauc_mrr_at_5_max": 0.039251, + "nauc_mrr_at_5_std": -0.223594, + "nauc_mrr_at_5_diff1": 0.15864, + "nauc_mrr_at_10_max": 0.029233, + "nauc_mrr_at_10_std": -0.229924, + "nauc_mrr_at_10_diff1": 0.167124, + "nauc_mrr_at_20_max": 0.028563, + "nauc_mrr_at_20_std": -0.235906, + "nauc_mrr_at_20_diff1": 0.1629, + "nauc_mrr_at_100_max": 0.024651, + "nauc_mrr_at_100_std": -0.238781, + "nauc_mrr_at_100_diff1": 0.164969, + "nauc_mrr_at_1000_max": 0.025671, + "nauc_mrr_at_1000_std": -0.237836, + "nauc_mrr_at_1000_diff1": 0.165195, + "main_score": 0.15365, + "hf_subset": "Biology", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.35065, + "ndcg_at_3": 0.40035, + "ndcg_at_5": 0.44458, + "ndcg_at_10": 0.49022, + "ndcg_at_20": 0.53557, + "ndcg_at_100": 0.57373, + "ndcg_at_1000": 0.59201, + "map_at_1": 0.19774, + "map_at_3": 0.3072, + "map_at_5": 0.35239, + "map_at_10": 0.39265, + "map_at_20": 0.4151, + "map_at_100": 0.42717, + "map_at_1000": 0.42831, + "recall_at_1": 0.19774, + "recall_at_3": 0.37744, + "recall_at_5": 0.49808, + "recall_at_10": 0.62596, + "recall_at_20": 0.74898, + "recall_at_100": 0.88319, + "recall_at_1000": 0.99567, + "precision_at_1": 0.35065, + "precision_at_3": 0.28139, + "precision_at_5": 0.24156, + "precision_at_10": 0.16494, + "precision_at_20": 0.10519, + "precision_at_100": 0.02623, + "precision_at_1000": 0.00294, + "mrr_at_1": 0.350649, + "mrr_at_3": 0.458874, + "mrr_at_5": 0.495887, + "mrr_at_10": 0.502664, + "mrr_at_20": 0.506026, + "mrr_at_100": 0.507568, + "mrr_at_1000": 0.508047, + "nauc_ndcg_at_1_max": -0.101996, + "nauc_ndcg_at_1_std": -0.130844, + "nauc_ndcg_at_1_diff1": 0.251971, + "nauc_ndcg_at_3_max": -0.09149, + "nauc_ndcg_at_3_std": -0.228965, + "nauc_ndcg_at_3_diff1": 0.247555, + "nauc_ndcg_at_5_max": -0.011352, + "nauc_ndcg_at_5_std": -0.258914, + "nauc_ndcg_at_5_diff1": 0.296586, + "nauc_ndcg_at_10_max": 0.01081, + "nauc_ndcg_at_10_std": -0.222061, + "nauc_ndcg_at_10_diff1": 0.286609, + "nauc_ndcg_at_20_max": 0.032042, + "nauc_ndcg_at_20_std": -0.18812, + "nauc_ndcg_at_20_diff1": 0.235671, + "nauc_ndcg_at_100_max": 0.046696, + "nauc_ndcg_at_100_std": -0.130511, + "nauc_ndcg_at_100_diff1": 0.226595, + "nauc_ndcg_at_1000_max": 0.024056, + "nauc_ndcg_at_1000_std": -0.121875, + "nauc_ndcg_at_1000_diff1": 0.212613, + "nauc_map_at_1_max": -0.009945, + "nauc_map_at_1_std": -0.185142, + "nauc_map_at_1_diff1": 0.383663, + "nauc_map_at_3_max": -0.034383, + "nauc_map_at_3_std": -0.272968, + "nauc_map_at_3_diff1": 0.361472, + "nauc_map_at_5_max": -0.013403, + "nauc_map_at_5_std": -0.285053, + "nauc_map_at_5_diff1": 0.362729, + "nauc_map_at_10_max": -0.014052, + "nauc_map_at_10_std": -0.241434, + "nauc_map_at_10_diff1": 0.322603, + "nauc_map_at_20_max": 0.001529, + "nauc_map_at_20_std": -0.222874, + "nauc_map_at_20_diff1": 0.300921, + "nauc_map_at_100_max": 0.004071, + "nauc_map_at_100_std": -0.201431, + "nauc_map_at_100_diff1": 0.292588, + "nauc_map_at_1000_max": 0.002484, + "nauc_map_at_1000_std": -0.200398, + "nauc_map_at_1000_diff1": 0.29108, + "nauc_recall_at_1_max": -0.009945, + "nauc_recall_at_1_std": -0.185142, + "nauc_recall_at_1_diff1": 0.383663, + "nauc_recall_at_3_max": -0.051801, + "nauc_recall_at_3_std": -0.331686, + "nauc_recall_at_3_diff1": 0.286455, + "nauc_recall_at_5_max": 0.046762, + "nauc_recall_at_5_std": -0.379807, + "nauc_recall_at_5_diff1": 0.336476, + "nauc_recall_at_10_max": 0.087519, + "nauc_recall_at_10_std": -0.312032, + "nauc_recall_at_10_diff1": 0.312982, + "nauc_recall_at_20_max": 0.148118, + "nauc_recall_at_20_std": -0.30051, + "nauc_recall_at_20_diff1": 0.16756, + "nauc_recall_at_100_max": 0.405164, + "nauc_recall_at_100_std": -0.124493, + "nauc_recall_at_100_diff1": 0.230133, + "nauc_recall_at_1000_max": 0.554847, + "nauc_recall_at_1000_std": -1.164365, + "nauc_recall_at_1000_diff1": 0.357916, + "nauc_precision_at_1_max": -0.101996, + "nauc_precision_at_1_std": -0.130844, + "nauc_precision_at_1_diff1": 0.251971, + "nauc_precision_at_3_max": -0.102258, + "nauc_precision_at_3_std": -0.116041, + "nauc_precision_at_3_diff1": 0.072308, + "nauc_precision_at_5_max": 0.048049, + "nauc_precision_at_5_std": 0.022391, + "nauc_precision_at_5_diff1": -0.040525, + "nauc_precision_at_10_max": 0.022632, + "nauc_precision_at_10_std": 0.178299, + "nauc_precision_at_10_diff1": -0.159084, + "nauc_precision_at_20_max": 0.084592, + "nauc_precision_at_20_std": 0.289993, + "nauc_precision_at_20_diff1": -0.278982, + "nauc_precision_at_100_max": 0.080725, + "nauc_precision_at_100_std": 0.421219, + "nauc_precision_at_100_diff1": -0.340959, + "nauc_precision_at_1000_max": 0.059716, + "nauc_precision_at_1000_std": 0.481827, + "nauc_precision_at_1000_diff1": -0.428399, + "nauc_mrr_at_1_max": -0.101996, + "nauc_mrr_at_1_std": -0.130844, + "nauc_mrr_at_1_diff1": 0.251971, + "nauc_mrr_at_3_max": -0.126119, + "nauc_mrr_at_3_std": -0.148681, + "nauc_mrr_at_3_diff1": 0.186279, + "nauc_mrr_at_5_max": -0.056282, + "nauc_mrr_at_5_std": -0.132109, + "nauc_mrr_at_5_diff1": 0.20273, + "nauc_mrr_at_10_max": -0.056817, + "nauc_mrr_at_10_std": -0.134331, + "nauc_mrr_at_10_diff1": 0.206917, + "nauc_mrr_at_20_max": -0.061941, + "nauc_mrr_at_20_std": -0.135854, + "nauc_mrr_at_20_diff1": 0.20151, + "nauc_mrr_at_100_max": -0.061597, + "nauc_mrr_at_100_std": -0.136448, + "nauc_mrr_at_100_diff1": 0.204847, + "nauc_mrr_at_1000_max": -0.062291, + "nauc_mrr_at_1000_std": -0.136288, + "nauc_mrr_at_1000_diff1": 0.204663, + "main_score": 0.49022, + "hf_subset": "Bioinformatics", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.34091, + "ndcg_at_3": 0.38513, + "ndcg_at_5": 0.40051, + "ndcg_at_10": 0.44743, + "ndcg_at_20": 0.48953, + "ndcg_at_100": 0.54559, + "ndcg_at_1000": 0.55999, + "map_at_1": 0.20919, + "map_at_3": 0.31366, + "map_at_5": 0.3333, + "map_at_10": 0.36438, + "map_at_20": 0.38449, + "map_at_100": 0.39654, + "map_at_1000": 0.39765, + "recall_at_1": 0.20919, + "recall_at_3": 0.38205, + "recall_at_5": 0.43903, + "recall_at_10": 0.55936, + "recall_at_20": 0.66894, + "recall_at_100": 0.89334, + "recall_at_1000": 0.97017, + "precision_at_1": 0.34091, + "precision_at_3": 0.25, + "precision_at_5": 0.18636, + "precision_at_10": 0.12841, + "precision_at_20": 0.0858, + "precision_at_100": 0.02409, + "precision_at_1000": 0.00269, + "mrr_at_1": 0.340909, + "mrr_at_3": 0.435606, + "mrr_at_5": 0.456629, + "mrr_at_10": 0.470608, + "mrr_at_20": 0.476068, + "mrr_at_100": 0.479234, + "mrr_at_1000": 0.479349, + "nauc_ndcg_at_1_max": 0.194173, + "nauc_ndcg_at_1_std": -0.112067, + "nauc_ndcg_at_1_diff1": 0.192123, + "nauc_ndcg_at_3_max": 0.207364, + "nauc_ndcg_at_3_std": -0.142831, + "nauc_ndcg_at_3_diff1": 0.191392, + "nauc_ndcg_at_5_max": 0.217575, + "nauc_ndcg_at_5_std": -0.134483, + "nauc_ndcg_at_5_diff1": 0.192056, + "nauc_ndcg_at_10_max": 0.272168, + "nauc_ndcg_at_10_std": -0.134083, + "nauc_ndcg_at_10_diff1": 0.169102, + "nauc_ndcg_at_20_max": 0.267008, + "nauc_ndcg_at_20_std": -0.145742, + "nauc_ndcg_at_20_diff1": 0.172911, + "nauc_ndcg_at_100_max": 0.287687, + "nauc_ndcg_at_100_std": -0.073565, + "nauc_ndcg_at_100_diff1": 0.18744, + "nauc_ndcg_at_1000_max": 0.283605, + "nauc_ndcg_at_1000_std": -0.081815, + "nauc_ndcg_at_1000_diff1": 0.190706, + "nauc_map_at_1_max": 0.114931, + "nauc_map_at_1_std": -0.173887, + "nauc_map_at_1_diff1": 0.350711, + "nauc_map_at_3_max": 0.165905, + "nauc_map_at_3_std": -0.127125, + "nauc_map_at_3_diff1": 0.252462, + "nauc_map_at_5_max": 0.187633, + "nauc_map_at_5_std": -0.121594, + "nauc_map_at_5_diff1": 0.235682, + "nauc_map_at_10_max": 0.233712, + "nauc_map_at_10_std": -0.129712, + "nauc_map_at_10_diff1": 0.216425, + "nauc_map_at_20_max": 0.239093, + "nauc_map_at_20_std": -0.141769, + "nauc_map_at_20_diff1": 0.212778, + "nauc_map_at_100_max": 0.243753, + "nauc_map_at_100_std": -0.126309, + "nauc_map_at_100_diff1": 0.218152, + "nauc_map_at_1000_max": 0.244271, + "nauc_map_at_1000_std": -0.126131, + "nauc_map_at_1000_diff1": 0.218638, + "nauc_recall_at_1_max": 0.114931, + "nauc_recall_at_1_std": -0.173887, + "nauc_recall_at_1_diff1": 0.350711, + "nauc_recall_at_3_max": 0.1538, + "nauc_recall_at_3_std": -0.158236, + "nauc_recall_at_3_diff1": 0.197852, + "nauc_recall_at_5_max": 0.180405, + "nauc_recall_at_5_std": -0.143421, + "nauc_recall_at_5_diff1": 0.173699, + "nauc_recall_at_10_max": 0.296227, + "nauc_recall_at_10_std": -0.144513, + "nauc_recall_at_10_diff1": 0.091416, + "nauc_recall_at_20_max": 0.268211, + "nauc_recall_at_20_std": -0.203028, + "nauc_recall_at_20_diff1": 0.084428, + "nauc_recall_at_100_max": 0.394622, + "nauc_recall_at_100_std": 0.208143, + "nauc_recall_at_100_diff1": 0.147443, + "nauc_recall_at_1000_max": 0.370601, + "nauc_recall_at_1000_std": 0.309401, + "nauc_recall_at_1000_diff1": 0.41897, + "nauc_precision_at_1_max": 0.194173, + "nauc_precision_at_1_std": -0.112067, + "nauc_precision_at_1_diff1": 0.192123, + "nauc_precision_at_3_max": 0.317888, + "nauc_precision_at_3_std": -0.013013, + "nauc_precision_at_3_diff1": -0.023754, + "nauc_precision_at_5_max": 0.347231, + "nauc_precision_at_5_std": 0.023094, + "nauc_precision_at_5_diff1": -0.087752, + "nauc_precision_at_10_max": 0.401785, + "nauc_precision_at_10_std": -0.012619, + "nauc_precision_at_10_diff1": -0.125876, + "nauc_precision_at_20_max": 0.295267, + "nauc_precision_at_20_std": 0.009132, + "nauc_precision_at_20_diff1": -0.085641, + "nauc_precision_at_100_max": 0.250409, + "nauc_precision_at_100_std": 0.284877, + "nauc_precision_at_100_diff1": -0.120267, + "nauc_precision_at_1000_max": 0.195743, + "nauc_precision_at_1000_std": 0.25937, + "nauc_precision_at_1000_diff1": -0.148853, + "nauc_mrr_at_1_max": 0.194173, + "nauc_mrr_at_1_std": -0.112067, + "nauc_mrr_at_1_diff1": 0.192123, + "nauc_mrr_at_3_max": 0.247191, + "nauc_mrr_at_3_std": -0.137358, + "nauc_mrr_at_3_diff1": 0.149943, + "nauc_mrr_at_5_max": 0.241404, + "nauc_mrr_at_5_std": -0.119653, + "nauc_mrr_at_5_diff1": 0.156494, + "nauc_mrr_at_10_max": 0.259432, + "nauc_mrr_at_10_std": -0.10733, + "nauc_mrr_at_10_diff1": 0.156066, + "nauc_mrr_at_20_max": 0.25251, + "nauc_mrr_at_20_std": -0.107897, + "nauc_mrr_at_20_diff1": 0.157394, + "nauc_mrr_at_100_max": 0.253374, + "nauc_mrr_at_100_std": -0.106352, + "nauc_mrr_at_100_diff1": 0.157884, + "nauc_mrr_at_1000_max": 0.253136, + "nauc_mrr_at_1000_std": -0.10666, + "nauc_mrr_at_1000_diff1": 0.158161, + "main_score": 0.44743, + "hf_subset": "Medical-Sciences", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.1134, + "ndcg_at_3": 0.07565, + "ndcg_at_5": 0.07778, + "ndcg_at_10": 0.0998, + "ndcg_at_20": 0.12214, + "ndcg_at_100": 0.16465, + "ndcg_at_1000": 0.22201, + "map_at_1": 0.04864, + "map_at_3": 0.05271, + "map_at_5": 0.05761, + "map_at_10": 0.06618, + "map_at_20": 0.07346, + "map_at_100": 0.07989, + "map_at_1000": 0.08251, + "recall_at_1": 0.04864, + "recall_at_3": 0.05423, + "recall_at_5": 0.07142, + "recall_at_10": 0.132, + "recall_at_20": 0.2015, + "recall_at_100": 0.37559, + "recall_at_1000": 0.71715, + "precision_at_1": 0.1134, + "precision_at_3": 0.04811, + "precision_at_5": 0.03711, + "precision_at_10": 0.03299, + "precision_at_20": 0.02474, + "precision_at_100": 0.01021, + "precision_at_1000": 0.00205, + "mrr_at_1": 0.113402, + "mrr_at_3": 0.118557, + "mrr_at_5": 0.125773, + "mrr_at_10": 0.140861, + "mrr_at_20": 0.146298, + "mrr_at_100": 0.150884, + "mrr_at_1000": 0.152374, + "nauc_ndcg_at_1_max": 0.323649, + "nauc_ndcg_at_1_std": 0.05168, + "nauc_ndcg_at_1_diff1": -0.04881, + "nauc_ndcg_at_3_max": 0.314873, + "nauc_ndcg_at_3_std": 0.068993, + "nauc_ndcg_at_3_diff1": -0.118527, + "nauc_ndcg_at_5_max": 0.338208, + "nauc_ndcg_at_5_std": 0.138891, + "nauc_ndcg_at_5_diff1": -0.079323, + "nauc_ndcg_at_10_max": 0.305518, + "nauc_ndcg_at_10_std": 0.129599, + "nauc_ndcg_at_10_diff1": -0.023681, + "nauc_ndcg_at_20_max": 0.266592, + "nauc_ndcg_at_20_std": 0.152967, + "nauc_ndcg_at_20_diff1": -0.013657, + "nauc_ndcg_at_100_max": 0.264951, + "nauc_ndcg_at_100_std": 0.124765, + "nauc_ndcg_at_100_diff1": -0.005643, + "nauc_ndcg_at_1000_max": 0.331649, + "nauc_ndcg_at_1000_std": 0.195976, + "nauc_ndcg_at_1000_diff1": -0.009288, + "nauc_map_at_1_max": 0.266084, + "nauc_map_at_1_std": 0.076854, + "nauc_map_at_1_diff1": -0.124176, + "nauc_map_at_3_max": 0.294685, + "nauc_map_at_3_std": 0.070483, + "nauc_map_at_3_diff1": -0.137766, + "nauc_map_at_5_max": 0.326194, + "nauc_map_at_5_std": 0.107143, + "nauc_map_at_5_diff1": -0.104026, + "nauc_map_at_10_max": 0.306734, + "nauc_map_at_10_std": 0.100462, + "nauc_map_at_10_diff1": -0.080803, + "nauc_map_at_20_max": 0.293665, + "nauc_map_at_20_std": 0.116211, + "nauc_map_at_20_diff1": -0.065287, + "nauc_map_at_100_max": 0.292759, + "nauc_map_at_100_std": 0.11788, + "nauc_map_at_100_diff1": -0.065283, + "nauc_map_at_1000_max": 0.296455, + "nauc_map_at_1000_std": 0.12323, + "nauc_map_at_1000_diff1": -0.064704, + "nauc_recall_at_1_max": 0.266084, + "nauc_recall_at_1_std": 0.076854, + "nauc_recall_at_1_diff1": -0.124176, + "nauc_recall_at_3_max": 0.292997, + "nauc_recall_at_3_std": 0.067898, + "nauc_recall_at_3_diff1": -0.136678, + "nauc_recall_at_5_max": 0.362115, + "nauc_recall_at_5_std": 0.232025, + "nauc_recall_at_5_diff1": -0.077038, + "nauc_recall_at_10_max": 0.256442, + "nauc_recall_at_10_std": 0.172211, + "nauc_recall_at_10_diff1": 0.003801, + "nauc_recall_at_20_max": 0.158115, + "nauc_recall_at_20_std": 0.195897, + "nauc_recall_at_20_diff1": 0.02553, + "nauc_recall_at_100_max": 0.151982, + "nauc_recall_at_100_std": 0.101226, + "nauc_recall_at_100_diff1": 0.020327, + "nauc_recall_at_1000_max": 0.442007, + "nauc_recall_at_1000_std": 0.464138, + "nauc_recall_at_1000_diff1": 0.014884, + "nauc_precision_at_1_max": 0.323649, + "nauc_precision_at_1_std": 0.05168, + "nauc_precision_at_1_diff1": -0.04881, + "nauc_precision_at_3_max": 0.365344, + "nauc_precision_at_3_std": 0.044712, + "nauc_precision_at_3_diff1": -0.094317, + "nauc_precision_at_5_max": 0.436809, + "nauc_precision_at_5_std": 0.189258, + "nauc_precision_at_5_diff1": -0.025376, + "nauc_precision_at_10_max": 0.286654, + "nauc_precision_at_10_std": 0.127442, + "nauc_precision_at_10_diff1": 0.128429, + "nauc_precision_at_20_max": 0.234475, + "nauc_precision_at_20_std": 0.177441, + "nauc_precision_at_20_diff1": 0.106265, + "nauc_precision_at_100_max": 0.224912, + "nauc_precision_at_100_std": 0.091955, + "nauc_precision_at_100_diff1": 0.125145, + "nauc_precision_at_1000_max": 0.249765, + "nauc_precision_at_1000_std": 0.138367, + "nauc_precision_at_1000_diff1": 0.106253, + "nauc_mrr_at_1_max": 0.323649, + "nauc_mrr_at_1_std": 0.05168, + "nauc_mrr_at_1_diff1": -0.04881, + "nauc_mrr_at_3_max": 0.318182, + "nauc_mrr_at_3_std": 0.040718, + "nauc_mrr_at_3_diff1": -0.042929, + "nauc_mrr_at_5_max": 0.329891, + "nauc_mrr_at_5_std": 0.100052, + "nauc_mrr_at_5_diff1": -0.045007, + "nauc_mrr_at_10_max": 0.310308, + "nauc_mrr_at_10_std": 0.104638, + "nauc_mrr_at_10_diff1": -0.006304, + "nauc_mrr_at_20_max": 0.302028, + "nauc_mrr_at_20_std": 0.10301, + "nauc_mrr_at_20_diff1": -0.01068, + "nauc_mrr_at_100_max": 0.302876, + "nauc_mrr_at_100_std": 0.097029, + "nauc_mrr_at_100_diff1": -0.009803, + "nauc_mrr_at_1000_max": 0.304427, + "nauc_mrr_at_1000_std": 0.099042, + "nauc_mrr_at_1000_diff1": -0.011623, + "main_score": 0.0998, + "hf_subset": "MedXpertQA-Exam", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.08475, + "ndcg_at_3": 0.08365, + "ndcg_at_5": 0.10669, + "ndcg_at_10": 0.12328, + "ndcg_at_20": 0.15568, + "ndcg_at_100": 0.21151, + "ndcg_at_1000": 0.27669, + "map_at_1": 0.02599, + "map_at_3": 0.04921, + "map_at_5": 0.06861, + "map_at_10": 0.07837, + "map_at_20": 0.08819, + "map_at_100": 0.09923, + "map_at_1000": 0.10284, + "recall_at_1": 0.02599, + "recall_at_3": 0.06923, + "recall_at_5": 0.12735, + "recall_at_10": 0.16642, + "recall_at_20": 0.25008, + "recall_at_100": 0.44219, + "recall_at_1000": 0.78205, + "precision_at_1": 0.08475, + "precision_at_3": 0.07345, + "precision_at_5": 0.07966, + "precision_at_10": 0.05593, + "precision_at_20": 0.04492, + "precision_at_100": 0.01763, + "precision_at_1000": 0.00331, + "mrr_at_1": 0.084746, + "mrr_at_3": 0.121469, + "mrr_at_5": 0.149859, + "mrr_at_10": 0.158542, + "mrr_at_20": 0.170219, + "mrr_at_100": 0.174855, + "mrr_at_1000": 0.175879, + "nauc_ndcg_at_1_max": -0.029441, + "nauc_ndcg_at_1_std": 0.046113, + "nauc_ndcg_at_1_diff1": 0.197663, + "nauc_ndcg_at_3_max": -0.022104, + "nauc_ndcg_at_3_std": 0.132914, + "nauc_ndcg_at_3_diff1": 0.147823, + "nauc_ndcg_at_5_max": -0.119047, + "nauc_ndcg_at_5_std": 0.12681, + "nauc_ndcg_at_5_diff1": 0.173897, + "nauc_ndcg_at_10_max": -0.061762, + "nauc_ndcg_at_10_std": 0.157979, + "nauc_ndcg_at_10_diff1": 0.216251, + "nauc_ndcg_at_20_max": -0.045682, + "nauc_ndcg_at_20_std": 0.167598, + "nauc_ndcg_at_20_diff1": 0.178288, + "nauc_ndcg_at_100_max": 0.01301, + "nauc_ndcg_at_100_std": 0.207773, + "nauc_ndcg_at_100_diff1": 0.15024, + "nauc_ndcg_at_1000_max": 0.009224, + "nauc_ndcg_at_1000_std": 0.207124, + "nauc_ndcg_at_1000_diff1": 0.13497, + "nauc_map_at_1_max": -0.152929, + "nauc_map_at_1_std": 0.087936, + "nauc_map_at_1_diff1": 0.115847, + "nauc_map_at_3_max": -0.118009, + "nauc_map_at_3_std": 0.151786, + "nauc_map_at_3_diff1": 0.150023, + "nauc_map_at_5_max": -0.154728, + "nauc_map_at_5_std": 0.16049, + "nauc_map_at_5_diff1": 0.200927, + "nauc_map_at_10_max": -0.094409, + "nauc_map_at_10_std": 0.192397, + "nauc_map_at_10_diff1": 0.234957, + "nauc_map_at_20_max": -0.080221, + "nauc_map_at_20_std": 0.193576, + "nauc_map_at_20_diff1": 0.213649, + "nauc_map_at_100_max": -0.058868, + "nauc_map_at_100_std": 0.205568, + "nauc_map_at_100_diff1": 0.20106, + "nauc_map_at_1000_max": -0.058128, + "nauc_map_at_1000_std": 0.204234, + "nauc_map_at_1000_diff1": 0.198807, + "nauc_recall_at_1_max": -0.152929, + "nauc_recall_at_1_std": 0.087936, + "nauc_recall_at_1_diff1": 0.115847, + "nauc_recall_at_3_max": -0.08633, + "nauc_recall_at_3_std": 0.137919, + "nauc_recall_at_3_diff1": 0.115097, + "nauc_recall_at_5_max": -0.196908, + "nauc_recall_at_5_std": 0.111105, + "nauc_recall_at_5_diff1": 0.163804, + "nauc_recall_at_10_max": -0.080276, + "nauc_recall_at_10_std": 0.153245, + "nauc_recall_at_10_diff1": 0.210676, + "nauc_recall_at_20_max": -0.036814, + "nauc_recall_at_20_std": 0.169199, + "nauc_recall_at_20_diff1": 0.121589, + "nauc_recall_at_100_max": 0.092912, + "nauc_recall_at_100_std": 0.276324, + "nauc_recall_at_100_diff1": 0.097806, + "nauc_recall_at_1000_max": 0.14599, + "nauc_recall_at_1000_std": 0.403687, + "nauc_recall_at_1000_diff1": -0.010984, + "nauc_precision_at_1_max": -0.029441, + "nauc_precision_at_1_std": 0.046113, + "nauc_precision_at_1_diff1": 0.197663, + "nauc_precision_at_3_max": 0.038544, + "nauc_precision_at_3_std": 0.17519, + "nauc_precision_at_3_diff1": 0.175462, + "nauc_precision_at_5_max": -0.021561, + "nauc_precision_at_5_std": 0.170437, + "nauc_precision_at_5_diff1": 0.235828, + "nauc_precision_at_10_max": 0.07215, + "nauc_precision_at_10_std": 0.181737, + "nauc_precision_at_10_diff1": 0.277706, + "nauc_precision_at_20_max": 0.067358, + "nauc_precision_at_20_std": 0.168947, + "nauc_precision_at_20_diff1": 0.200733, + "nauc_precision_at_100_max": 0.130449, + "nauc_precision_at_100_std": 0.167266, + "nauc_precision_at_100_diff1": 0.089913, + "nauc_precision_at_1000_max": 0.104472, + "nauc_precision_at_1000_std": 0.044815, + "nauc_precision_at_1000_diff1": 0.016523, + "nauc_mrr_at_1_max": -0.029441, + "nauc_mrr_at_1_std": 0.046113, + "nauc_mrr_at_1_diff1": 0.197663, + "nauc_mrr_at_3_max": -0.003512, + "nauc_mrr_at_3_std": 0.088184, + "nauc_mrr_at_3_diff1": 0.122524, + "nauc_mrr_at_5_max": -0.04136, + "nauc_mrr_at_5_std": 0.076363, + "nauc_mrr_at_5_diff1": 0.127987, + "nauc_mrr_at_10_max": -0.033426, + "nauc_mrr_at_10_std": 0.073384, + "nauc_mrr_at_10_diff1": 0.144803, + "nauc_mrr_at_20_max": -0.036685, + "nauc_mrr_at_20_std": 0.072155, + "nauc_mrr_at_20_diff1": 0.143211, + "nauc_mrr_at_100_max": -0.029426, + "nauc_mrr_at_100_std": 0.075252, + "nauc_mrr_at_100_diff1": 0.139969, + "nauc_mrr_at_1000_max": -0.029612, + "nauc_mrr_at_1000_std": 0.075173, + "nauc_mrr_at_1000_diff1": 0.139132, + "main_score": 0.12328, + "hf_subset": "MedQA-Diag", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.5, + "ndcg_at_3": 0.45957, + "ndcg_at_5": 0.47062, + "ndcg_at_10": 0.5012, + "ndcg_at_20": 0.52069, + "ndcg_at_100": 0.54895, + "ndcg_at_1000": 0.57603, + "map_at_1": 0.32211, + "map_at_3": 0.40056, + "map_at_5": 0.4202, + "map_at_10": 0.43579, + "map_at_20": 0.44343, + "map_at_100": 0.44913, + "map_at_1000": 0.45027, + "recall_at_1": 0.32211, + "recall_at_3": 0.43533, + "recall_at_5": 0.48322, + "recall_at_10": 0.559, + "recall_at_20": 0.61856, + "recall_at_100": 0.73956, + "recall_at_1000": 0.92567, + "precision_at_1": 0.5, + "precision_at_3": 0.26222, + "precision_at_5": 0.184, + "precision_at_10": 0.11, + "precision_at_20": 0.062, + "precision_at_100": 0.01527, + "precision_at_1000": 0.00193, + "mrr_at_1": 0.5, + "mrr_at_3": 0.548889, + "mrr_at_5": 0.560556, + "mrr_at_10": 0.571717, + "mrr_at_20": 0.57438, + "mrr_at_100": 0.576359, + "mrr_at_1000": 0.576732, + "nauc_ndcg_at_1_max": 0.415741, + "nauc_ndcg_at_1_std": -0.040027, + "nauc_ndcg_at_1_diff1": 0.488661, + "nauc_ndcg_at_3_max": 0.325316, + "nauc_ndcg_at_3_std": -0.049727, + "nauc_ndcg_at_3_diff1": 0.365209, + "nauc_ndcg_at_5_max": 0.324178, + "nauc_ndcg_at_5_std": -0.068489, + "nauc_ndcg_at_5_diff1": 0.363413, + "nauc_ndcg_at_10_max": 0.334896, + "nauc_ndcg_at_10_std": -0.041495, + "nauc_ndcg_at_10_diff1": 0.361855, + "nauc_ndcg_at_20_max": 0.339288, + "nauc_ndcg_at_20_std": -0.015081, + "nauc_ndcg_at_20_diff1": 0.355188, + "nauc_ndcg_at_100_max": 0.33719, + "nauc_ndcg_at_100_std": -0.010199, + "nauc_ndcg_at_100_diff1": 0.346953, + "nauc_ndcg_at_1000_max": 0.344784, + "nauc_ndcg_at_1000_std": -0.012536, + "nauc_ndcg_at_1000_diff1": 0.370487, + "nauc_map_at_1_max": 0.164119, + "nauc_map_at_1_std": -0.093852, + "nauc_map_at_1_diff1": 0.330326, + "nauc_map_at_3_max": 0.257793, + "nauc_map_at_3_std": -0.067487, + "nauc_map_at_3_diff1": 0.350094, + "nauc_map_at_5_max": 0.283128, + "nauc_map_at_5_std": -0.077242, + "nauc_map_at_5_diff1": 0.34112, + "nauc_map_at_10_max": 0.292461, + "nauc_map_at_10_std": -0.066405, + "nauc_map_at_10_diff1": 0.339308, + "nauc_map_at_20_max": 0.293853, + "nauc_map_at_20_std": -0.054566, + "nauc_map_at_20_diff1": 0.337581, + "nauc_map_at_100_max": 0.295299, + "nauc_map_at_100_std": -0.052226, + "nauc_map_at_100_diff1": 0.335236, + "nauc_map_at_1000_max": 0.295982, + "nauc_map_at_1000_std": -0.051916, + "nauc_map_at_1000_diff1": 0.336713, + "nauc_recall_at_1_max": 0.164119, + "nauc_recall_at_1_std": -0.093852, + "nauc_recall_at_1_diff1": 0.330326, + "nauc_recall_at_3_max": 0.24448, + "nauc_recall_at_3_std": -0.057527, + "nauc_recall_at_3_diff1": 0.321677, + "nauc_recall_at_5_max": 0.266355, + "nauc_recall_at_5_std": -0.088203, + "nauc_recall_at_5_diff1": 0.294694, + "nauc_recall_at_10_max": 0.27403, + "nauc_recall_at_10_std": -0.020617, + "nauc_recall_at_10_diff1": 0.266443, + "nauc_recall_at_20_max": 0.272079, + "nauc_recall_at_20_std": 0.059077, + "nauc_recall_at_20_diff1": 0.22148, + "nauc_recall_at_100_max": 0.219625, + "nauc_recall_at_100_std": 0.081859, + "nauc_recall_at_100_diff1": 0.12589, + "nauc_recall_at_1000_max": 0.140405, + "nauc_recall_at_1000_std": 0.148715, + "nauc_recall_at_1000_diff1": 0.191624, + "nauc_precision_at_1_max": 0.415741, + "nauc_precision_at_1_std": -0.040027, + "nauc_precision_at_1_diff1": 0.488661, + "nauc_precision_at_3_max": 0.446112, + "nauc_precision_at_3_std": 0.027728, + "nauc_precision_at_3_diff1": 0.290211, + "nauc_precision_at_5_max": 0.465786, + "nauc_precision_at_5_std": -0.009449, + "nauc_precision_at_5_diff1": 0.230562, + "nauc_precision_at_10_max": 0.434104, + "nauc_precision_at_10_std": 0.054199, + "nauc_precision_at_10_diff1": 0.189399, + "nauc_precision_at_20_max": 0.393767, + "nauc_precision_at_20_std": 0.14048, + "nauc_precision_at_20_diff1": 0.14454, + "nauc_precision_at_100_max": 0.32315, + "nauc_precision_at_100_std": 0.174951, + "nauc_precision_at_100_diff1": 0.068144, + "nauc_precision_at_1000_max": 0.255431, + "nauc_precision_at_1000_std": 0.125457, + "nauc_precision_at_1000_diff1": 0.09977, + "nauc_mrr_at_1_max": 0.415741, + "nauc_mrr_at_1_std": -0.040027, + "nauc_mrr_at_1_diff1": 0.488661, + "nauc_mrr_at_3_max": 0.458234, + "nauc_mrr_at_3_std": -0.012417, + "nauc_mrr_at_3_diff1": 0.49617, + "nauc_mrr_at_5_max": 0.451509, + "nauc_mrr_at_5_std": -0.029024, + "nauc_mrr_at_5_diff1": 0.492501, + "nauc_mrr_at_10_max": 0.446438, + "nauc_mrr_at_10_std": -0.01549, + "nauc_mrr_at_10_diff1": 0.49285, + "nauc_mrr_at_20_max": 0.446617, + "nauc_mrr_at_20_std": -0.014017, + "nauc_mrr_at_20_diff1": 0.489959, + "nauc_mrr_at_100_max": 0.444637, + "nauc_mrr_at_100_std": -0.015783, + "nauc_mrr_at_100_diff1": 0.489406, + "nauc_mrr_at_1000_max": 0.4447, + "nauc_mrr_at_1000_std": -0.015477, + "nauc_mrr_at_1000_diff1": 0.489534, + "main_score": 0.5012, + "hf_subset": "PMC-Treatment", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.23684, + "ndcg_at_3": 0.24093, + "ndcg_at_5": 0.27116, + "ndcg_at_10": 0.3132, + "ndcg_at_20": 0.34822, + "ndcg_at_100": 0.38772, + "ndcg_at_1000": 0.41837, + "map_at_1": 0.10453, + "map_at_3": 0.18092, + "map_at_5": 0.20702, + "map_at_10": 0.22693, + "map_at_20": 0.23875, + "map_at_100": 0.24706, + "map_at_1000": 0.24875, + "recall_at_1": 0.10453, + "recall_at_3": 0.25219, + "recall_at_5": 0.32602, + "recall_at_10": 0.43056, + "recall_at_20": 0.54313, + "recall_at_100": 0.71053, + "recall_at_1000": 0.90424, + "precision_at_1": 0.23684, + "precision_at_3": 0.17836, + "precision_at_5": 0.13684, + "precision_at_10": 0.09035, + "precision_at_20": 0.05658, + "precision_at_100": 0.01518, + "precision_at_1000": 0.00196, + "mrr_at_1": 0.236842, + "mrr_at_3": 0.327485, + "mrr_at_5": 0.339766, + "mrr_at_10": 0.357574, + "mrr_at_20": 0.364828, + "mrr_at_100": 0.367631, + "mrr_at_1000": 0.368189, + "nauc_ndcg_at_1_max": 0.233554, + "nauc_ndcg_at_1_std": 0.030471, + "nauc_ndcg_at_1_diff1": 0.255415, + "nauc_ndcg_at_3_max": 0.218798, + "nauc_ndcg_at_3_std": 0.075964, + "nauc_ndcg_at_3_diff1": 0.163151, + "nauc_ndcg_at_5_max": 0.228038, + "nauc_ndcg_at_5_std": 0.057727, + "nauc_ndcg_at_5_diff1": 0.157139, + "nauc_ndcg_at_10_max": 0.273951, + "nauc_ndcg_at_10_std": 0.041867, + "nauc_ndcg_at_10_diff1": 0.158704, + "nauc_ndcg_at_20_max": 0.252598, + "nauc_ndcg_at_20_std": 0.047568, + "nauc_ndcg_at_20_diff1": 0.136772, + "nauc_ndcg_at_100_max": 0.269251, + "nauc_ndcg_at_100_std": 0.041975, + "nauc_ndcg_at_100_diff1": 0.136299, + "nauc_ndcg_at_1000_max": 0.257487, + "nauc_ndcg_at_1000_std": 0.065601, + "nauc_ndcg_at_1000_diff1": 0.145482, + "nauc_map_at_1_max": 0.196879, + "nauc_map_at_1_std": 0.043396, + "nauc_map_at_1_diff1": 0.291958, + "nauc_map_at_3_max": 0.231688, + "nauc_map_at_3_std": 0.07947, + "nauc_map_at_3_diff1": 0.208917, + "nauc_map_at_5_max": 0.219872, + "nauc_map_at_5_std": 0.053209, + "nauc_map_at_5_diff1": 0.199851, + "nauc_map_at_10_max": 0.257815, + "nauc_map_at_10_std": 0.04965, + "nauc_map_at_10_diff1": 0.195815, + "nauc_map_at_20_max": 0.247029, + "nauc_map_at_20_std": 0.056218, + "nauc_map_at_20_diff1": 0.188569, + "nauc_map_at_100_max": 0.249552, + "nauc_map_at_100_std": 0.058274, + "nauc_map_at_100_diff1": 0.185355, + "nauc_map_at_1000_max": 0.248762, + "nauc_map_at_1000_std": 0.060795, + "nauc_map_at_1000_diff1": 0.186007, + "nauc_recall_at_1_max": 0.196879, + "nauc_recall_at_1_std": 0.043396, + "nauc_recall_at_1_diff1": 0.291958, + "nauc_recall_at_3_max": 0.196191, + "nauc_recall_at_3_std": 0.055968, + "nauc_recall_at_3_diff1": 0.100644, + "nauc_recall_at_5_max": 0.198721, + "nauc_recall_at_5_std": 0.023266, + "nauc_recall_at_5_diff1": 0.081227, + "nauc_recall_at_10_max": 0.281579, + "nauc_recall_at_10_std": -0.013075, + "nauc_recall_at_10_diff1": 0.084579, + "nauc_recall_at_20_max": 0.215101, + "nauc_recall_at_20_std": -0.016301, + "nauc_recall_at_20_diff1": 0.009206, + "nauc_recall_at_100_max": 0.322884, + "nauc_recall_at_100_std": -0.07188, + "nauc_recall_at_100_diff1": 0.01435, + "nauc_recall_at_1000_max": 0.28482, + "nauc_recall_at_1000_std": 0.045595, + "nauc_recall_at_1000_diff1": 0.081468, + "nauc_precision_at_1_max": 0.233554, + "nauc_precision_at_1_std": 0.030471, + "nauc_precision_at_1_diff1": 0.255415, + "nauc_precision_at_3_max": 0.203412, + "nauc_precision_at_3_std": 0.099719, + "nauc_precision_at_3_diff1": 0.106129, + "nauc_precision_at_5_max": 0.173953, + "nauc_precision_at_5_std": 0.057119, + "nauc_precision_at_5_diff1": 0.079044, + "nauc_precision_at_10_max": 0.251185, + "nauc_precision_at_10_std": 0.02056, + "nauc_precision_at_10_diff1": 0.078826, + "nauc_precision_at_20_max": 0.154342, + "nauc_precision_at_20_std": 0.047606, + "nauc_precision_at_20_diff1": 0.000703, + "nauc_precision_at_100_max": 0.150975, + "nauc_precision_at_100_std": 0.030262, + "nauc_precision_at_100_diff1": -0.025354, + "nauc_precision_at_1000_max": 0.006832, + "nauc_precision_at_1000_std": 0.094593, + "nauc_precision_at_1000_diff1": -0.106002, + "nauc_mrr_at_1_max": 0.233554, + "nauc_mrr_at_1_std": 0.030471, + "nauc_mrr_at_1_diff1": 0.255415, + "nauc_mrr_at_3_max": 0.248303, + "nauc_mrr_at_3_std": 0.066663, + "nauc_mrr_at_3_diff1": 0.176064, + "nauc_mrr_at_5_max": 0.2531, + "nauc_mrr_at_5_std": 0.080964, + "nauc_mrr_at_5_diff1": 0.160845, + "nauc_mrr_at_10_max": 0.248828, + "nauc_mrr_at_10_std": 0.069563, + "nauc_mrr_at_10_diff1": 0.161655, + "nauc_mrr_at_20_max": 0.25015, + "nauc_mrr_at_20_std": 0.066172, + "nauc_mrr_at_20_diff1": 0.162036, + "nauc_mrr_at_100_max": 0.252496, + "nauc_mrr_at_100_std": 0.065941, + "nauc_mrr_at_100_diff1": 0.163104, + "nauc_mrr_at_1000_max": 0.252489, + "nauc_mrr_at_1000_std": 0.066228, + "nauc_mrr_at_1000_diff1": 0.163655, + "main_score": 0.3132, + "hf_subset": "PMC-Clinical", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.26357, + "ndcg_at_3": 0.21412, + "ndcg_at_5": 0.21774, + "ndcg_at_10": 0.27238, + "ndcg_at_20": 0.33003, + "ndcg_at_100": 0.41926, + "ndcg_at_1000": 0.4508, + "map_at_1": 0.08902, + "map_at_3": 0.1309, + "map_at_5": 0.14824, + "map_at_10": 0.17754, + "map_at_20": 0.20025, + "map_at_100": 0.22268, + "map_at_1000": 0.22525, + "recall_at_1": 0.08902, + "recall_at_3": 0.1668, + "recall_at_5": 0.21357, + "recall_at_10": 0.34147, + "recall_at_20": 0.49599, + "recall_at_100": 0.81951, + "recall_at_1000": 0.98553, + "precision_at_1": 0.26357, + "precision_at_3": 0.17313, + "precision_at_5": 0.14419, + "precision_at_10": 0.11628, + "precision_at_20": 0.08605, + "precision_at_100": 0.02915, + "precision_at_1000": 0.0035, + "mrr_at_1": 0.263566, + "mrr_at_3": 0.330749, + "mrr_at_5": 0.349354, + "mrr_at_10": 0.368648, + "mrr_at_20": 0.379299, + "mrr_at_100": 0.383725, + "mrr_at_1000": 0.384117, + "nauc_ndcg_at_1_max": 0.251487, + "nauc_ndcg_at_1_std": 0.164814, + "nauc_ndcg_at_1_diff1": 0.199575, + "nauc_ndcg_at_3_max": 0.127602, + "nauc_ndcg_at_3_std": 0.058471, + "nauc_ndcg_at_3_diff1": 0.058337, + "nauc_ndcg_at_5_max": 0.154467, + "nauc_ndcg_at_5_std": 0.090019, + "nauc_ndcg_at_5_diff1": 0.049979, + "nauc_ndcg_at_10_max": 0.176746, + "nauc_ndcg_at_10_std": 0.088533, + "nauc_ndcg_at_10_diff1": 0.02286, + "nauc_ndcg_at_20_max": 0.23802, + "nauc_ndcg_at_20_std": 0.133409, + "nauc_ndcg_at_20_diff1": 0.002795, + "nauc_ndcg_at_100_max": 0.25512, + "nauc_ndcg_at_100_std": 0.213504, + "nauc_ndcg_at_100_diff1": 0.037355, + "nauc_ndcg_at_1000_max": 0.213416, + "nauc_ndcg_at_1000_std": 0.19074, + "nauc_ndcg_at_1000_diff1": 0.016146, + "nauc_map_at_1_max": 0.123542, + "nauc_map_at_1_std": 0.042831, + "nauc_map_at_1_diff1": 0.233598, + "nauc_map_at_3_max": 0.113508, + "nauc_map_at_3_std": 0.015258, + "nauc_map_at_3_diff1": 0.128684, + "nauc_map_at_5_max": 0.130487, + "nauc_map_at_5_std": 0.056758, + "nauc_map_at_5_diff1": 0.096251, + "nauc_map_at_10_max": 0.146925, + "nauc_map_at_10_std": 0.061456, + "nauc_map_at_10_diff1": 0.0714, + "nauc_map_at_20_max": 0.17387, + "nauc_map_at_20_std": 0.076282, + "nauc_map_at_20_diff1": 0.057495, + "nauc_map_at_100_max": 0.18185, + "nauc_map_at_100_std": 0.103256, + "nauc_map_at_100_diff1": 0.054941, + "nauc_map_at_1000_max": 0.178533, + "nauc_map_at_1000_std": 0.102891, + "nauc_map_at_1000_diff1": 0.052889, + "nauc_recall_at_1_max": 0.123542, + "nauc_recall_at_1_std": 0.042831, + "nauc_recall_at_1_diff1": 0.233598, + "nauc_recall_at_3_max": 0.060812, + "nauc_recall_at_3_std": -0.026973, + "nauc_recall_at_3_diff1": 0.050769, + "nauc_recall_at_5_max": 0.097687, + "nauc_recall_at_5_std": 0.048948, + "nauc_recall_at_5_diff1": -0.010515, + "nauc_recall_at_10_max": 0.124768, + "nauc_recall_at_10_std": 0.030929, + "nauc_recall_at_10_diff1": -0.049361, + "nauc_recall_at_20_max": 0.246583, + "nauc_recall_at_20_std": 0.113884, + "nauc_recall_at_20_diff1": -0.078964, + "nauc_recall_at_100_max": 0.363363, + "nauc_recall_at_100_std": 0.39846, + "nauc_recall_at_100_diff1": 0.076318, + "nauc_recall_at_1000_max": -0.732735, + "nauc_recall_at_1000_std": 0.96262, + "nauc_recall_at_1000_diff1": -0.913483, + "nauc_precision_at_1_max": 0.251487, + "nauc_precision_at_1_std": 0.164814, + "nauc_precision_at_1_diff1": 0.199575, + "nauc_precision_at_3_max": 0.143864, + "nauc_precision_at_3_std": 0.088898, + "nauc_precision_at_3_diff1": -0.045132, + "nauc_precision_at_5_max": 0.174311, + "nauc_precision_at_5_std": 0.156645, + "nauc_precision_at_5_diff1": -0.105696, + "nauc_precision_at_10_max": 0.205224, + "nauc_precision_at_10_std": 0.152864, + "nauc_precision_at_10_diff1": -0.163463, + "nauc_precision_at_20_max": 0.283828, + "nauc_precision_at_20_std": 0.232267, + "nauc_precision_at_20_diff1": -0.189969, + "nauc_precision_at_100_max": 0.246743, + "nauc_precision_at_100_std": 0.384174, + "nauc_precision_at_100_diff1": -0.089921, + "nauc_precision_at_1000_max": 0.10642, + "nauc_precision_at_1000_std": 0.307566, + "nauc_precision_at_1000_diff1": -0.142056, + "nauc_mrr_at_1_max": 0.251487, + "nauc_mrr_at_1_std": 0.164814, + "nauc_mrr_at_1_diff1": 0.199575, + "nauc_mrr_at_3_max": 0.213648, + "nauc_mrr_at_3_std": 0.129369, + "nauc_mrr_at_3_diff1": 0.109566, + "nauc_mrr_at_5_max": 0.22984, + "nauc_mrr_at_5_std": 0.136565, + "nauc_mrr_at_5_diff1": 0.102092, + "nauc_mrr_at_10_max": 0.2283, + "nauc_mrr_at_10_std": 0.14098, + "nauc_mrr_at_10_diff1": 0.09437, + "nauc_mrr_at_20_max": 0.241638, + "nauc_mrr_at_20_std": 0.152304, + "nauc_mrr_at_20_diff1": 0.096012, + "nauc_mrr_at_100_max": 0.238516, + "nauc_mrr_at_100_std": 0.153317, + "nauc_mrr_at_100_diff1": 0.102648, + "nauc_mrr_at_1000_max": 0.237725, + "nauc_mrr_at_1000_std": 0.152462, + "nauc_mrr_at_1000_diff1": 0.102452, + "main_score": 0.27238, + "hf_subset": "IIYi-Clinical", + "languages": [ + "eng-Latn" + ] + } + ] + }, + "evaluation_time": 15704.703388214111, + "kg_co2_emissions": null +} \ No newline at end of file diff --git a/results/intfloat__e5-mistral-7b-instruct/07163b72af1488142a360786df853f237b1a3ca1/R2MEDRetrieval.json b/results/intfloat__e5-mistral-7b-instruct/07163b72af1488142a360786df853f237b1a3ca1/R2MEDRetrieval.json new file mode 100644 index 0000000000..ef145c5540 --- /dev/null +++ b/results/intfloat__e5-mistral-7b-instruct/07163b72af1488142a360786df853f237b1a3ca1/R2MEDRetrieval.json @@ -0,0 +1,1187 @@ +{ + "dataset_revision": "1.0", + "task_name": "R2MEDRetrieval", + "mteb_version": "1.38.20", + "scores": { + "test": [ + { + "ndcg_at_1": 0.18447, + "ndcg_at_3": 0.14883, + "ndcg_at_5": 0.15893, + "ndcg_at_10": 0.18539, + "ndcg_at_20": 0.20575, + "ndcg_at_100": 0.26809, + "ndcg_at_1000": 0.32637, + "map_at_1": 0.05563, + "map_at_3": 0.08392, + "map_at_5": 0.10478, + "map_at_10": 0.12377, + "map_at_20": 0.13334, + "map_at_100": 0.14601, + "map_at_1000": 0.14925, + "recall_at_1": 0.05563, + "recall_at_3": 0.10137, + "recall_at_5": 0.14848, + "recall_at_10": 0.22393, + "recall_at_20": 0.27917, + "recall_at_100": 0.51557, + "recall_at_1000": 0.83962, + "precision_at_1": 0.18447, + "precision_at_3": 0.12298, + "precision_at_5": 0.11068, + "precision_at_10": 0.08932, + "precision_at_20": 0.05631, + "precision_at_100": 0.01961, + "precision_at_1000": 0.00315, + "mrr_at_1": 0.184466, + "mrr_at_3": 0.218447, + "mrr_at_5": 0.232039, + "mrr_at_10": 0.249087, + "mrr_at_20": 0.251176, + "mrr_at_100": 0.256606, + "mrr_at_1000": 0.257827, + "nauc_ndcg_at_1_max": -0.031218, + "nauc_ndcg_at_1_std": -0.311016, + "nauc_ndcg_at_1_diff1": 0.105578, + "nauc_ndcg_at_3_max": -0.033159, + "nauc_ndcg_at_3_std": -0.296413, + "nauc_ndcg_at_3_diff1": 0.037659, + "nauc_ndcg_at_5_max": -0.073355, + "nauc_ndcg_at_5_std": -0.341181, + "nauc_ndcg_at_5_diff1": 0.034375, + "nauc_ndcg_at_10_max": -0.095267, + "nauc_ndcg_at_10_std": -0.342975, + "nauc_ndcg_at_10_diff1": 0.052268, + "nauc_ndcg_at_20_max": -0.08178, + "nauc_ndcg_at_20_std": -0.336821, + "nauc_ndcg_at_20_diff1": 0.094949, + "nauc_ndcg_at_100_max": -0.092801, + "nauc_ndcg_at_100_std": -0.353489, + "nauc_ndcg_at_100_diff1": 0.070757, + "nauc_ndcg_at_1000_max": -0.090286, + "nauc_ndcg_at_1000_std": -0.332227, + "nauc_ndcg_at_1000_diff1": 0.067265, + "nauc_map_at_1_max": -0.046139, + "nauc_map_at_1_std": -0.344642, + "nauc_map_at_1_diff1": 0.063797, + "nauc_map_at_3_max": -0.034617, + "nauc_map_at_3_std": -0.329261, + "nauc_map_at_3_diff1": 0.060258, + "nauc_map_at_5_max": -0.053515, + "nauc_map_at_5_std": -0.33879, + "nauc_map_at_5_diff1": 0.071525, + "nauc_map_at_10_max": -0.080743, + "nauc_map_at_10_std": -0.341027, + "nauc_map_at_10_diff1": 0.070425, + "nauc_map_at_20_max": -0.074203, + "nauc_map_at_20_std": -0.34268, + "nauc_map_at_20_diff1": 0.094444, + "nauc_map_at_100_max": -0.078101, + "nauc_map_at_100_std": -0.345525, + "nauc_map_at_100_diff1": 0.088407, + "nauc_map_at_1000_max": -0.079066, + "nauc_map_at_1000_std": -0.344567, + "nauc_map_at_1000_diff1": 0.086905, + "nauc_recall_at_1_max": -0.046139, + "nauc_recall_at_1_std": -0.344642, + "nauc_recall_at_1_diff1": 0.063797, + "nauc_recall_at_3_max": -0.02488, + "nauc_recall_at_3_std": -0.307001, + "nauc_recall_at_3_diff1": 0.015256, + "nauc_recall_at_5_max": -0.080205, + "nauc_recall_at_5_std": -0.331552, + "nauc_recall_at_5_diff1": 0.028456, + "nauc_recall_at_10_max": -0.141517, + "nauc_recall_at_10_std": -0.333443, + "nauc_recall_at_10_diff1": 0.034263, + "nauc_recall_at_20_max": -0.106387, + "nauc_recall_at_20_std": -0.307223, + "nauc_recall_at_20_diff1": 0.123405, + "nauc_recall_at_100_max": -0.112365, + "nauc_recall_at_100_std": -0.31372, + "nauc_recall_at_100_diff1": 0.074026, + "nauc_recall_at_1000_max": -0.13086, + "nauc_recall_at_1000_std": -0.074858, + "nauc_recall_at_1000_diff1": 0.041845, + "nauc_precision_at_1_max": -0.031218, + "nauc_precision_at_1_std": -0.311016, + "nauc_precision_at_1_diff1": 0.105578, + "nauc_precision_at_3_max": -0.014656, + "nauc_precision_at_3_std": -0.267675, + "nauc_precision_at_3_diff1": 0.0422, + "nauc_precision_at_5_max": -0.08185, + "nauc_precision_at_5_std": -0.322683, + "nauc_precision_at_5_diff1": 0.042909, + "nauc_precision_at_10_max": -0.169836, + "nauc_precision_at_10_std": -0.340292, + "nauc_precision_at_10_diff1": 0.02571, + "nauc_precision_at_20_max": -0.152569, + "nauc_precision_at_20_std": -0.319751, + "nauc_precision_at_20_diff1": 0.084281, + "nauc_precision_at_100_max": -0.159951, + "nauc_precision_at_100_std": -0.283361, + "nauc_precision_at_100_diff1": -0.018603, + "nauc_precision_at_1000_max": -0.156733, + "nauc_precision_at_1000_std": -0.198002, + "nauc_precision_at_1000_diff1": -0.068379, + "nauc_mrr_at_1_max": -0.031218, + "nauc_mrr_at_1_std": -0.311016, + "nauc_mrr_at_1_diff1": 0.105578, + "nauc_mrr_at_3_max": 0.003338, + "nauc_mrr_at_3_std": -0.297478, + "nauc_mrr_at_3_diff1": 0.062653, + "nauc_mrr_at_5_max": -0.020788, + "nauc_mrr_at_5_std": -0.310554, + "nauc_mrr_at_5_diff1": 0.04404, + "nauc_mrr_at_10_max": -0.034684, + "nauc_mrr_at_10_std": -0.322403, + "nauc_mrr_at_10_diff1": 0.054593, + "nauc_mrr_at_20_max": -0.035749, + "nauc_mrr_at_20_std": -0.317797, + "nauc_mrr_at_20_diff1": 0.054051, + "nauc_mrr_at_100_max": -0.036437, + "nauc_mrr_at_100_std": -0.322493, + "nauc_mrr_at_100_diff1": 0.052423, + "nauc_mrr_at_1000_max": -0.035898, + "nauc_mrr_at_1000_std": -0.321694, + "nauc_mrr_at_1000_diff1": 0.053062, + "main_score": 0.18539, + "hf_subset": "Biology", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.28571, + "ndcg_at_3": 0.31465, + "ndcg_at_5": 0.34448, + "ndcg_at_10": 0.38514, + "ndcg_at_20": 0.41776, + "ndcg_at_100": 0.47252, + "ndcg_at_1000": 0.49956, + "map_at_1": 0.13476, + "map_at_3": 0.23286, + "map_at_5": 0.27085, + "map_at_10": 0.2987, + "map_at_20": 0.31238, + "map_at_100": 0.32535, + "map_at_1000": 0.32767, + "recall_at_1": 0.13476, + "recall_at_3": 0.29915, + "recall_at_5": 0.40598, + "recall_at_10": 0.5141, + "recall_at_20": 0.60275, + "recall_at_100": 0.81177, + "recall_at_1000": 0.95485, + "precision_at_1": 0.28571, + "precision_at_3": 0.22511, + "precision_at_5": 0.18701, + "precision_at_10": 0.12987, + "precision_at_20": 0.08182, + "precision_at_100": 0.02364, + "precision_at_1000": 0.00288, + "mrr_at_1": 0.285714, + "mrr_at_3": 0.365801, + "mrr_at_5": 0.392424, + "mrr_at_10": 0.406519, + "mrr_at_20": 0.410515, + "mrr_at_100": 0.414194, + "mrr_at_1000": 0.41452, + "nauc_ndcg_at_1_max": 0.055892, + "nauc_ndcg_at_1_std": -0.079817, + "nauc_ndcg_at_1_diff1": 0.133511, + "nauc_ndcg_at_3_max": 0.027999, + "nauc_ndcg_at_3_std": -0.043923, + "nauc_ndcg_at_3_diff1": 0.034002, + "nauc_ndcg_at_5_max": 0.118332, + "nauc_ndcg_at_5_std": -0.048474, + "nauc_ndcg_at_5_diff1": 0.017019, + "nauc_ndcg_at_10_max": 0.173467, + "nauc_ndcg_at_10_std": -0.025985, + "nauc_ndcg_at_10_diff1": 0.050426, + "nauc_ndcg_at_20_max": 0.18853, + "nauc_ndcg_at_20_std": 0.016767, + "nauc_ndcg_at_20_diff1": 0.048687, + "nauc_ndcg_at_100_max": 0.164646, + "nauc_ndcg_at_100_std": 0.028276, + "nauc_ndcg_at_100_diff1": 0.056083, + "nauc_ndcg_at_1000_max": 0.158605, + "nauc_ndcg_at_1000_std": -0.000985, + "nauc_ndcg_at_1000_diff1": 0.052098, + "nauc_map_at_1_max": -0.013832, + "nauc_map_at_1_std": -0.104386, + "nauc_map_at_1_diff1": 0.106182, + "nauc_map_at_3_max": 0.020238, + "nauc_map_at_3_std": -0.051858, + "nauc_map_at_3_diff1": 0.052567, + "nauc_map_at_5_max": 0.103015, + "nauc_map_at_5_std": -0.040559, + "nauc_map_at_5_diff1": 0.023376, + "nauc_map_at_10_max": 0.131809, + "nauc_map_at_10_std": -0.035664, + "nauc_map_at_10_diff1": 0.039175, + "nauc_map_at_20_max": 0.136312, + "nauc_map_at_20_std": -0.025361, + "nauc_map_at_20_diff1": 0.039927, + "nauc_map_at_100_max": 0.134341, + "nauc_map_at_100_std": -0.018601, + "nauc_map_at_100_diff1": 0.046123, + "nauc_map_at_1000_max": 0.13307, + "nauc_map_at_1000_std": -0.021012, + "nauc_map_at_1000_diff1": 0.045417, + "nauc_recall_at_1_max": -0.013832, + "nauc_recall_at_1_std": -0.104386, + "nauc_recall_at_1_diff1": 0.106182, + "nauc_recall_at_3_max": -0.002898, + "nauc_recall_at_3_std": -0.035153, + "nauc_recall_at_3_diff1": -0.00861, + "nauc_recall_at_5_max": 0.148983, + "nauc_recall_at_5_std": -0.039911, + "nauc_recall_at_5_diff1": -0.054138, + "nauc_recall_at_10_max": 0.266497, + "nauc_recall_at_10_std": 0.022444, + "nauc_recall_at_10_diff1": 0.02186, + "nauc_recall_at_20_max": 0.345397, + "nauc_recall_at_20_std": 0.170669, + "nauc_recall_at_20_diff1": 0.015437, + "nauc_recall_at_100_max": 0.280135, + "nauc_recall_at_100_std": 0.344058, + "nauc_recall_at_100_diff1": -0.004955, + "nauc_recall_at_1000_max": 0.396205, + "nauc_recall_at_1000_std": 0.270561, + "nauc_recall_at_1000_diff1": -0.518075, + "nauc_precision_at_1_max": 0.055892, + "nauc_precision_at_1_std": -0.079817, + "nauc_precision_at_1_diff1": 0.133511, + "nauc_precision_at_3_max": 0.111092, + "nauc_precision_at_3_std": -0.023327, + "nauc_precision_at_3_diff1": -0.044645, + "nauc_precision_at_5_max": 0.277164, + "nauc_precision_at_5_std": 0.005212, + "nauc_precision_at_5_diff1": -0.075108, + "nauc_precision_at_10_max": 0.272674, + "nauc_precision_at_10_std": 0.011871, + "nauc_precision_at_10_diff1": 0.038375, + "nauc_precision_at_20_max": 0.215579, + "nauc_precision_at_20_std": 0.078331, + "nauc_precision_at_20_diff1": 0.021099, + "nauc_precision_at_100_max": 0.107017, + "nauc_precision_at_100_std": 0.06002, + "nauc_precision_at_100_diff1": 0.050072, + "nauc_precision_at_1000_max": 0.062661, + "nauc_precision_at_1000_std": -0.011558, + "nauc_precision_at_1000_diff1": 0.050611, + "nauc_mrr_at_1_max": 0.055892, + "nauc_mrr_at_1_std": -0.079817, + "nauc_mrr_at_1_diff1": 0.133511, + "nauc_mrr_at_3_max": 0.049641, + "nauc_mrr_at_3_std": -0.07036, + "nauc_mrr_at_3_diff1": 0.071977, + "nauc_mrr_at_5_max": 0.090196, + "nauc_mrr_at_5_std": -0.078351, + "nauc_mrr_at_5_diff1": 0.098283, + "nauc_mrr_at_10_max": 0.10181, + "nauc_mrr_at_10_std": -0.062035, + "nauc_mrr_at_10_diff1": 0.113213, + "nauc_mrr_at_20_max": 0.102788, + "nauc_mrr_at_20_std": -0.050786, + "nauc_mrr_at_20_diff1": 0.11003, + "nauc_mrr_at_100_max": 0.096779, + "nauc_mrr_at_100_std": -0.054883, + "nauc_mrr_at_100_diff1": 0.107112, + "nauc_mrr_at_1000_max": 0.097107, + "nauc_mrr_at_1000_std": -0.055103, + "nauc_mrr_at_1000_diff1": 0.107333, + "main_score": 0.38514, + "hf_subset": "Bioinformatics", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.28409, + "ndcg_at_3": 0.35175, + "ndcg_at_5": 0.3689, + "ndcg_at_10": 0.41186, + "ndcg_at_20": 0.45847, + "ndcg_at_100": 0.50855, + "ndcg_at_1000": 0.53002, + "map_at_1": 0.15873, + "map_at_3": 0.27447, + "map_at_5": 0.29408, + "map_at_10": 0.32009, + "map_at_20": 0.33969, + "map_at_100": 0.35228, + "map_at_1000": 0.35389, + "recall_at_1": 0.15873, + "recall_at_3": 0.37119, + "recall_at_5": 0.43532, + "recall_at_10": 0.54648, + "recall_at_20": 0.68045, + "recall_at_100": 0.8553, + "recall_at_1000": 0.97538, + "precision_at_1": 0.28409, + "precision_at_3": 0.24242, + "precision_at_5": 0.175, + "precision_at_10": 0.12159, + "precision_at_20": 0.08125, + "precision_at_100": 0.02307, + "precision_at_1000": 0.0027, + "mrr_at_1": 0.284091, + "mrr_at_3": 0.407197, + "mrr_at_5": 0.425379, + "mrr_at_10": 0.43975, + "mrr_at_20": 0.446902, + "mrr_at_100": 0.449406, + "mrr_at_1000": 0.449764, + "nauc_ndcg_at_1_max": 0.301424, + "nauc_ndcg_at_1_std": 0.062995, + "nauc_ndcg_at_1_diff1": 0.142726, + "nauc_ndcg_at_3_max": 0.405107, + "nauc_ndcg_at_3_std": 0.037168, + "nauc_ndcg_at_3_diff1": 0.206709, + "nauc_ndcg_at_5_max": 0.388979, + "nauc_ndcg_at_5_std": 0.023669, + "nauc_ndcg_at_5_diff1": 0.203276, + "nauc_ndcg_at_10_max": 0.373418, + "nauc_ndcg_at_10_std": -0.020909, + "nauc_ndcg_at_10_diff1": 0.233715, + "nauc_ndcg_at_20_max": 0.392204, + "nauc_ndcg_at_20_std": -0.044907, + "nauc_ndcg_at_20_diff1": 0.23081, + "nauc_ndcg_at_100_max": 0.398658, + "nauc_ndcg_at_100_std": 0.031215, + "nauc_ndcg_at_100_diff1": 0.19596, + "nauc_ndcg_at_1000_max": 0.388323, + "nauc_ndcg_at_1000_std": 0.033469, + "nauc_ndcg_at_1000_diff1": 0.198108, + "nauc_map_at_1_max": 0.229588, + "nauc_map_at_1_std": -0.094147, + "nauc_map_at_1_diff1": 0.23436, + "nauc_map_at_3_max": 0.3675, + "nauc_map_at_3_std": -0.003834, + "nauc_map_at_3_diff1": 0.196405, + "nauc_map_at_5_max": 0.37462, + "nauc_map_at_5_std": 0.014003, + "nauc_map_at_5_diff1": 0.197137, + "nauc_map_at_10_max": 0.371318, + "nauc_map_at_10_std": -0.001346, + "nauc_map_at_10_diff1": 0.222414, + "nauc_map_at_20_max": 0.379232, + "nauc_map_at_20_std": -0.01002, + "nauc_map_at_20_diff1": 0.219516, + "nauc_map_at_100_max": 0.380067, + "nauc_map_at_100_std": 0.006559, + "nauc_map_at_100_diff1": 0.209784, + "nauc_map_at_1000_max": 0.379133, + "nauc_map_at_1000_std": 0.007367, + "nauc_map_at_1000_diff1": 0.209464, + "nauc_recall_at_1_max": 0.229588, + "nauc_recall_at_1_std": -0.094147, + "nauc_recall_at_1_diff1": 0.23436, + "nauc_recall_at_3_max": 0.360337, + "nauc_recall_at_3_std": -0.06125, + "nauc_recall_at_3_diff1": 0.196255, + "nauc_recall_at_5_max": 0.357678, + "nauc_recall_at_5_std": -0.04859, + "nauc_recall_at_5_diff1": 0.211063, + "nauc_recall_at_10_max": 0.310855, + "nauc_recall_at_10_std": -0.149219, + "nauc_recall_at_10_diff1": 0.280831, + "nauc_recall_at_20_max": 0.361607, + "nauc_recall_at_20_std": -0.271492, + "nauc_recall_at_20_diff1": 0.319553, + "nauc_recall_at_100_max": 0.43141, + "nauc_recall_at_100_std": -0.021843, + "nauc_recall_at_100_diff1": 0.211526, + "nauc_recall_at_1000_max": 0.424983, + "nauc_recall_at_1000_std": -0.438698, + "nauc_recall_at_1000_diff1": 0.613759, + "nauc_precision_at_1_max": 0.301424, + "nauc_precision_at_1_std": 0.062995, + "nauc_precision_at_1_diff1": 0.142726, + "nauc_precision_at_3_max": 0.474393, + "nauc_precision_at_3_std": 0.245623, + "nauc_precision_at_3_diff1": 0.128544, + "nauc_precision_at_5_max": 0.43493, + "nauc_precision_at_5_std": 0.275541, + "nauc_precision_at_5_diff1": 0.11376, + "nauc_precision_at_10_max": 0.308235, + "nauc_precision_at_10_std": 0.157853, + "nauc_precision_at_10_diff1": 0.168796, + "nauc_precision_at_20_max": 0.226204, + "nauc_precision_at_20_std": 0.075793, + "nauc_precision_at_20_diff1": 0.065361, + "nauc_precision_at_100_max": 0.117292, + "nauc_precision_at_100_std": 0.249307, + "nauc_precision_at_100_diff1": -0.06825, + "nauc_precision_at_1000_max": 0.015032, + "nauc_precision_at_1000_std": 0.247766, + "nauc_precision_at_1000_diff1": -0.093854, + "nauc_mrr_at_1_max": 0.301424, + "nauc_mrr_at_1_std": 0.062995, + "nauc_mrr_at_1_diff1": 0.142726, + "nauc_mrr_at_3_max": 0.359937, + "nauc_mrr_at_3_std": 0.063001, + "nauc_mrr_at_3_diff1": 0.133334, + "nauc_mrr_at_5_max": 0.363937, + "nauc_mrr_at_5_std": 0.06294, + "nauc_mrr_at_5_diff1": 0.159603, + "nauc_mrr_at_10_max": 0.357074, + "nauc_mrr_at_10_std": 0.05344, + "nauc_mrr_at_10_diff1": 0.162108, + "nauc_mrr_at_20_max": 0.359487, + "nauc_mrr_at_20_std": 0.054674, + "nauc_mrr_at_20_diff1": 0.160107, + "nauc_mrr_at_100_max": 0.358098, + "nauc_mrr_at_100_std": 0.056548, + "nauc_mrr_at_100_diff1": 0.158412, + "nauc_mrr_at_1000_max": 0.357926, + "nauc_mrr_at_1000_std": 0.056127, + "nauc_mrr_at_1000_diff1": 0.158647, + "main_score": 0.41186, + "hf_subset": "Medical-Sciences", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.08247, + "ndcg_at_3": 0.09123, + "ndcg_at_5": 0.10127, + "ndcg_at_10": 0.1089, + "ndcg_at_20": 0.1309, + "ndcg_at_100": 0.16972, + "ndcg_at_1000": 0.22228, + "map_at_1": 0.03876, + "map_at_3": 0.05809, + "map_at_5": 0.06783, + "map_at_10": 0.07275, + "map_at_20": 0.07981, + "map_at_100": 0.08608, + "map_at_1000": 0.08852, + "recall_at_1": 0.03876, + "recall_at_3": 0.08052, + "recall_at_5": 0.11627, + "recall_at_10": 0.14077, + "recall_at_20": 0.20728, + "recall_at_100": 0.36751, + "recall_at_1000": 0.68279, + "precision_at_1": 0.08247, + "precision_at_3": 0.07216, + "precision_at_5": 0.06186, + "precision_at_10": 0.03814, + "precision_at_20": 0.02784, + "precision_at_100": 0.0099, + "precision_at_1000": 0.00193, + "mrr_at_1": 0.082474, + "mrr_at_3": 0.127148, + "mrr_at_5": 0.141065, + "mrr_at_10": 0.14496, + "mrr_at_20": 0.150279, + "mrr_at_100": 0.155798, + "mrr_at_1000": 0.15708, + "nauc_ndcg_at_1_max": -0.142145, + "nauc_ndcg_at_1_std": 0.146494, + "nauc_ndcg_at_1_diff1": 0.070216, + "nauc_ndcg_at_3_max": 0.000654, + "nauc_ndcg_at_3_std": 0.11032, + "nauc_ndcg_at_3_diff1": 0.131828, + "nauc_ndcg_at_5_max": 0.027517, + "nauc_ndcg_at_5_std": 0.191383, + "nauc_ndcg_at_5_diff1": 0.123339, + "nauc_ndcg_at_10_max": -0.018341, + "nauc_ndcg_at_10_std": 0.163143, + "nauc_ndcg_at_10_diff1": 0.100113, + "nauc_ndcg_at_20_max": -0.00159, + "nauc_ndcg_at_20_std": 0.154023, + "nauc_ndcg_at_20_diff1": 0.072032, + "nauc_ndcg_at_100_max": 0.081874, + "nauc_ndcg_at_100_std": 0.208722, + "nauc_ndcg_at_100_diff1": 0.122083, + "nauc_ndcg_at_1000_max": 0.120701, + "nauc_ndcg_at_1000_std": 0.26608, + "nauc_ndcg_at_1000_diff1": 0.143698, + "nauc_map_at_1_max": -0.129549, + "nauc_map_at_1_std": 0.112351, + "nauc_map_at_1_diff1": 0.119285, + "nauc_map_at_3_max": -0.092297, + "nauc_map_at_3_std": 0.119433, + "nauc_map_at_3_diff1": 0.107956, + "nauc_map_at_5_max": -0.042407, + "nauc_map_at_5_std": 0.175458, + "nauc_map_at_5_diff1": 0.118765, + "nauc_map_at_10_max": -0.05742, + "nauc_map_at_10_std": 0.15792, + "nauc_map_at_10_diff1": 0.107219, + "nauc_map_at_20_max": -0.044305, + "nauc_map_at_20_std": 0.155894, + "nauc_map_at_20_diff1": 0.092304, + "nauc_map_at_100_max": -0.024898, + "nauc_map_at_100_std": 0.168981, + "nauc_map_at_100_diff1": 0.102763, + "nauc_map_at_1000_max": -0.01935, + "nauc_map_at_1000_std": 0.17319, + "nauc_map_at_1000_diff1": 0.104908, + "nauc_recall_at_1_max": -0.129549, + "nauc_recall_at_1_std": 0.112351, + "nauc_recall_at_1_diff1": 0.119285, + "nauc_recall_at_3_max": -0.092425, + "nauc_recall_at_3_std": 0.103547, + "nauc_recall_at_3_diff1": 0.065154, + "nauc_recall_at_5_max": 0.047428, + "nauc_recall_at_5_std": 0.22964, + "nauc_recall_at_5_diff1": 0.095622, + "nauc_recall_at_10_max": -0.030545, + "nauc_recall_at_10_std": 0.155265, + "nauc_recall_at_10_diff1": 0.071901, + "nauc_recall_at_20_max": 0.005369, + "nauc_recall_at_20_std": 0.128614, + "nauc_recall_at_20_diff1": 0.007126, + "nauc_recall_at_100_max": 0.193647, + "nauc_recall_at_100_std": 0.261701, + "nauc_recall_at_100_diff1": 0.133497, + "nauc_recall_at_1000_max": 0.425998, + "nauc_recall_at_1000_std": 0.584957, + "nauc_recall_at_1000_diff1": 0.221328, + "nauc_precision_at_1_max": -0.142145, + "nauc_precision_at_1_std": 0.146494, + "nauc_precision_at_1_diff1": 0.070216, + "nauc_precision_at_3_max": 0.075048, + "nauc_precision_at_3_std": 0.12908, + "nauc_precision_at_3_diff1": 0.153938, + "nauc_precision_at_5_max": 0.131357, + "nauc_precision_at_5_std": 0.239059, + "nauc_precision_at_5_diff1": 0.134873, + "nauc_precision_at_10_max": 0.068655, + "nauc_precision_at_10_std": 0.178975, + "nauc_precision_at_10_diff1": 0.111512, + "nauc_precision_at_20_max": 0.084851, + "nauc_precision_at_20_std": 0.147371, + "nauc_precision_at_20_diff1": 0.075606, + "nauc_precision_at_100_max": 0.275857, + "nauc_precision_at_100_std": 0.234436, + "nauc_precision_at_100_diff1": 0.166683, + "nauc_precision_at_1000_max": 0.257506, + "nauc_precision_at_1000_std": 0.274596, + "nauc_precision_at_1000_diff1": 0.208669, + "nauc_mrr_at_1_max": -0.142145, + "nauc_mrr_at_1_std": 0.146494, + "nauc_mrr_at_1_diff1": 0.070216, + "nauc_mrr_at_3_max": 0.026839, + "nauc_mrr_at_3_std": 0.121228, + "nauc_mrr_at_3_diff1": 0.119533, + "nauc_mrr_at_5_max": 0.050383, + "nauc_mrr_at_5_std": 0.16061, + "nauc_mrr_at_5_diff1": 0.119181, + "nauc_mrr_at_10_max": 0.03407, + "nauc_mrr_at_10_std": 0.146622, + "nauc_mrr_at_10_diff1": 0.114524, + "nauc_mrr_at_20_max": 0.028472, + "nauc_mrr_at_20_std": 0.140221, + "nauc_mrr_at_20_diff1": 0.105893, + "nauc_mrr_at_100_max": 0.034695, + "nauc_mrr_at_100_std": 0.144347, + "nauc_mrr_at_100_diff1": 0.113924, + "nauc_mrr_at_1000_max": 0.034347, + "nauc_mrr_at_1000_std": 0.144414, + "nauc_mrr_at_1000_diff1": 0.112986, + "main_score": 0.1089, + "hf_subset": "MedXpertQA-Exam", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.11017, + "ndcg_at_3": 0.09946, + "ndcg_at_5": 0.11762, + "ndcg_at_10": 0.13896, + "ndcg_at_20": 0.16793, + "ndcg_at_100": 0.22599, + "ndcg_at_1000": 0.27859, + "map_at_1": 0.03475, + "map_at_3": 0.05894, + "map_at_5": 0.07624, + "map_at_10": 0.08858, + "map_at_20": 0.09889, + "map_at_100": 0.10959, + "map_at_1000": 0.11246, + "recall_at_1": 0.03475, + "recall_at_3": 0.07204, + "recall_at_5": 0.12497, + "recall_at_10": 0.17359, + "recall_at_20": 0.24633, + "recall_at_100": 0.46018, + "recall_at_1000": 0.74463, + "precision_at_1": 0.11017, + "precision_at_3": 0.08475, + "precision_at_5": 0.08644, + "precision_at_10": 0.06441, + "precision_at_20": 0.04873, + "precision_at_100": 0.01822, + "precision_at_1000": 0.00308, + "mrr_at_1": 0.110169, + "mrr_at_3": 0.15113, + "mrr_at_5": 0.175282, + "mrr_at_10": 0.187991, + "mrr_at_20": 0.194495, + "mrr_at_100": 0.199888, + "mrr_at_1000": 0.200508, + "nauc_ndcg_at_1_max": 0.015576, + "nauc_ndcg_at_1_std": 0.070744, + "nauc_ndcg_at_1_diff1": -0.014755, + "nauc_ndcg_at_3_max": 0.145743, + "nauc_ndcg_at_3_std": 0.175449, + "nauc_ndcg_at_3_diff1": -0.050404, + "nauc_ndcg_at_5_max": 0.119283, + "nauc_ndcg_at_5_std": 0.162729, + "nauc_ndcg_at_5_diff1": -0.05003, + "nauc_ndcg_at_10_max": 0.163518, + "nauc_ndcg_at_10_std": 0.190503, + "nauc_ndcg_at_10_diff1": -0.021052, + "nauc_ndcg_at_20_max": 0.154547, + "nauc_ndcg_at_20_std": 0.179009, + "nauc_ndcg_at_20_diff1": 0.008345, + "nauc_ndcg_at_100_max": 0.178438, + "nauc_ndcg_at_100_std": 0.211812, + "nauc_ndcg_at_100_diff1": 0.003771, + "nauc_ndcg_at_1000_max": 0.161829, + "nauc_ndcg_at_1000_std": 0.220965, + "nauc_ndcg_at_1000_diff1": 0.011913, + "nauc_map_at_1_max": -0.029977, + "nauc_map_at_1_std": -0.033116, + "nauc_map_at_1_diff1": 0.008436, + "nauc_map_at_3_max": 0.103072, + "nauc_map_at_3_std": 0.078807, + "nauc_map_at_3_diff1": -0.040013, + "nauc_map_at_5_max": 0.094843, + "nauc_map_at_5_std": 0.109448, + "nauc_map_at_5_diff1": -0.051465, + "nauc_map_at_10_max": 0.146966, + "nauc_map_at_10_std": 0.150109, + "nauc_map_at_10_diff1": -0.04008, + "nauc_map_at_20_max": 0.145579, + "nauc_map_at_20_std": 0.154717, + "nauc_map_at_20_diff1": -0.023286, + "nauc_map_at_100_max": 0.155517, + "nauc_map_at_100_std": 0.172169, + "nauc_map_at_100_diff1": -0.019324, + "nauc_map_at_1000_max": 0.153464, + "nauc_map_at_1000_std": 0.173655, + "nauc_map_at_1000_diff1": -0.019502, + "nauc_recall_at_1_max": -0.029977, + "nauc_recall_at_1_std": -0.033116, + "nauc_recall_at_1_diff1": 0.008436, + "nauc_recall_at_3_max": 0.187736, + "nauc_recall_at_3_std": 0.14786, + "nauc_recall_at_3_diff1": -0.050505, + "nauc_recall_at_5_max": 0.082742, + "nauc_recall_at_5_std": 0.141822, + "nauc_recall_at_5_diff1": -0.078421, + "nauc_recall_at_10_max": 0.158967, + "nauc_recall_at_10_std": 0.188648, + "nauc_recall_at_10_diff1": -0.025367, + "nauc_recall_at_20_max": 0.138969, + "nauc_recall_at_20_std": 0.167571, + "nauc_recall_at_20_diff1": 0.038746, + "nauc_recall_at_100_max": 0.215084, + "nauc_recall_at_100_std": 0.233878, + "nauc_recall_at_100_diff1": 0.008172, + "nauc_recall_at_1000_max": 0.182973, + "nauc_recall_at_1000_std": 0.363597, + "nauc_recall_at_1000_diff1": 0.042348, + "nauc_precision_at_1_max": 0.015576, + "nauc_precision_at_1_std": 0.070744, + "nauc_precision_at_1_diff1": -0.014755, + "nauc_precision_at_3_max": 0.212811, + "nauc_precision_at_3_std": 0.241246, + "nauc_precision_at_3_diff1": -0.045188, + "nauc_precision_at_5_max": 0.216126, + "nauc_precision_at_5_std": 0.261194, + "nauc_precision_at_5_diff1": -0.033377, + "nauc_precision_at_10_max": 0.252413, + "nauc_precision_at_10_std": 0.286937, + "nauc_precision_at_10_diff1": 0.047284, + "nauc_precision_at_20_max": 0.199837, + "nauc_precision_at_20_std": 0.206736, + "nauc_precision_at_20_diff1": 0.072035, + "nauc_precision_at_100_max": 0.174561, + "nauc_precision_at_100_std": 0.21692, + "nauc_precision_at_100_diff1": 0.061625, + "nauc_precision_at_1000_max": 0.044942, + "nauc_precision_at_1000_std": 0.107214, + "nauc_precision_at_1000_diff1": 0.086151, + "nauc_mrr_at_1_max": 0.015576, + "nauc_mrr_at_1_std": 0.070744, + "nauc_mrr_at_1_diff1": -0.014755, + "nauc_mrr_at_3_max": 0.11755, + "nauc_mrr_at_3_std": 0.165306, + "nauc_mrr_at_3_diff1": -0.05462, + "nauc_mrr_at_5_max": 0.119124, + "nauc_mrr_at_5_std": 0.186208, + "nauc_mrr_at_5_diff1": -0.050346, + "nauc_mrr_at_10_max": 0.124417, + "nauc_mrr_at_10_std": 0.18558, + "nauc_mrr_at_10_diff1": -0.025358, + "nauc_mrr_at_20_max": 0.120475, + "nauc_mrr_at_20_std": 0.175631, + "nauc_mrr_at_20_diff1": -0.01844, + "nauc_mrr_at_100_max": 0.121037, + "nauc_mrr_at_100_std": 0.176835, + "nauc_mrr_at_100_diff1": -0.021223, + "nauc_mrr_at_1000_max": 0.121287, + "nauc_mrr_at_1000_std": 0.176785, + "nauc_mrr_at_1000_diff1": -0.021131, + "main_score": 0.13896, + "hf_subset": "MedQA-Diag", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.27333, + "ndcg_at_3": 0.25358, + "ndcg_at_5": 0.26388, + "ndcg_at_10": 0.28906, + "ndcg_at_20": 0.30277, + "ndcg_at_100": 0.33942, + "ndcg_at_1000": 0.37956, + "map_at_1": 0.16289, + "map_at_3": 0.20841, + "map_at_5": 0.22056, + "map_at_10": 0.23144, + "map_at_20": 0.23608, + "map_at_100": 0.2421, + "map_at_1000": 0.24397, + "recall_at_1": 0.16289, + "recall_at_3": 0.24733, + "recall_at_5": 0.286, + "recall_at_10": 0.35111, + "recall_at_20": 0.39689, + "recall_at_100": 0.56144, + "recall_at_1000": 0.81989, + "precision_at_1": 0.27333, + "precision_at_3": 0.15333, + "precision_at_5": 0.108, + "precision_at_10": 0.06733, + "precision_at_20": 0.03833, + "precision_at_100": 0.011, + "precision_at_1000": 0.00171, + "mrr_at_1": 0.273333, + "mrr_at_3": 0.324444, + "mrr_at_5": 0.335111, + "mrr_at_10": 0.34569, + "mrr_at_20": 0.347821, + "mrr_at_100": 0.352382, + "mrr_at_1000": 0.35311, + "nauc_ndcg_at_1_max": 0.387392, + "nauc_ndcg_at_1_std": -0.048066, + "nauc_ndcg_at_1_diff1": 0.585335, + "nauc_ndcg_at_3_max": 0.369542, + "nauc_ndcg_at_3_std": -0.050161, + "nauc_ndcg_at_3_diff1": 0.505564, + "nauc_ndcg_at_5_max": 0.362524, + "nauc_ndcg_at_5_std": -0.050045, + "nauc_ndcg_at_5_diff1": 0.489442, + "nauc_ndcg_at_10_max": 0.34942, + "nauc_ndcg_at_10_std": -0.046114, + "nauc_ndcg_at_10_diff1": 0.463814, + "nauc_ndcg_at_20_max": 0.346669, + "nauc_ndcg_at_20_std": -0.032346, + "nauc_ndcg_at_20_diff1": 0.463864, + "nauc_ndcg_at_100_max": 0.344803, + "nauc_ndcg_at_100_std": -0.015225, + "nauc_ndcg_at_100_diff1": 0.467044, + "nauc_ndcg_at_1000_max": 0.357831, + "nauc_ndcg_at_1000_std": -0.002834, + "nauc_ndcg_at_1000_diff1": 0.492944, + "nauc_map_at_1_max": 0.261559, + "nauc_map_at_1_std": -0.102647, + "nauc_map_at_1_diff1": 0.481265, + "nauc_map_at_3_max": 0.320685, + "nauc_map_at_3_std": -0.08958, + "nauc_map_at_3_diff1": 0.486913, + "nauc_map_at_5_max": 0.338221, + "nauc_map_at_5_std": -0.07626, + "nauc_map_at_5_diff1": 0.491351, + "nauc_map_at_10_max": 0.331385, + "nauc_map_at_10_std": -0.069981, + "nauc_map_at_10_diff1": 0.478906, + "nauc_map_at_20_max": 0.331933, + "nauc_map_at_20_std": -0.063185, + "nauc_map_at_20_diff1": 0.478533, + "nauc_map_at_100_max": 0.334535, + "nauc_map_at_100_std": -0.059541, + "nauc_map_at_100_diff1": 0.480299, + "nauc_map_at_1000_max": 0.335518, + "nauc_map_at_1000_std": -0.058916, + "nauc_map_at_1000_diff1": 0.481887, + "nauc_recall_at_1_max": 0.261559, + "nauc_recall_at_1_std": -0.102647, + "nauc_recall_at_1_diff1": 0.481265, + "nauc_recall_at_3_max": 0.322265, + "nauc_recall_at_3_std": -0.07274, + "nauc_recall_at_3_diff1": 0.443957, + "nauc_recall_at_5_max": 0.316351, + "nauc_recall_at_5_std": -0.0695, + "nauc_recall_at_5_diff1": 0.410795, + "nauc_recall_at_10_max": 0.275573, + "nauc_recall_at_10_std": -0.056971, + "nauc_recall_at_10_diff1": 0.3289, + "nauc_recall_at_20_max": 0.247042, + "nauc_recall_at_20_std": -0.027066, + "nauc_recall_at_20_diff1": 0.317818, + "nauc_recall_at_100_max": 0.148627, + "nauc_recall_at_100_std": 0.026803, + "nauc_recall_at_100_diff1": 0.245994, + "nauc_recall_at_1000_max": 0.14317, + "nauc_recall_at_1000_std": 0.221565, + "nauc_recall_at_1000_diff1": 0.382395, + "nauc_precision_at_1_max": 0.387392, + "nauc_precision_at_1_std": -0.048066, + "nauc_precision_at_1_diff1": 0.585335, + "nauc_precision_at_3_max": 0.513143, + "nauc_precision_at_3_std": 0.075953, + "nauc_precision_at_3_diff1": 0.532489, + "nauc_precision_at_5_max": 0.560302, + "nauc_precision_at_5_std": 0.122162, + "nauc_precision_at_5_diff1": 0.518323, + "nauc_precision_at_10_max": 0.496164, + "nauc_precision_at_10_std": 0.120526, + "nauc_precision_at_10_diff1": 0.43858, + "nauc_precision_at_20_max": 0.467253, + "nauc_precision_at_20_std": 0.170823, + "nauc_precision_at_20_diff1": 0.399427, + "nauc_precision_at_100_max": 0.434094, + "nauc_precision_at_100_std": 0.238585, + "nauc_precision_at_100_diff1": 0.335542, + "nauc_precision_at_1000_max": 0.350739, + "nauc_precision_at_1000_std": 0.211557, + "nauc_precision_at_1000_diff1": 0.28679, + "nauc_mrr_at_1_max": 0.387392, + "nauc_mrr_at_1_std": -0.048066, + "nauc_mrr_at_1_diff1": 0.585335, + "nauc_mrr_at_3_max": 0.407403, + "nauc_mrr_at_3_std": -0.000735, + "nauc_mrr_at_3_diff1": 0.541243, + "nauc_mrr_at_5_max": 0.403658, + "nauc_mrr_at_5_std": -0.005154, + "nauc_mrr_at_5_diff1": 0.535949, + "nauc_mrr_at_10_max": 0.399851, + "nauc_mrr_at_10_std": -0.012664, + "nauc_mrr_at_10_diff1": 0.529887, + "nauc_mrr_at_20_max": 0.39749, + "nauc_mrr_at_20_std": -0.012674, + "nauc_mrr_at_20_diff1": 0.531228, + "nauc_mrr_at_100_max": 0.396955, + "nauc_mrr_at_100_std": -0.012723, + "nauc_mrr_at_100_diff1": 0.533005, + "nauc_mrr_at_1000_max": 0.396987, + "nauc_mrr_at_1000_std": -0.012626, + "nauc_mrr_at_1000_diff1": 0.533261, + "main_score": 0.28906, + "hf_subset": "PMC-Treatment", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.17544, + "ndcg_at_3": 0.17553, + "ndcg_at_5": 0.21815, + "ndcg_at_10": 0.25177, + "ndcg_at_20": 0.27906, + "ndcg_at_100": 0.32602, + "ndcg_at_1000": 0.36664, + "map_at_1": 0.07675, + "map_at_3": 0.13353, + "map_at_5": 0.15889, + "map_at_10": 0.17475, + "map_at_20": 0.18424, + "map_at_100": 0.19388, + "map_at_1000": 0.19605, + "recall_at_1": 0.07675, + "recall_at_3": 0.18713, + "recall_at_5": 0.28143, + "recall_at_10": 0.36184, + "recall_at_20": 0.44518, + "recall_at_100": 0.64035, + "recall_at_1000": 0.89693, + "precision_at_1": 0.17544, + "precision_at_3": 0.12865, + "precision_at_5": 0.11228, + "precision_at_10": 0.07456, + "precision_at_20": 0.04781, + "precision_at_100": 0.01386, + "precision_at_1000": 0.00195, + "mrr_at_1": 0.175439, + "mrr_at_3": 0.238304, + "mrr_at_5": 0.268129, + "mrr_at_10": 0.28293, + "mrr_at_20": 0.287793, + "mrr_at_100": 0.292431, + "mrr_at_1000": 0.29343, + "nauc_ndcg_at_1_max": 0.192679, + "nauc_ndcg_at_1_std": -0.143442, + "nauc_ndcg_at_1_diff1": 0.485186, + "nauc_ndcg_at_3_max": 0.183927, + "nauc_ndcg_at_3_std": -0.203522, + "nauc_ndcg_at_3_diff1": 0.364367, + "nauc_ndcg_at_5_max": 0.132264, + "nauc_ndcg_at_5_std": -0.16053, + "nauc_ndcg_at_5_diff1": 0.361089, + "nauc_ndcg_at_10_max": 0.191491, + "nauc_ndcg_at_10_std": -0.120195, + "nauc_ndcg_at_10_diff1": 0.362018, + "nauc_ndcg_at_20_max": 0.171295, + "nauc_ndcg_at_20_std": -0.10842, + "nauc_ndcg_at_20_diff1": 0.361927, + "nauc_ndcg_at_100_max": 0.137165, + "nauc_ndcg_at_100_std": -0.098659, + "nauc_ndcg_at_100_diff1": 0.30711, + "nauc_ndcg_at_1000_max": 0.142179, + "nauc_ndcg_at_1000_std": -0.127195, + "nauc_ndcg_at_1000_diff1": 0.335205, + "nauc_map_at_1_max": 0.161272, + "nauc_map_at_1_std": -0.186252, + "nauc_map_at_1_diff1": 0.475831, + "nauc_map_at_3_max": 0.188653, + "nauc_map_at_3_std": -0.223277, + "nauc_map_at_3_diff1": 0.391311, + "nauc_map_at_5_max": 0.1539, + "nauc_map_at_5_std": -0.182399, + "nauc_map_at_5_diff1": 0.387444, + "nauc_map_at_10_max": 0.188678, + "nauc_map_at_10_std": -0.159024, + "nauc_map_at_10_diff1": 0.391123, + "nauc_map_at_20_max": 0.186538, + "nauc_map_at_20_std": -0.153748, + "nauc_map_at_20_diff1": 0.394083, + "nauc_map_at_100_max": 0.17694, + "nauc_map_at_100_std": -0.150282, + "nauc_map_at_100_diff1": 0.379883, + "nauc_map_at_1000_max": 0.176322, + "nauc_map_at_1000_std": -0.152117, + "nauc_map_at_1000_diff1": 0.381339, + "nauc_recall_at_1_max": 0.161272, + "nauc_recall_at_1_std": -0.186252, + "nauc_recall_at_1_diff1": 0.475831, + "nauc_recall_at_3_max": 0.155311, + "nauc_recall_at_3_std": -0.21222, + "nauc_recall_at_3_diff1": 0.276153, + "nauc_recall_at_5_max": 0.069837, + "nauc_recall_at_5_std": -0.105018, + "nauc_recall_at_5_diff1": 0.254619, + "nauc_recall_at_10_max": 0.166969, + "nauc_recall_at_10_std": -0.023947, + "nauc_recall_at_10_diff1": 0.232911, + "nauc_recall_at_20_max": 0.111585, + "nauc_recall_at_20_std": 0.003894, + "nauc_recall_at_20_diff1": 0.224384, + "nauc_recall_at_100_max": -0.001888, + "nauc_recall_at_100_std": 0.033256, + "nauc_recall_at_100_diff1": 0.035652, + "nauc_recall_at_1000_max": -0.089359, + "nauc_recall_at_1000_std": -0.093469, + "nauc_recall_at_1000_diff1": 0.085488, + "nauc_precision_at_1_max": 0.192679, + "nauc_precision_at_1_std": -0.143442, + "nauc_precision_at_1_diff1": 0.485186, + "nauc_precision_at_3_max": 0.187371, + "nauc_precision_at_3_std": -0.206761, + "nauc_precision_at_3_diff1": 0.308432, + "nauc_precision_at_5_max": 0.114291, + "nauc_precision_at_5_std": -0.151725, + "nauc_precision_at_5_diff1": 0.332688, + "nauc_precision_at_10_max": 0.217673, + "nauc_precision_at_10_std": -0.041766, + "nauc_precision_at_10_diff1": 0.271684, + "nauc_precision_at_20_max": 0.13376, + "nauc_precision_at_20_std": -0.001623, + "nauc_precision_at_20_diff1": 0.207995, + "nauc_precision_at_100_max": 0.040502, + "nauc_precision_at_100_std": 0.028974, + "nauc_precision_at_100_diff1": 0.043406, + "nauc_precision_at_1000_max": 0.012913, + "nauc_precision_at_1000_std": -0.039411, + "nauc_precision_at_1000_diff1": 0.022594, + "nauc_mrr_at_1_max": 0.192679, + "nauc_mrr_at_1_std": -0.143442, + "nauc_mrr_at_1_diff1": 0.485186, + "nauc_mrr_at_3_max": 0.180322, + "nauc_mrr_at_3_std": -0.166682, + "nauc_mrr_at_3_diff1": 0.405085, + "nauc_mrr_at_5_max": 0.153317, + "nauc_mrr_at_5_std": -0.156486, + "nauc_mrr_at_5_diff1": 0.400494, + "nauc_mrr_at_10_max": 0.174646, + "nauc_mrr_at_10_std": -0.145678, + "nauc_mrr_at_10_diff1": 0.402732, + "nauc_mrr_at_20_max": 0.165671, + "nauc_mrr_at_20_std": -0.142622, + "nauc_mrr_at_20_diff1": 0.402075, + "nauc_mrr_at_100_max": 0.1631, + "nauc_mrr_at_100_std": -0.141516, + "nauc_mrr_at_100_diff1": 0.39771, + "nauc_mrr_at_1000_max": 0.163951, + "nauc_mrr_at_1000_std": -0.141934, + "nauc_mrr_at_1000_diff1": 0.398326, + "main_score": 0.25177, + "hf_subset": "PMC-Clinical", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.18605, + "ndcg_at_3": 0.14722, + "ndcg_at_5": 0.16427, + "ndcg_at_10": 0.21746, + "ndcg_at_20": 0.26474, + "ndcg_at_100": 0.35013, + "ndcg_at_1000": 0.3911, + "map_at_1": 0.05891, + "map_at_3": 0.08833, + "map_at_5": 0.10708, + "map_at_10": 0.1345, + "map_at_20": 0.15319, + "map_at_100": 0.17164, + "map_at_1000": 0.17476, + "recall_at_1": 0.05891, + "recall_at_3": 0.11408, + "recall_at_5": 0.17183, + "recall_at_10": 0.29186, + "recall_at_20": 0.41344, + "recall_at_100": 0.73411, + "recall_at_1000": 0.95168, + "precision_at_1": 0.18605, + "precision_at_3": 0.11628, + "precision_at_5": 0.11163, + "precision_at_10": 0.1, + "precision_at_20": 0.07519, + "precision_at_100": 0.0262, + "precision_at_1000": 0.00339, + "mrr_at_1": 0.186047, + "mrr_at_3": 0.236434, + "mrr_at_5": 0.263178, + "mrr_at_10": 0.284859, + "mrr_at_20": 0.292002, + "mrr_at_100": 0.297868, + "mrr_at_1000": 0.298225, + "nauc_ndcg_at_1_max": 0.062293, + "nauc_ndcg_at_1_std": 0.18563, + "nauc_ndcg_at_1_diff1": 0.171393, + "nauc_ndcg_at_3_max": 0.049926, + "nauc_ndcg_at_3_std": 0.080108, + "nauc_ndcg_at_3_diff1": 0.102774, + "nauc_ndcg_at_5_max": 0.075792, + "nauc_ndcg_at_5_std": 0.067447, + "nauc_ndcg_at_5_diff1": 0.105374, + "nauc_ndcg_at_10_max": 0.147093, + "nauc_ndcg_at_10_std": 0.072071, + "nauc_ndcg_at_10_diff1": 0.104567, + "nauc_ndcg_at_20_max": 0.127955, + "nauc_ndcg_at_20_std": 0.097273, + "nauc_ndcg_at_20_diff1": 0.085686, + "nauc_ndcg_at_100_max": 0.125421, + "nauc_ndcg_at_100_std": 0.195633, + "nauc_ndcg_at_100_diff1": 0.052223, + "nauc_ndcg_at_1000_max": 0.120989, + "nauc_ndcg_at_1000_std": 0.190344, + "nauc_ndcg_at_1000_diff1": 0.048357, + "nauc_map_at_1_max": -0.039609, + "nauc_map_at_1_std": 0.079092, + "nauc_map_at_1_diff1": 0.139206, + "nauc_map_at_3_max": -0.014951, + "nauc_map_at_3_std": 0.051213, + "nauc_map_at_3_diff1": 0.092342, + "nauc_map_at_5_max": 0.029303, + "nauc_map_at_5_std": 0.059085, + "nauc_map_at_5_diff1": 0.106769, + "nauc_map_at_10_max": 0.105929, + "nauc_map_at_10_std": 0.061869, + "nauc_map_at_10_diff1": 0.113755, + "nauc_map_at_20_max": 0.096688, + "nauc_map_at_20_std": 0.071486, + "nauc_map_at_20_diff1": 0.101671, + "nauc_map_at_100_max": 0.094402, + "nauc_map_at_100_std": 0.100782, + "nauc_map_at_100_diff1": 0.092577, + "nauc_map_at_1000_max": 0.094584, + "nauc_map_at_1000_std": 0.100682, + "nauc_map_at_1000_diff1": 0.092986, + "nauc_recall_at_1_max": -0.039609, + "nauc_recall_at_1_std": 0.079092, + "nauc_recall_at_1_diff1": 0.139206, + "nauc_recall_at_3_max": -0.027987, + "nauc_recall_at_3_std": -0.013619, + "nauc_recall_at_3_diff1": 0.018249, + "nauc_recall_at_5_max": 0.075436, + "nauc_recall_at_5_std": -0.011984, + "nauc_recall_at_5_diff1": 0.070175, + "nauc_recall_at_10_max": 0.161608, + "nauc_recall_at_10_std": -0.000575, + "nauc_recall_at_10_diff1": 0.071168, + "nauc_recall_at_20_max": 0.122271, + "nauc_recall_at_20_std": 0.041256, + "nauc_recall_at_20_diff1": 0.053391, + "nauc_recall_at_100_max": 0.08823, + "nauc_recall_at_100_std": 0.306247, + "nauc_recall_at_100_diff1": -0.078128, + "nauc_recall_at_1000_max": -0.072846, + "nauc_recall_at_1000_std": 0.750253, + "nauc_recall_at_1000_diff1": -0.561028, + "nauc_precision_at_1_max": 0.062293, + "nauc_precision_at_1_std": 0.18563, + "nauc_precision_at_1_diff1": 0.171393, + "nauc_precision_at_3_max": 0.121676, + "nauc_precision_at_3_std": 0.13311, + "nauc_precision_at_3_diff1": 0.105719, + "nauc_precision_at_5_max": 0.179754, + "nauc_precision_at_5_std": 0.134708, + "nauc_precision_at_5_diff1": 0.105899, + "nauc_precision_at_10_max": 0.27653, + "nauc_precision_at_10_std": 0.130796, + "nauc_precision_at_10_diff1": 0.074191, + "nauc_precision_at_20_max": 0.182183, + "nauc_precision_at_20_std": 0.167255, + "nauc_precision_at_20_diff1": 0.012247, + "nauc_precision_at_100_max": 0.174375, + "nauc_precision_at_100_std": 0.353781, + "nauc_precision_at_100_diff1": -0.057792, + "nauc_precision_at_1000_max": 0.172581, + "nauc_precision_at_1000_std": 0.324486, + "nauc_precision_at_1000_diff1": -0.084553, + "nauc_mrr_at_1_max": 0.062293, + "nauc_mrr_at_1_std": 0.18563, + "nauc_mrr_at_1_diff1": 0.171393, + "nauc_mrr_at_3_max": 0.098479, + "nauc_mrr_at_3_std": 0.114438, + "nauc_mrr_at_3_diff1": 0.131386, + "nauc_mrr_at_5_max": 0.110579, + "nauc_mrr_at_5_std": 0.111879, + "nauc_mrr_at_5_diff1": 0.125321, + "nauc_mrr_at_10_max": 0.111925, + "nauc_mrr_at_10_std": 0.124273, + "nauc_mrr_at_10_diff1": 0.118633, + "nauc_mrr_at_20_max": 0.110857, + "nauc_mrr_at_20_std": 0.13301, + "nauc_mrr_at_20_diff1": 0.115528, + "nauc_mrr_at_100_max": 0.107675, + "nauc_mrr_at_100_std": 0.132788, + "nauc_mrr_at_100_diff1": 0.114836, + "nauc_mrr_at_1000_max": 0.106961, + "nauc_mrr_at_1000_std": 0.132197, + "nauc_mrr_at_1000_diff1": 0.114938, + "main_score": 0.21746, + "hf_subset": "IIYi-Clinical", + "languages": [ + "eng-Latn" + ] + } + ] + }, + "evaluation_time": 3346.673637866974, + "kg_co2_emissions": null +} \ No newline at end of file diff --git a/results/intfloat__multilingual-e5-base/d13f1b27baf31030b7fd040960d60d909913633f/R2MEDRetrieval.json b/results/intfloat__multilingual-e5-base/d13f1b27baf31030b7fd040960d60d909913633f/R2MEDRetrieval.json new file mode 100644 index 0000000000..7470da6059 --- /dev/null +++ b/results/intfloat__multilingual-e5-base/d13f1b27baf31030b7fd040960d60d909913633f/R2MEDRetrieval.json @@ -0,0 +1,1187 @@ +{ + "dataset_revision": "1.0", + "task_name": "R2MEDRetrieval", + "mteb_version": "1.38.20", + "scores": { + "test": [ + { + "ndcg_at_1": 0.04854, + "ndcg_at_3": 0.02506, + "ndcg_at_5": 0.0224, + "ndcg_at_10": 0.02728, + "ndcg_at_20": 0.02991, + "ndcg_at_100": 0.04232, + "ndcg_at_1000": 0.06983, + "map_at_1": 0.01335, + "map_at_3": 0.01389, + "map_at_5": 0.01389, + "map_at_10": 0.01689, + "map_at_20": 0.01729, + "map_at_100": 0.0187, + "map_at_1000": 0.01944, + "recall_at_1": 0.01335, + "recall_at_3": 0.01497, + "recall_at_5": 0.01497, + "recall_at_10": 0.02751, + "recall_at_20": 0.03456, + "recall_at_100": 0.07933, + "recall_at_1000": 0.24305, + "precision_at_1": 0.04854, + "precision_at_3": 0.01942, + "precision_at_5": 0.01165, + "precision_at_10": 0.00971, + "precision_at_20": 0.00631, + "precision_at_100": 0.0032, + "precision_at_1000": 0.00088, + "mrr_at_1": 0.048544, + "mrr_at_3": 0.05178, + "mrr_at_5": 0.05178, + "mrr_at_10": 0.053167, + "mrr_at_20": 0.054871, + "mrr_at_100": 0.057533, + "mrr_at_1000": 0.058378, + "nauc_ndcg_at_1_max": 0.509755, + "nauc_ndcg_at_1_std": 0.097359, + "nauc_ndcg_at_1_diff1": 0.648144, + "nauc_ndcg_at_3_max": 0.522827, + "nauc_ndcg_at_3_std": 0.117924, + "nauc_ndcg_at_3_diff1": 0.598318, + "nauc_ndcg_at_5_max": 0.526666, + "nauc_ndcg_at_5_std": 0.128508, + "nauc_ndcg_at_5_diff1": 0.575976, + "nauc_ndcg_at_10_max": 0.54594, + "nauc_ndcg_at_10_std": 0.073683, + "nauc_ndcg_at_10_diff1": 0.571706, + "nauc_ndcg_at_20_max": 0.476177, + "nauc_ndcg_at_20_std": 0.061548, + "nauc_ndcg_at_20_diff1": 0.492164, + "nauc_ndcg_at_100_max": 0.321519, + "nauc_ndcg_at_100_std": -0.008093, + "nauc_ndcg_at_100_diff1": 0.361681, + "nauc_ndcg_at_1000_max": 0.223687, + "nauc_ndcg_at_1000_std": 0.025838, + "nauc_ndcg_at_1000_diff1": 0.248069, + "nauc_map_at_1_max": 0.542119, + "nauc_map_at_1_std": 0.153754, + "nauc_map_at_1_diff1": 0.573508, + "nauc_map_at_3_max": 0.546446, + "nauc_map_at_3_std": 0.160349, + "nauc_map_at_3_diff1": 0.555122, + "nauc_map_at_5_max": 0.546446, + "nauc_map_at_5_std": 0.160349, + "nauc_map_at_5_diff1": 0.555122, + "nauc_map_at_10_max": 0.560948, + "nauc_map_at_10_std": 0.103474, + "nauc_map_at_10_diff1": 0.57507, + "nauc_map_at_20_max": 0.54196, + "nauc_map_at_20_std": 0.099496, + "nauc_map_at_20_diff1": 0.55402, + "nauc_map_at_100_max": 0.501221, + "nauc_map_at_100_std": 0.082254, + "nauc_map_at_100_diff1": 0.518839, + "nauc_map_at_1000_max": 0.489187, + "nauc_map_at_1000_std": 0.083215, + "nauc_map_at_1000_diff1": 0.505642, + "nauc_recall_at_1_max": 0.542119, + "nauc_recall_at_1_std": 0.153754, + "nauc_recall_at_1_diff1": 0.573508, + "nauc_recall_at_3_max": 0.554165, + "nauc_recall_at_3_std": 0.172113, + "nauc_recall_at_3_diff1": 0.522324, + "nauc_recall_at_5_max": 0.554165, + "nauc_recall_at_5_std": 0.172113, + "nauc_recall_at_5_diff1": 0.522324, + "nauc_recall_at_10_max": 0.557581, + "nauc_recall_at_10_std": -0.000317, + "nauc_recall_at_10_diff1": 0.540514, + "nauc_recall_at_20_max": 0.391576, + "nauc_recall_at_20_std": -0.018856, + "nauc_recall_at_20_diff1": 0.365878, + "nauc_recall_at_100_max": 0.122029, + "nauc_recall_at_100_std": -0.12947, + "nauc_recall_at_100_diff1": 0.17085, + "nauc_recall_at_1000_max": -0.004431, + "nauc_recall_at_1000_std": -0.000626, + "nauc_recall_at_1000_diff1": 0.003825, + "nauc_precision_at_1_max": 0.509755, + "nauc_precision_at_1_std": 0.097359, + "nauc_precision_at_1_diff1": 0.648144, + "nauc_precision_at_3_max": 0.533719, + "nauc_precision_at_3_std": 0.135062, + "nauc_precision_at_3_diff1": 0.556796, + "nauc_precision_at_5_max": 0.533719, + "nauc_precision_at_5_std": 0.135062, + "nauc_precision_at_5_diff1": 0.556796, + "nauc_precision_at_10_max": 0.527949, + "nauc_precision_at_10_std": -0.009277, + "nauc_precision_at_10_diff1": 0.609437, + "nauc_precision_at_20_max": 0.350252, + "nauc_precision_at_20_std": -0.016095, + "nauc_precision_at_20_diff1": 0.384704, + "nauc_precision_at_100_max": 0.051611, + "nauc_precision_at_100_std": -0.125484, + "nauc_precision_at_100_diff1": 0.137531, + "nauc_precision_at_1000_max": -0.037835, + "nauc_precision_at_1000_std": -0.03536, + "nauc_precision_at_1000_diff1": 0.030578, + "nauc_mrr_at_1_max": 0.509755, + "nauc_mrr_at_1_std": 0.097359, + "nauc_mrr_at_1_diff1": 0.648144, + "nauc_mrr_at_3_max": 0.518742, + "nauc_mrr_at_3_std": 0.111498, + "nauc_mrr_at_3_diff1": 0.613889, + "nauc_mrr_at_5_max": 0.518742, + "nauc_mrr_at_5_std": 0.111498, + "nauc_mrr_at_5_diff1": 0.613889, + "nauc_mrr_at_10_max": 0.513651, + "nauc_mrr_at_10_std": 0.09782, + "nauc_mrr_at_10_diff1": 0.600484, + "nauc_mrr_at_20_max": 0.490353, + "nauc_mrr_at_20_std": 0.094203, + "nauc_mrr_at_20_diff1": 0.570341, + "nauc_mrr_at_100_max": 0.4661, + "nauc_mrr_at_100_std": 0.086197, + "nauc_mrr_at_100_diff1": 0.544886, + "nauc_mrr_at_1000_max": 0.465456, + "nauc_mrr_at_1000_std": 0.088857, + "nauc_mrr_at_1000_diff1": 0.542528, + "main_score": 0.02728, + "hf_subset": "Biology", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.14286, + "ndcg_at_3": 0.13627, + "ndcg_at_5": 0.15371, + "ndcg_at_10": 0.16918, + "ndcg_at_20": 0.20116, + "ndcg_at_100": 0.25892, + "ndcg_at_1000": 0.31014, + "map_at_1": 0.05076, + "map_at_3": 0.08846, + "map_at_5": 0.10544, + "map_at_10": 0.11425, + "map_at_20": 0.12568, + "map_at_100": 0.1351, + "map_at_1000": 0.13804, + "recall_at_1": 0.05076, + "recall_at_3": 0.1395, + "recall_at_5": 0.19222, + "recall_at_10": 0.22525, + "recall_at_20": 0.32548, + "recall_at_100": 0.57072, + "recall_at_1000": 0.85606, + "precision_at_1": 0.14286, + "precision_at_3": 0.1039, + "precision_at_5": 0.09091, + "precision_at_10": 0.06104, + "precision_at_20": 0.04286, + "precision_at_100": 0.01558, + "precision_at_1000": 0.0026, + "mrr_at_1": 0.142857, + "mrr_at_3": 0.186147, + "mrr_at_5": 0.207576, + "mrr_at_10": 0.216502, + "mrr_at_20": 0.222944, + "mrr_at_100": 0.2276, + "mrr_at_1000": 0.228479, + "nauc_ndcg_at_1_max": 0.205273, + "nauc_ndcg_at_1_std": -0.016577, + "nauc_ndcg_at_1_diff1": 0.062725, + "nauc_ndcg_at_3_max": 0.203459, + "nauc_ndcg_at_3_std": 0.170044, + "nauc_ndcg_at_3_diff1": 0.054833, + "nauc_ndcg_at_5_max": 0.247564, + "nauc_ndcg_at_5_std": 0.208729, + "nauc_ndcg_at_5_diff1": 0.130244, + "nauc_ndcg_at_10_max": 0.257304, + "nauc_ndcg_at_10_std": 0.205152, + "nauc_ndcg_at_10_diff1": 0.124073, + "nauc_ndcg_at_20_max": 0.198009, + "nauc_ndcg_at_20_std": 0.186852, + "nauc_ndcg_at_20_diff1": 0.07105, + "nauc_ndcg_at_100_max": 0.208723, + "nauc_ndcg_at_100_std": 0.193601, + "nauc_ndcg_at_100_diff1": 0.017354, + "nauc_ndcg_at_1000_max": 0.195032, + "nauc_ndcg_at_1000_std": 0.174418, + "nauc_ndcg_at_1000_diff1": 0.027547, + "nauc_map_at_1_max": 0.166163, + "nauc_map_at_1_std": -0.111818, + "nauc_map_at_1_diff1": 0.243215, + "nauc_map_at_3_max": 0.206101, + "nauc_map_at_3_std": 0.130036, + "nauc_map_at_3_diff1": 0.138992, + "nauc_map_at_5_max": 0.23477, + "nauc_map_at_5_std": 0.176436, + "nauc_map_at_5_diff1": 0.153331, + "nauc_map_at_10_max": 0.255526, + "nauc_map_at_10_std": 0.18532, + "nauc_map_at_10_diff1": 0.156879, + "nauc_map_at_20_max": 0.233254, + "nauc_map_at_20_std": 0.184035, + "nauc_map_at_20_diff1": 0.133638, + "nauc_map_at_100_max": 0.240804, + "nauc_map_at_100_std": 0.187878, + "nauc_map_at_100_diff1": 0.12182, + "nauc_map_at_1000_max": 0.236867, + "nauc_map_at_1000_std": 0.18604, + "nauc_map_at_1000_diff1": 0.118987, + "nauc_recall_at_1_max": 0.166163, + "nauc_recall_at_1_std": -0.111818, + "nauc_recall_at_1_diff1": 0.243215, + "nauc_recall_at_3_max": 0.222606, + "nauc_recall_at_3_std": 0.278554, + "nauc_recall_at_3_diff1": 0.109657, + "nauc_recall_at_5_max": 0.262925, + "nauc_recall_at_5_std": 0.316712, + "nauc_recall_at_5_diff1": 0.153735, + "nauc_recall_at_10_max": 0.269611, + "nauc_recall_at_10_std": 0.305149, + "nauc_recall_at_10_diff1": 0.133042, + "nauc_recall_at_20_max": 0.119698, + "nauc_recall_at_20_std": 0.232318, + "nauc_recall_at_20_diff1": 0.005846, + "nauc_recall_at_100_max": 0.140704, + "nauc_recall_at_100_std": 0.257386, + "nauc_recall_at_100_diff1": -0.119309, + "nauc_recall_at_1000_max": 0.127493, + "nauc_recall_at_1000_std": 0.419292, + "nauc_recall_at_1000_diff1": -0.155802, + "nauc_precision_at_1_max": 0.205273, + "nauc_precision_at_1_std": -0.016577, + "nauc_precision_at_1_diff1": 0.062725, + "nauc_precision_at_3_max": 0.169193, + "nauc_precision_at_3_std": 0.222119, + "nauc_precision_at_3_diff1": -0.040034, + "nauc_precision_at_5_max": 0.265854, + "nauc_precision_at_5_std": 0.284192, + "nauc_precision_at_5_diff1": 0.075676, + "nauc_precision_at_10_max": 0.23523, + "nauc_precision_at_10_std": 0.221716, + "nauc_precision_at_10_diff1": 0.021541, + "nauc_precision_at_20_max": 0.097813, + "nauc_precision_at_20_std": 0.157983, + "nauc_precision_at_20_diff1": -0.090409, + "nauc_precision_at_100_max": 0.071978, + "nauc_precision_at_100_std": 0.086006, + "nauc_precision_at_100_diff1": -0.206476, + "nauc_precision_at_1000_max": -0.052206, + "nauc_precision_at_1000_std": -0.11412, + "nauc_precision_at_1000_diff1": -0.140309, + "nauc_mrr_at_1_max": 0.205273, + "nauc_mrr_at_1_std": -0.016577, + "nauc_mrr_at_1_diff1": 0.062725, + "nauc_mrr_at_3_max": 0.185602, + "nauc_mrr_at_3_std": 0.064591, + "nauc_mrr_at_3_diff1": 0.028222, + "nauc_mrr_at_5_max": 0.220344, + "nauc_mrr_at_5_std": 0.085455, + "nauc_mrr_at_5_diff1": 0.058028, + "nauc_mrr_at_10_max": 0.19754, + "nauc_mrr_at_10_std": 0.063464, + "nauc_mrr_at_10_diff1": 0.035426, + "nauc_mrr_at_20_max": 0.187394, + "nauc_mrr_at_20_std": 0.058668, + "nauc_mrr_at_20_diff1": 0.028256, + "nauc_mrr_at_100_max": 0.188418, + "nauc_mrr_at_100_std": 0.062027, + "nauc_mrr_at_100_diff1": 0.025216, + "nauc_mrr_at_1000_max": 0.188815, + "nauc_mrr_at_1000_std": 0.062264, + "nauc_mrr_at_1000_diff1": 0.026481, + "main_score": 0.16918, + "hf_subset": "Bioinformatics", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.13636, + "ndcg_at_3": 0.17146, + "ndcg_at_5": 0.18667, + "ndcg_at_10": 0.20912, + "ndcg_at_20": 0.24095, + "ndcg_at_100": 0.28134, + "ndcg_at_1000": 0.32831, + "map_at_1": 0.0664, + "map_at_3": 0.12594, + "map_at_5": 0.13918, + "map_at_10": 0.15054, + "map_at_20": 0.16131, + "map_at_100": 0.16839, + "map_at_1000": 0.17069, + "recall_at_1": 0.0664, + "recall_at_3": 0.18071, + "recall_at_5": 0.23033, + "recall_at_10": 0.2855, + "recall_at_20": 0.39271, + "recall_at_100": 0.5567, + "recall_at_1000": 0.84041, + "precision_at_1": 0.13636, + "precision_at_3": 0.125, + "precision_at_5": 0.09773, + "precision_at_10": 0.06705, + "precision_at_20": 0.04375, + "precision_at_100": 0.01352, + "precision_at_1000": 0.00218, + "mrr_at_1": 0.136364, + "mrr_at_3": 0.206439, + "mrr_at_5": 0.227462, + "mrr_at_10": 0.237004, + "mrr_at_20": 0.244693, + "mrr_at_100": 0.248329, + "mrr_at_1000": 0.249296, + "nauc_ndcg_at_1_max": 0.215639, + "nauc_ndcg_at_1_std": -0.064352, + "nauc_ndcg_at_1_diff1": 0.258047, + "nauc_ndcg_at_3_max": 0.241838, + "nauc_ndcg_at_3_std": 0.044856, + "nauc_ndcg_at_3_diff1": 0.094347, + "nauc_ndcg_at_5_max": 0.283902, + "nauc_ndcg_at_5_std": 0.0909, + "nauc_ndcg_at_5_diff1": 0.088876, + "nauc_ndcg_at_10_max": 0.299878, + "nauc_ndcg_at_10_std": 0.144666, + "nauc_ndcg_at_10_diff1": 0.093817, + "nauc_ndcg_at_20_max": 0.263386, + "nauc_ndcg_at_20_std": 0.123194, + "nauc_ndcg_at_20_diff1": 0.071094, + "nauc_ndcg_at_100_max": 0.300361, + "nauc_ndcg_at_100_std": 0.169804, + "nauc_ndcg_at_100_diff1": 0.092397, + "nauc_ndcg_at_1000_max": 0.285118, + "nauc_ndcg_at_1000_std": 0.166667, + "nauc_ndcg_at_1000_diff1": 0.085065, + "nauc_map_at_1_max": 0.091756, + "nauc_map_at_1_std": 0.006331, + "nauc_map_at_1_diff1": 0.167864, + "nauc_map_at_3_max": 0.219585, + "nauc_map_at_3_std": 0.044126, + "nauc_map_at_3_diff1": 0.100742, + "nauc_map_at_5_max": 0.245482, + "nauc_map_at_5_std": 0.066052, + "nauc_map_at_5_diff1": 0.107915, + "nauc_map_at_10_max": 0.266365, + "nauc_map_at_10_std": 0.098744, + "nauc_map_at_10_diff1": 0.106814, + "nauc_map_at_20_max": 0.260243, + "nauc_map_at_20_std": 0.092578, + "nauc_map_at_20_diff1": 0.096736, + "nauc_map_at_100_max": 0.271929, + "nauc_map_at_100_std": 0.102465, + "nauc_map_at_100_diff1": 0.099141, + "nauc_map_at_1000_max": 0.272409, + "nauc_map_at_1000_std": 0.103914, + "nauc_map_at_1000_diff1": 0.099917, + "nauc_recall_at_1_max": 0.091756, + "nauc_recall_at_1_std": 0.006331, + "nauc_recall_at_1_diff1": 0.167864, + "nauc_recall_at_3_max": 0.203598, + "nauc_recall_at_3_std": 0.07123, + "nauc_recall_at_3_diff1": 0.011658, + "nauc_recall_at_5_max": 0.249917, + "nauc_recall_at_5_std": 0.127859, + "nauc_recall_at_5_diff1": 0.037007, + "nauc_recall_at_10_max": 0.262352, + "nauc_recall_at_10_std": 0.222944, + "nauc_recall_at_10_diff1": 0.027866, + "nauc_recall_at_20_max": 0.141189, + "nauc_recall_at_20_std": 0.132965, + "nauc_recall_at_20_diff1": -0.034761, + "nauc_recall_at_100_max": 0.212613, + "nauc_recall_at_100_std": 0.285657, + "nauc_recall_at_100_diff1": 0.080999, + "nauc_recall_at_1000_max": -0.059741, + "nauc_recall_at_1000_std": 0.279481, + "nauc_recall_at_1000_diff1": -0.01748, + "nauc_precision_at_1_max": 0.215639, + "nauc_precision_at_1_std": -0.064352, + "nauc_precision_at_1_diff1": 0.258047, + "nauc_precision_at_3_max": 0.387231, + "nauc_precision_at_3_std": 0.110254, + "nauc_precision_at_3_diff1": 0.062223, + "nauc_precision_at_5_max": 0.494852, + "nauc_precision_at_5_std": 0.173448, + "nauc_precision_at_5_diff1": 0.065863, + "nauc_precision_at_10_max": 0.504468, + "nauc_precision_at_10_std": 0.278012, + "nauc_precision_at_10_diff1": 0.111745, + "nauc_precision_at_20_max": 0.411159, + "nauc_precision_at_20_std": 0.241378, + "nauc_precision_at_20_diff1": 0.081903, + "nauc_precision_at_100_max": 0.447148, + "nauc_precision_at_100_std": 0.289425, + "nauc_precision_at_100_diff1": 0.065913, + "nauc_precision_at_1000_max": 0.249029, + "nauc_precision_at_1000_std": 0.216182, + "nauc_precision_at_1000_diff1": 0.00778, + "nauc_mrr_at_1_max": 0.215639, + "nauc_mrr_at_1_std": -0.064352, + "nauc_mrr_at_1_diff1": 0.258047, + "nauc_mrr_at_3_max": 0.234064, + "nauc_mrr_at_3_std": -0.0, + "nauc_mrr_at_3_diff1": 0.152177, + "nauc_mrr_at_5_max": 0.290311, + "nauc_mrr_at_5_std": 0.042935, + "nauc_mrr_at_5_diff1": 0.143572, + "nauc_mrr_at_10_max": 0.292406, + "nauc_mrr_at_10_std": 0.061552, + "nauc_mrr_at_10_diff1": 0.153749, + "nauc_mrr_at_20_max": 0.278397, + "nauc_mrr_at_20_std": 0.057388, + "nauc_mrr_at_20_diff1": 0.15056, + "nauc_mrr_at_100_max": 0.277238, + "nauc_mrr_at_100_std": 0.05945, + "nauc_mrr_at_100_diff1": 0.15021, + "nauc_mrr_at_1000_max": 0.277025, + "nauc_mrr_at_1000_std": 0.058222, + "nauc_mrr_at_1000_diff1": 0.149915, + "main_score": 0.20912, + "hf_subset": "Medical-Sciences", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.02062, + "ndcg_at_3": 0.01366, + "ndcg_at_5": 0.01388, + "ndcg_at_10": 0.01322, + "ndcg_at_20": 0.01492, + "ndcg_at_100": 0.0238, + "ndcg_at_1000": 0.06442, + "map_at_1": 0.00491, + "map_at_3": 0.00749, + "map_at_5": 0.008, + "map_at_10": 0.008, + "map_at_20": 0.00886, + "map_at_100": 0.00974, + "map_at_1000": 0.01076, + "recall_at_1": 0.00491, + "recall_at_3": 0.01006, + "recall_at_5": 0.01264, + "recall_at_10": 0.01264, + "recall_at_20": 0.0178, + "recall_at_100": 0.04796, + "recall_at_1000": 0.32311, + "precision_at_1": 0.02062, + "precision_at_3": 0.01031, + "precision_at_5": 0.00825, + "precision_at_10": 0.00412, + "precision_at_20": 0.00258, + "precision_at_100": 0.00186, + "precision_at_1000": 0.0009, + "mrr_at_1": 0.020619, + "mrr_at_3": 0.025773, + "mrr_at_5": 0.027835, + "mrr_at_10": 0.027835, + "mrr_at_20": 0.027835, + "mrr_at_100": 0.030287, + "mrr_at_1000": 0.031432, + "nauc_ndcg_at_1_max": 0.835306, + "nauc_ndcg_at_1_std": 0.125847, + "nauc_ndcg_at_1_diff1": 0.396681, + "nauc_ndcg_at_3_max": 0.42301, + "nauc_ndcg_at_3_std": 0.38099, + "nauc_ndcg_at_3_diff1": 0.259829, + "nauc_ndcg_at_5_max": 0.463802, + "nauc_ndcg_at_5_std": 0.457277, + "nauc_ndcg_at_5_diff1": 0.27132, + "nauc_ndcg_at_10_max": 0.453432, + "nauc_ndcg_at_10_std": 0.483826, + "nauc_ndcg_at_10_diff1": 0.234782, + "nauc_ndcg_at_20_max": 0.335464, + "nauc_ndcg_at_20_std": 0.542903, + "nauc_ndcg_at_20_diff1": 0.199648, + "nauc_ndcg_at_100_max": 0.204066, + "nauc_ndcg_at_100_std": 0.369917, + "nauc_ndcg_at_100_diff1": 0.148667, + "nauc_ndcg_at_1000_max": 0.163505, + "nauc_ndcg_at_1000_std": 0.198816, + "nauc_ndcg_at_1000_diff1": 0.090919, + "nauc_map_at_1_max": 0.901184, + "nauc_map_at_1_std": 0.205064, + "nauc_map_at_1_diff1": 0.155354, + "nauc_map_at_3_max": 0.392205, + "nauc_map_at_3_std": 0.47873, + "nauc_map_at_3_diff1": 0.077018, + "nauc_map_at_5_max": 0.431358, + "nauc_map_at_5_std": 0.491091, + "nauc_map_at_5_diff1": 0.136474, + "nauc_map_at_10_max": 0.431358, + "nauc_map_at_10_std": 0.491091, + "nauc_map_at_10_diff1": 0.136474, + "nauc_map_at_20_max": 0.333567, + "nauc_map_at_20_std": 0.540431, + "nauc_map_at_20_diff1": 0.116243, + "nauc_map_at_100_max": 0.300236, + "nauc_map_at_100_std": 0.500852, + "nauc_map_at_100_diff1": 0.107111, + "nauc_map_at_1000_max": 0.287771, + "nauc_map_at_1000_std": 0.474476, + "nauc_map_at_1000_diff1": 0.105135, + "nauc_recall_at_1_max": 0.901184, + "nauc_recall_at_1_std": 0.205064, + "nauc_recall_at_1_diff1": 0.155354, + "nauc_recall_at_3_max": 0.143923, + "nauc_recall_at_3_std": 0.612226, + "nauc_recall_at_3_diff1": 0.038805, + "nauc_recall_at_5_max": 0.318463, + "nauc_recall_at_5_std": 0.62413, + "nauc_recall_at_5_diff1": 0.234777, + "nauc_recall_at_10_max": 0.318463, + "nauc_recall_at_10_std": 0.62413, + "nauc_recall_at_10_diff1": 0.234777, + "nauc_recall_at_20_max": 0.059007, + "nauc_recall_at_20_std": 0.733003, + "nauc_recall_at_20_diff1": 0.145862, + "nauc_recall_at_100_max": -0.006075, + "nauc_recall_at_100_std": 0.306668, + "nauc_recall_at_100_diff1": 0.085244, + "nauc_recall_at_1000_max": 0.083334, + "nauc_recall_at_1000_std": 0.076413, + "nauc_recall_at_1000_diff1": 0.055248, + "nauc_precision_at_1_max": 0.835306, + "nauc_precision_at_1_std": 0.125847, + "nauc_precision_at_1_diff1": 0.396681, + "nauc_precision_at_3_max": 0.364445, + "nauc_precision_at_3_std": 0.417232, + "nauc_precision_at_3_diff1": 0.24039, + "nauc_precision_at_5_max": 0.523334, + "nauc_precision_at_5_std": 0.480577, + "nauc_precision_at_5_diff1": 0.430292, + "nauc_precision_at_10_max": 0.523334, + "nauc_precision_at_10_std": 0.480577, + "nauc_precision_at_10_diff1": 0.430292, + "nauc_precision_at_20_max": 0.303211, + "nauc_precision_at_20_std": 0.584461, + "nauc_precision_at_20_diff1": 0.329795, + "nauc_precision_at_100_max": 0.094209, + "nauc_precision_at_100_std": 0.221252, + "nauc_precision_at_100_diff1": 0.181605, + "nauc_precision_at_1000_max": 0.100413, + "nauc_precision_at_1000_std": 0.005342, + "nauc_precision_at_1000_diff1": 0.055612, + "nauc_mrr_at_1_max": 0.835306, + "nauc_mrr_at_1_std": 0.125847, + "nauc_mrr_at_1_diff1": 0.396681, + "nauc_mrr_at_3_max": 0.552789, + "nauc_mrr_at_3_std": 0.300678, + "nauc_mrr_at_3_diff1": 0.302907, + "nauc_mrr_at_5_max": 0.585916, + "nauc_mrr_at_5_std": 0.32808, + "nauc_mrr_at_5_diff1": 0.354543, + "nauc_mrr_at_10_max": 0.585916, + "nauc_mrr_at_10_std": 0.32808, + "nauc_mrr_at_10_diff1": 0.354543, + "nauc_mrr_at_20_max": 0.585916, + "nauc_mrr_at_20_std": 0.32808, + "nauc_mrr_at_20_diff1": 0.354543, + "nauc_mrr_at_100_max": 0.535339, + "nauc_mrr_at_100_std": 0.307997, + "nauc_mrr_at_100_diff1": 0.32693, + "nauc_mrr_at_1000_max": 0.525449, + "nauc_mrr_at_1000_std": 0.304737, + "nauc_mrr_at_1000_diff1": 0.31785, + "main_score": 0.01322, + "hf_subset": "MedXpertQA-Exam", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.02542, + "ndcg_at_3": 0.02767, + "ndcg_at_5": 0.02943, + "ndcg_at_10": 0.03778, + "ndcg_at_20": 0.0458, + "ndcg_at_100": 0.06505, + "ndcg_at_1000": 0.10617, + "map_at_1": 0.00593, + "map_at_3": 0.0155, + "map_at_5": 0.01923, + "map_at_10": 0.025, + "map_at_20": 0.02667, + "map_at_100": 0.02881, + "map_at_1000": 0.0305, + "recall_at_1": 0.00593, + "recall_at_3": 0.0238, + "recall_at_5": 0.03355, + "recall_at_10": 0.05226, + "recall_at_20": 0.0726, + "recall_at_100": 0.14112, + "recall_at_1000": 0.35542, + "precision_at_1": 0.02542, + "precision_at_3": 0.02542, + "precision_at_5": 0.02373, + "precision_at_10": 0.0178, + "precision_at_20": 0.01314, + "precision_at_100": 0.00551, + "precision_at_1000": 0.00152, + "mrr_at_1": 0.025424, + "mrr_at_3": 0.036723, + "mrr_at_5": 0.042655, + "mrr_at_10": 0.046069, + "mrr_at_20": 0.050784, + "mrr_at_100": 0.055205, + "mrr_at_1000": 0.056206, + "nauc_ndcg_at_1_max": -0.053293, + "nauc_ndcg_at_1_std": 0.776529, + "nauc_ndcg_at_1_diff1": 0.198706, + "nauc_ndcg_at_3_max": -0.153728, + "nauc_ndcg_at_3_std": 0.414922, + "nauc_ndcg_at_3_diff1": 0.075167, + "nauc_ndcg_at_5_max": -0.194374, + "nauc_ndcg_at_5_std": 0.417551, + "nauc_ndcg_at_5_diff1": 0.104533, + "nauc_ndcg_at_10_max": -0.211545, + "nauc_ndcg_at_10_std": 0.435297, + "nauc_ndcg_at_10_diff1": 0.088069, + "nauc_ndcg_at_20_max": -0.208015, + "nauc_ndcg_at_20_std": 0.430641, + "nauc_ndcg_at_20_diff1": 0.068205, + "nauc_ndcg_at_100_max": -0.175457, + "nauc_ndcg_at_100_std": 0.466499, + "nauc_ndcg_at_100_diff1": -0.005971, + "nauc_ndcg_at_1000_max": -0.184705, + "nauc_ndcg_at_1000_std": 0.422963, + "nauc_ndcg_at_1000_diff1": -0.018794, + "nauc_map_at_1_max": -0.080642, + "nauc_map_at_1_std": 0.760567, + "nauc_map_at_1_diff1": 0.248872, + "nauc_map_at_3_max": -0.128791, + "nauc_map_at_3_std": 0.469736, + "nauc_map_at_3_diff1": 0.107224, + "nauc_map_at_5_max": -0.14105, + "nauc_map_at_5_std": 0.529493, + "nauc_map_at_5_diff1": 0.156778, + "nauc_map_at_10_max": -0.174506, + "nauc_map_at_10_std": 0.553323, + "nauc_map_at_10_diff1": 0.158348, + "nauc_map_at_20_max": -0.178586, + "nauc_map_at_20_std": 0.54837, + "nauc_map_at_20_diff1": 0.149353, + "nauc_map_at_100_max": -0.166928, + "nauc_map_at_100_std": 0.5534, + "nauc_map_at_100_diff1": 0.128058, + "nauc_map_at_1000_max": -0.166918, + "nauc_map_at_1000_std": 0.551562, + "nauc_map_at_1000_diff1": 0.121066, + "nauc_recall_at_1_max": -0.080642, + "nauc_recall_at_1_std": 0.760567, + "nauc_recall_at_1_diff1": 0.248872, + "nauc_recall_at_3_max": -0.261281, + "nauc_recall_at_3_std": 0.212114, + "nauc_recall_at_3_diff1": 0.13154, + "nauc_recall_at_5_max": -0.250278, + "nauc_recall_at_5_std": 0.335494, + "nauc_recall_at_5_diff1": 0.118678, + "nauc_recall_at_10_max": -0.265181, + "nauc_recall_at_10_std": 0.364452, + "nauc_recall_at_10_diff1": 0.064661, + "nauc_recall_at_20_max": -0.248257, + "nauc_recall_at_20_std": 0.370626, + "nauc_recall_at_20_diff1": 0.024707, + "nauc_recall_at_100_max": -0.178424, + "nauc_recall_at_100_std": 0.409709, + "nauc_recall_at_100_diff1": -0.100783, + "nauc_recall_at_1000_max": -0.175027, + "nauc_recall_at_1000_std": 0.327113, + "nauc_recall_at_1000_diff1": -0.122454, + "nauc_precision_at_1_max": -0.053293, + "nauc_precision_at_1_std": 0.776529, + "nauc_precision_at_1_diff1": 0.198706, + "nauc_precision_at_3_max": -0.127688, + "nauc_precision_at_3_std": 0.427719, + "nauc_precision_at_3_diff1": 0.057177, + "nauc_precision_at_5_max": -0.161098, + "nauc_precision_at_5_std": 0.48293, + "nauc_precision_at_5_diff1": 0.05118, + "nauc_precision_at_10_max": -0.201246, + "nauc_precision_at_10_std": 0.474713, + "nauc_precision_at_10_diff1": 0.04736, + "nauc_precision_at_20_max": -0.184002, + "nauc_precision_at_20_std": 0.439581, + "nauc_precision_at_20_diff1": 0.040493, + "nauc_precision_at_100_max": -0.112411, + "nauc_precision_at_100_std": 0.528243, + "nauc_precision_at_100_diff1": -0.089925, + "nauc_precision_at_1000_max": -0.139643, + "nauc_precision_at_1000_std": 0.344166, + "nauc_precision_at_1000_diff1": -0.031979, + "nauc_mrr_at_1_max": -0.053293, + "nauc_mrr_at_1_std": 0.776529, + "nauc_mrr_at_1_diff1": 0.198706, + "nauc_mrr_at_3_max": -0.196573, + "nauc_mrr_at_3_std": 0.379164, + "nauc_mrr_at_3_diff1": 0.125158, + "nauc_mrr_at_5_max": -0.203971, + "nauc_mrr_at_5_std": 0.368435, + "nauc_mrr_at_5_diff1": 0.068915, + "nauc_mrr_at_10_max": -0.208565, + "nauc_mrr_at_10_std": 0.345209, + "nauc_mrr_at_10_diff1": 0.048075, + "nauc_mrr_at_20_max": -0.197435, + "nauc_mrr_at_20_std": 0.342418, + "nauc_mrr_at_20_diff1": 0.037749, + "nauc_mrr_at_100_max": -0.194756, + "nauc_mrr_at_100_std": 0.352494, + "nauc_mrr_at_100_diff1": 0.027374, + "nauc_mrr_at_1000_max": -0.196102, + "nauc_mrr_at_1000_std": 0.34986, + "nauc_mrr_at_1000_diff1": 0.030524, + "main_score": 0.03778, + "hf_subset": "MedQA-Diag", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.01333, + "ndcg_at_3": 0.014, + "ndcg_at_5": 0.01472, + "ndcg_at_10": 0.02351, + "ndcg_at_20": 0.03159, + "ndcg_at_100": 0.05005, + "ndcg_at_1000": 0.08781, + "map_at_1": 0.008, + "map_at_3": 0.01133, + "map_at_5": 0.012, + "map_at_10": 0.01551, + "map_at_20": 0.01727, + "map_at_100": 0.01932, + "map_at_1000": 0.02039, + "recall_at_1": 0.008, + "recall_at_3": 0.01467, + "recall_at_5": 0.018, + "recall_at_10": 0.03989, + "recall_at_20": 0.06644, + "recall_at_100": 0.15556, + "recall_at_1000": 0.42067, + "precision_at_1": 0.01333, + "precision_at_3": 0.00667, + "precision_at_5": 0.00533, + "precision_at_10": 0.00733, + "precision_at_20": 0.00667, + "precision_at_100": 0.00307, + "precision_at_1000": 0.00086, + "mrr_at_1": 0.013333, + "mrr_at_3": 0.016667, + "mrr_at_5": 0.018, + "mrr_at_10": 0.023415, + "mrr_at_20": 0.026754, + "mrr_at_100": 0.029522, + "mrr_at_1000": 0.030628, + "nauc_ndcg_at_1_max": -0.494902, + "nauc_ndcg_at_1_std": -0.194526, + "nauc_ndcg_at_1_diff1": -0.494902, + "nauc_ndcg_at_3_max": -0.539053, + "nauc_ndcg_at_3_std": 0.094088, + "nauc_ndcg_at_3_diff1": -0.498711, + "nauc_ndcg_at_5_max": -0.417303, + "nauc_ndcg_at_5_std": 0.215759, + "nauc_ndcg_at_5_diff1": -0.405836, + "nauc_ndcg_at_10_max": -0.243844, + "nauc_ndcg_at_10_std": 0.15667, + "nauc_ndcg_at_10_diff1": -0.29857, + "nauc_ndcg_at_20_max": -0.141056, + "nauc_ndcg_at_20_std": 0.197088, + "nauc_ndcg_at_20_diff1": -0.271722, + "nauc_ndcg_at_100_max": -0.123196, + "nauc_ndcg_at_100_std": 0.053502, + "nauc_ndcg_at_100_diff1": -0.184713, + "nauc_ndcg_at_1000_max": -0.109228, + "nauc_ndcg_at_1000_std": 0.027784, + "nauc_ndcg_at_1000_diff1": -0.065519, + "nauc_map_at_1_max": -0.548117, + "nauc_map_at_1_std": -0.111886, + "nauc_map_at_1_diff1": -0.441687, + "nauc_map_at_3_max": -0.555943, + "nauc_map_at_3_std": 0.115706, + "nauc_map_at_3_diff1": -0.480816, + "nauc_map_at_5_max": -0.488284, + "nauc_map_at_5_std": 0.164833, + "nauc_map_at_5_diff1": -0.436112, + "nauc_map_at_10_max": -0.343449, + "nauc_map_at_10_std": 0.183427, + "nauc_map_at_10_diff1": -0.346846, + "nauc_map_at_20_max": -0.29299, + "nauc_map_at_20_std": 0.190573, + "nauc_map_at_20_diff1": -0.333243, + "nauc_map_at_100_max": -0.275838, + "nauc_map_at_100_std": 0.157149, + "nauc_map_at_100_diff1": -0.309497, + "nauc_map_at_1000_max": -0.273477, + "nauc_map_at_1000_std": 0.153355, + "nauc_map_at_1000_diff1": -0.295872, + "nauc_recall_at_1_max": -0.548117, + "nauc_recall_at_1_std": -0.111886, + "nauc_recall_at_1_diff1": -0.441687, + "nauc_recall_at_3_max": -0.560212, + "nauc_recall_at_3_std": 0.239847, + "nauc_recall_at_3_diff1": -0.502159, + "nauc_recall_at_5_max": -0.33389, + "nauc_recall_at_5_std": 0.380616, + "nauc_recall_at_5_diff1": -0.349194, + "nauc_recall_at_10_max": -0.159818, + "nauc_recall_at_10_std": 0.185274, + "nauc_recall_at_10_diff1": -0.236827, + "nauc_recall_at_20_max": -0.028991, + "nauc_recall_at_20_std": 0.240144, + "nauc_recall_at_20_diff1": -0.224516, + "nauc_recall_at_100_max": -0.06073, + "nauc_recall_at_100_std": -0.029015, + "nauc_recall_at_100_diff1": -0.109063, + "nauc_recall_at_1000_max": -0.008776, + "nauc_recall_at_1000_std": -0.053915, + "nauc_recall_at_1000_diff1": 0.093845, + "nauc_precision_at_1_max": -0.494902, + "nauc_precision_at_1_std": -0.194526, + "nauc_precision_at_1_diff1": -0.494902, + "nauc_precision_at_3_max": -0.52151, + "nauc_precision_at_3_std": 0.090958, + "nauc_precision_at_3_diff1": -0.52151, + "nauc_precision_at_5_max": -0.225651, + "nauc_precision_at_5_std": 0.318218, + "nauc_precision_at_5_diff1": -0.310169, + "nauc_precision_at_10_max": -0.021148, + "nauc_precision_at_10_std": 0.127009, + "nauc_precision_at_10_diff1": -0.186965, + "nauc_precision_at_20_max": 0.052643, + "nauc_precision_at_20_std": 0.216973, + "nauc_precision_at_20_diff1": -0.18444, + "nauc_precision_at_100_max": 0.026913, + "nauc_precision_at_100_std": -0.017896, + "nauc_precision_at_100_diff1": -0.060379, + "nauc_precision_at_1000_max": -0.043919, + "nauc_precision_at_1000_std": -0.046792, + "nauc_precision_at_1000_diff1": 0.092878, + "nauc_mrr_at_1_max": -0.494902, + "nauc_mrr_at_1_std": -0.194526, + "nauc_mrr_at_1_diff1": -0.494902, + "nauc_mrr_at_3_max": -0.510867, + "nauc_mrr_at_3_std": -0.023236, + "nauc_mrr_at_3_diff1": -0.510867, + "nauc_mrr_at_5_max": -0.423993, + "nauc_mrr_at_5_std": 0.052559, + "nauc_mrr_at_5_diff1": -0.449036, + "nauc_mrr_at_10_max": -0.322283, + "nauc_mrr_at_10_std": 0.013746, + "nauc_mrr_at_10_diff1": -0.384352, + "nauc_mrr_at_20_max": -0.253767, + "nauc_mrr_at_20_std": 0.056992, + "nauc_mrr_at_20_diff1": -0.348141, + "nauc_mrr_at_100_max": -0.247425, + "nauc_mrr_at_100_std": 0.029026, + "nauc_mrr_at_100_diff1": -0.315017, + "nauc_mrr_at_1000_max": -0.246241, + "nauc_mrr_at_1000_std": 0.031268, + "nauc_mrr_at_1000_diff1": -0.306577, + "main_score": 0.02351, + "hf_subset": "PMC-Treatment", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.08772, + "ndcg_at_3": 0.08041, + "ndcg_at_5": 0.08748, + "ndcg_at_10": 0.10383, + "ndcg_at_20": 0.11983, + "ndcg_at_100": 0.17081, + "ndcg_at_1000": 0.21346, + "map_at_1": 0.03289, + "map_at_3": 0.05263, + "map_at_5": 0.0576, + "map_at_10": 0.06402, + "map_at_20": 0.06823, + "map_at_100": 0.07624, + "map_at_1000": 0.07813, + "recall_at_1": 0.03289, + "recall_at_3": 0.08553, + "recall_at_5": 0.10599, + "recall_at_10": 0.14693, + "recall_at_20": 0.1981, + "recall_at_100": 0.42178, + "recall_at_1000": 0.69371, + "precision_at_1": 0.08772, + "precision_at_3": 0.06433, + "precision_at_5": 0.04561, + "precision_at_10": 0.03158, + "precision_at_20": 0.02149, + "precision_at_100": 0.00904, + "precision_at_1000": 0.00154, + "mrr_at_1": 0.087719, + "mrr_at_3": 0.128655, + "mrr_at_5": 0.133918, + "mrr_at_10": 0.142725, + "mrr_at_20": 0.148097, + "mrr_at_100": 0.154466, + "mrr_at_1000": 0.155584, + "nauc_ndcg_at_1_max": 0.124344, + "nauc_ndcg_at_1_std": -0.069754, + "nauc_ndcg_at_1_diff1": 0.209942, + "nauc_ndcg_at_3_max": 0.151359, + "nauc_ndcg_at_3_std": -0.109539, + "nauc_ndcg_at_3_diff1": 0.171639, + "nauc_ndcg_at_5_max": 0.148132, + "nauc_ndcg_at_5_std": -0.123842, + "nauc_ndcg_at_5_diff1": 0.173214, + "nauc_ndcg_at_10_max": 0.093376, + "nauc_ndcg_at_10_std": -0.101726, + "nauc_ndcg_at_10_diff1": 0.166672, + "nauc_ndcg_at_20_max": 0.086379, + "nauc_ndcg_at_20_std": -0.066363, + "nauc_ndcg_at_20_diff1": 0.123268, + "nauc_ndcg_at_100_max": 0.106403, + "nauc_ndcg_at_100_std": -0.01677, + "nauc_ndcg_at_100_diff1": 0.141445, + "nauc_ndcg_at_1000_max": 0.112735, + "nauc_ndcg_at_1000_std": -0.005997, + "nauc_ndcg_at_1000_diff1": 0.176617, + "nauc_map_at_1_max": 0.083303, + "nauc_map_at_1_std": -0.129767, + "nauc_map_at_1_diff1": 0.257262, + "nauc_map_at_3_max": 0.13963, + "nauc_map_at_3_std": -0.139053, + "nauc_map_at_3_diff1": 0.210223, + "nauc_map_at_5_max": 0.148175, + "nauc_map_at_5_std": -0.150864, + "nauc_map_at_5_diff1": 0.191317, + "nauc_map_at_10_max": 0.114587, + "nauc_map_at_10_std": -0.137142, + "nauc_map_at_10_diff1": 0.188408, + "nauc_map_at_20_max": 0.108443, + "nauc_map_at_20_std": -0.117501, + "nauc_map_at_20_diff1": 0.164264, + "nauc_map_at_100_max": 0.114524, + "nauc_map_at_100_std": -0.096035, + "nauc_map_at_100_diff1": 0.164073, + "nauc_map_at_1000_max": 0.113739, + "nauc_map_at_1000_std": -0.094804, + "nauc_map_at_1000_diff1": 0.16601, + "nauc_recall_at_1_max": 0.083303, + "nauc_recall_at_1_std": -0.129767, + "nauc_recall_at_1_diff1": 0.257262, + "nauc_recall_at_3_max": 0.168361, + "nauc_recall_at_3_std": -0.135949, + "nauc_recall_at_3_diff1": 0.183536, + "nauc_recall_at_5_max": 0.157759, + "nauc_recall_at_5_std": -0.143911, + "nauc_recall_at_5_diff1": 0.148548, + "nauc_recall_at_10_max": 0.071818, + "nauc_recall_at_10_std": -0.114467, + "nauc_recall_at_10_diff1": 0.134433, + "nauc_recall_at_20_max": 0.050096, + "nauc_recall_at_20_std": -0.035154, + "nauc_recall_at_20_diff1": 0.028696, + "nauc_recall_at_100_max": 0.092521, + "nauc_recall_at_100_std": 0.054897, + "nauc_recall_at_100_diff1": 0.074102, + "nauc_recall_at_1000_max": 0.141192, + "nauc_recall_at_1000_std": 0.132391, + "nauc_recall_at_1000_diff1": 0.209126, + "nauc_precision_at_1_max": 0.124344, + "nauc_precision_at_1_std": -0.069754, + "nauc_precision_at_1_diff1": 0.209942, + "nauc_precision_at_3_max": 0.146063, + "nauc_precision_at_3_std": -0.082202, + "nauc_precision_at_3_diff1": 0.133145, + "nauc_precision_at_5_max": 0.15295, + "nauc_precision_at_5_std": -0.075051, + "nauc_precision_at_5_diff1": 0.129693, + "nauc_precision_at_10_max": 0.021164, + "nauc_precision_at_10_std": 0.006645, + "nauc_precision_at_10_diff1": 0.130511, + "nauc_precision_at_20_max": 0.044074, + "nauc_precision_at_20_std": 0.065621, + "nauc_precision_at_20_diff1": 0.061495, + "nauc_precision_at_100_max": 0.103242, + "nauc_precision_at_100_std": 0.17136, + "nauc_precision_at_100_diff1": 0.139379, + "nauc_precision_at_1000_max": 0.062129, + "nauc_precision_at_1000_std": 0.157122, + "nauc_precision_at_1000_diff1": 0.208118, + "nauc_mrr_at_1_max": 0.124344, + "nauc_mrr_at_1_std": -0.069754, + "nauc_mrr_at_1_diff1": 0.209942, + "nauc_mrr_at_3_max": 0.139174, + "nauc_mrr_at_3_std": -0.076831, + "nauc_mrr_at_3_diff1": 0.159219, + "nauc_mrr_at_5_max": 0.133878, + "nauc_mrr_at_5_std": -0.067535, + "nauc_mrr_at_5_diff1": 0.162664, + "nauc_mrr_at_10_max": 0.1097, + "nauc_mrr_at_10_std": -0.058654, + "nauc_mrr_at_10_diff1": 0.155985, + "nauc_mrr_at_20_max": 0.106792, + "nauc_mrr_at_20_std": -0.055206, + "nauc_mrr_at_20_diff1": 0.153407, + "nauc_mrr_at_100_max": 0.107523, + "nauc_mrr_at_100_std": -0.053768, + "nauc_mrr_at_100_diff1": 0.156681, + "nauc_mrr_at_1000_max": 0.107874, + "nauc_mrr_at_1000_std": -0.054624, + "nauc_mrr_at_1000_diff1": 0.156803, + "main_score": 0.10383, + "hf_subset": "PMC-Clinical", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.06202, + "ndcg_at_3": 0.05015, + "ndcg_at_5": 0.04773, + "ndcg_at_10": 0.05255, + "ndcg_at_20": 0.07005, + "ndcg_at_100": 0.11641, + "ndcg_at_1000": 0.17467, + "map_at_1": 0.01447, + "map_at_3": 0.02532, + "map_at_5": 0.028, + "map_at_10": 0.03051, + "map_at_20": 0.03503, + "map_at_100": 0.04102, + "map_at_1000": 0.04381, + "recall_at_1": 0.01447, + "recall_at_3": 0.0323, + "recall_at_5": 0.04276, + "recall_at_10": 0.05504, + "recall_at_20": 0.10142, + "recall_at_100": 0.28695, + "recall_at_1000": 0.6137, + "precision_at_1": 0.06202, + "precision_at_3": 0.04651, + "precision_at_5": 0.03721, + "precision_at_10": 0.02326, + "precision_at_20": 0.02016, + "precision_at_100": 0.01008, + "precision_at_1000": 0.00217, + "mrr_at_1": 0.062016, + "mrr_at_3": 0.083979, + "mrr_at_5": 0.092894, + "mrr_at_10": 0.096253, + "mrr_at_20": 0.104178, + "mrr_at_100": 0.111102, + "mrr_at_1000": 0.112278, + "nauc_ndcg_at_1_max": 0.301287, + "nauc_ndcg_at_1_std": 0.203864, + "nauc_ndcg_at_1_diff1": 0.11268, + "nauc_ndcg_at_3_max": 0.310735, + "nauc_ndcg_at_3_std": 0.322812, + "nauc_ndcg_at_3_diff1": -0.01879, + "nauc_ndcg_at_5_max": 0.259523, + "nauc_ndcg_at_5_std": 0.295123, + "nauc_ndcg_at_5_diff1": -0.013434, + "nauc_ndcg_at_10_max": 0.228333, + "nauc_ndcg_at_10_std": 0.245057, + "nauc_ndcg_at_10_diff1": -0.016074, + "nauc_ndcg_at_20_max": 0.262415, + "nauc_ndcg_at_20_std": 0.283923, + "nauc_ndcg_at_20_diff1": 0.015264, + "nauc_ndcg_at_100_max": 0.271931, + "nauc_ndcg_at_100_std": 0.32286, + "nauc_ndcg_at_100_diff1": 0.01482, + "nauc_ndcg_at_1000_max": 0.342831, + "nauc_ndcg_at_1000_std": 0.351008, + "nauc_ndcg_at_1000_diff1": 0.009468, + "nauc_map_at_1_max": 0.246448, + "nauc_map_at_1_std": 0.221888, + "nauc_map_at_1_diff1": 0.107192, + "nauc_map_at_3_max": 0.30893, + "nauc_map_at_3_std": 0.349534, + "nauc_map_at_3_diff1": -0.038603, + "nauc_map_at_5_max": 0.285851, + "nauc_map_at_5_std": 0.336147, + "nauc_map_at_5_diff1": -0.037838, + "nauc_map_at_10_max": 0.262335, + "nauc_map_at_10_std": 0.305024, + "nauc_map_at_10_diff1": -0.035846, + "nauc_map_at_20_max": 0.27716, + "nauc_map_at_20_std": 0.321688, + "nauc_map_at_20_diff1": -0.022628, + "nauc_map_at_100_max": 0.274307, + "nauc_map_at_100_std": 0.335761, + "nauc_map_at_100_diff1": -0.025416, + "nauc_map_at_1000_max": 0.290527, + "nauc_map_at_1000_std": 0.345149, + "nauc_map_at_1000_diff1": -0.02753, + "nauc_recall_at_1_max": 0.246448, + "nauc_recall_at_1_std": 0.221888, + "nauc_recall_at_1_diff1": 0.107192, + "nauc_recall_at_3_max": 0.330737, + "nauc_recall_at_3_std": 0.365909, + "nauc_recall_at_3_diff1": -0.071226, + "nauc_recall_at_5_max": 0.245388, + "nauc_recall_at_5_std": 0.304908, + "nauc_recall_at_5_diff1": -0.044433, + "nauc_recall_at_10_max": 0.183288, + "nauc_recall_at_10_std": 0.205597, + "nauc_recall_at_10_diff1": -0.022601, + "nauc_recall_at_20_max": 0.243053, + "nauc_recall_at_20_std": 0.269997, + "nauc_recall_at_20_diff1": 0.055373, + "nauc_recall_at_100_max": 0.188911, + "nauc_recall_at_100_std": 0.255668, + "nauc_recall_at_100_diff1": 0.074952, + "nauc_recall_at_1000_max": 0.291541, + "nauc_recall_at_1000_std": 0.301225, + "nauc_recall_at_1000_diff1": 0.072515, + "nauc_precision_at_1_max": 0.301287, + "nauc_precision_at_1_std": 0.203864, + "nauc_precision_at_1_diff1": 0.11268, + "nauc_precision_at_3_max": 0.320772, + "nauc_precision_at_3_std": 0.375516, + "nauc_precision_at_3_diff1": -0.061685, + "nauc_precision_at_5_max": 0.244265, + "nauc_precision_at_5_std": 0.31316, + "nauc_precision_at_5_diff1": -0.054878, + "nauc_precision_at_10_max": 0.186195, + "nauc_precision_at_10_std": 0.226573, + "nauc_precision_at_10_diff1": -0.047522, + "nauc_precision_at_20_max": 0.253518, + "nauc_precision_at_20_std": 0.305716, + "nauc_precision_at_20_diff1": -0.008274, + "nauc_precision_at_100_max": 0.287338, + "nauc_precision_at_100_std": 0.381467, + "nauc_precision_at_100_diff1": -0.036282, + "nauc_precision_at_1000_max": 0.386433, + "nauc_precision_at_1000_std": 0.353233, + "nauc_precision_at_1000_diff1": -0.050014, + "nauc_mrr_at_1_max": 0.301287, + "nauc_mrr_at_1_std": 0.203864, + "nauc_mrr_at_1_diff1": 0.11268, + "nauc_mrr_at_3_max": 0.29916, + "nauc_mrr_at_3_std": 0.235867, + "nauc_mrr_at_3_diff1": 0.034262, + "nauc_mrr_at_5_max": 0.257356, + "nauc_mrr_at_5_std": 0.212339, + "nauc_mrr_at_5_diff1": 0.037853, + "nauc_mrr_at_10_max": 0.25021, + "nauc_mrr_at_10_std": 0.195357, + "nauc_mrr_at_10_diff1": 0.03729, + "nauc_mrr_at_20_max": 0.257129, + "nauc_mrr_at_20_std": 0.210762, + "nauc_mrr_at_20_diff1": 0.039071, + "nauc_mrr_at_100_max": 0.262204, + "nauc_mrr_at_100_std": 0.214833, + "nauc_mrr_at_100_diff1": 0.037427, + "nauc_mrr_at_1000_max": 0.262402, + "nauc_mrr_at_1000_std": 0.21403, + "nauc_mrr_at_1000_diff1": 0.037429, + "main_score": 0.05255, + "hf_subset": "IIYi-Clinical", + "languages": [ + "eng-Latn" + ] + } + ] + }, + "evaluation_time": 374.84417152404785, + "kg_co2_emissions": null +} \ No newline at end of file diff --git a/results/intfloat__multilingual-e5-large/ab10c1a7f42e74530fe7ae5be82e6d4f11a719eb/R2MEDRetrieval.json b/results/intfloat__multilingual-e5-large/ab10c1a7f42e74530fe7ae5be82e6d4f11a719eb/R2MEDRetrieval.json new file mode 100644 index 0000000000..ab0df7bcd4 --- /dev/null +++ b/results/intfloat__multilingual-e5-large/ab10c1a7f42e74530fe7ae5be82e6d4f11a719eb/R2MEDRetrieval.json @@ -0,0 +1,1187 @@ +{ + "dataset_revision": "1.0", + "task_name": "R2MEDRetrieval", + "mteb_version": "1.38.20", + "scores": { + "test": [ + { + "ndcg_at_1": 0.02913, + "ndcg_at_3": 0.01595, + "ndcg_at_5": 0.01686, + "ndcg_at_10": 0.0179, + "ndcg_at_20": 0.02166, + "ndcg_at_100": 0.02679, + "ndcg_at_1000": 0.0474, + "map_at_1": 0.00841, + "map_at_3": 0.00922, + "map_at_5": 0.01044, + "map_at_10": 0.01092, + "map_at_20": 0.01208, + "map_at_100": 0.01283, + "map_at_1000": 0.0133, + "recall_at_1": 0.00841, + "recall_at_3": 0.01084, + "recall_at_5": 0.0157, + "recall_at_10": 0.01764, + "recall_at_20": 0.02896, + "recall_at_100": 0.04668, + "recall_at_1000": 0.17137, + "precision_at_1": 0.02913, + "precision_at_3": 0.01294, + "precision_at_5": 0.00971, + "precision_at_10": 0.00583, + "precision_at_20": 0.00437, + "precision_at_100": 0.00165, + "precision_at_1000": 0.00057, + "mrr_at_1": 0.029126, + "mrr_at_3": 0.032362, + "mrr_at_5": 0.03479, + "mrr_at_10": 0.03479, + "mrr_at_20": 0.035483, + "mrr_at_100": 0.036729, + "mrr_at_1000": 0.037567, + "nauc_ndcg_at_1_max": 0.060589, + "nauc_ndcg_at_1_std": -0.396488, + "nauc_ndcg_at_1_diff1": 0.062034, + "nauc_ndcg_at_3_max": 0.066227, + "nauc_ndcg_at_3_std": -0.293621, + "nauc_ndcg_at_3_diff1": -0.028518, + "nauc_ndcg_at_5_max": 0.15238, + "nauc_ndcg_at_5_std": -0.329093, + "nauc_ndcg_at_5_diff1": 0.058929, + "nauc_ndcg_at_10_max": 0.110359, + "nauc_ndcg_at_10_std": -0.343177, + "nauc_ndcg_at_10_diff1": 0.03714, + "nauc_ndcg_at_20_max": 0.107184, + "nauc_ndcg_at_20_std": -0.350258, + "nauc_ndcg_at_20_diff1": 0.050143, + "nauc_ndcg_at_100_max": 0.175455, + "nauc_ndcg_at_100_std": -0.288798, + "nauc_ndcg_at_100_diff1": 0.124042, + "nauc_ndcg_at_1000_max": 0.118551, + "nauc_ndcg_at_1000_std": -0.214779, + "nauc_ndcg_at_1000_diff1": 0.096533, + "nauc_map_at_1_max": 0.157884, + "nauc_map_at_1_std": -0.369512, + "nauc_map_at_1_diff1": 0.120282, + "nauc_map_at_3_max": 0.152811, + "nauc_map_at_3_std": -0.308715, + "nauc_map_at_3_diff1": 0.05957, + "nauc_map_at_5_max": 0.172668, + "nauc_map_at_5_std": -0.339309, + "nauc_map_at_5_diff1": 0.090269, + "nauc_map_at_10_max": 0.139579, + "nauc_map_at_10_std": -0.349643, + "nauc_map_at_10_diff1": 0.072187, + "nauc_map_at_20_max": 0.141272, + "nauc_map_at_20_std": -0.3507, + "nauc_map_at_20_diff1": 0.077035, + "nauc_map_at_100_max": 0.159854, + "nauc_map_at_100_std": -0.338539, + "nauc_map_at_100_diff1": 0.091419, + "nauc_map_at_1000_max": 0.155179, + "nauc_map_at_1000_std": -0.33295, + "nauc_map_at_1000_diff1": 0.08978, + "nauc_recall_at_1_max": 0.157884, + "nauc_recall_at_1_std": -0.369512, + "nauc_recall_at_1_diff1": 0.120282, + "nauc_recall_at_3_max": 0.144937, + "nauc_recall_at_3_std": -0.214343, + "nauc_recall_at_3_diff1": -0.034668, + "nauc_recall_at_5_max": 0.200187, + "nauc_recall_at_5_std": -0.324905, + "nauc_recall_at_5_diff1": 0.076129, + "nauc_recall_at_10_max": 0.115194, + "nauc_recall_at_10_std": -0.352089, + "nauc_recall_at_10_diff1": 0.032896, + "nauc_recall_at_20_max": 0.101289, + "nauc_recall_at_20_std": -0.36676, + "nauc_recall_at_20_diff1": 0.064641, + "nauc_recall_at_100_max": 0.230485, + "nauc_recall_at_100_std": -0.23236, + "nauc_recall_at_100_diff1": 0.197991, + "nauc_recall_at_1000_max": 0.076186, + "nauc_recall_at_1000_std": -0.117806, + "nauc_recall_at_1000_diff1": 0.086442, + "nauc_precision_at_1_max": 0.060589, + "nauc_precision_at_1_std": -0.396488, + "nauc_precision_at_1_diff1": 0.062034, + "nauc_precision_at_3_max": 0.070455, + "nauc_precision_at_3_std": -0.216471, + "nauc_precision_at_3_diff1": -0.096432, + "nauc_precision_at_5_max": 0.12108, + "nauc_precision_at_5_std": -0.287543, + "nauc_precision_at_5_diff1": -0.01243, + "nauc_precision_at_10_max": 0.005595, + "nauc_precision_at_10_std": -0.334923, + "nauc_precision_at_10_diff1": -0.063121, + "nauc_precision_at_20_max": 0.052287, + "nauc_precision_at_20_std": -0.347166, + "nauc_precision_at_20_diff1": 0.006111, + "nauc_precision_at_100_max": 0.230919, + "nauc_precision_at_100_std": -0.198746, + "nauc_precision_at_100_diff1": 0.205906, + "nauc_precision_at_1000_max": 0.060483, + "nauc_precision_at_1000_std": -0.102795, + "nauc_precision_at_1000_diff1": 0.090041, + "nauc_mrr_at_1_max": 0.060589, + "nauc_mrr_at_1_std": -0.396488, + "nauc_mrr_at_1_diff1": 0.062034, + "nauc_mrr_at_3_max": 0.064535, + "nauc_mrr_at_3_std": -0.324481, + "nauc_mrr_at_3_diff1": -0.001352, + "nauc_mrr_at_5_max": 0.082608, + "nauc_mrr_at_5_std": -0.341738, + "nauc_mrr_at_5_diff1": 0.021317, + "nauc_mrr_at_10_max": 0.082608, + "nauc_mrr_at_10_std": -0.341738, + "nauc_mrr_at_10_diff1": 0.021317, + "nauc_mrr_at_20_max": 0.074806, + "nauc_mrr_at_20_std": -0.344778, + "nauc_mrr_at_20_diff1": 0.019553, + "nauc_mrr_at_100_max": 0.091712, + "nauc_mrr_at_100_std": -0.331918, + "nauc_mrr_at_100_diff1": 0.040258, + "nauc_mrr_at_1000_max": 0.092376, + "nauc_mrr_at_1000_std": -0.327193, + "nauc_mrr_at_1000_diff1": 0.041245, + "main_score": 0.0179, + "hf_subset": "Biology", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.1039, + "ndcg_at_3": 0.12863, + "ndcg_at_5": 0.16226, + "ndcg_at_10": 0.18908, + "ndcg_at_20": 0.21733, + "ndcg_at_100": 0.26642, + "ndcg_at_1000": 0.32059, + "map_at_1": 0.05671, + "map_at_3": 0.09468, + "map_at_5": 0.11911, + "map_at_10": 0.1331, + "map_at_20": 0.142, + "map_at_100": 0.15031, + "map_at_1000": 0.15308, + "recall_at_1": 0.05671, + "recall_at_3": 0.14221, + "recall_at_5": 0.2131, + "recall_at_10": 0.28434, + "recall_at_20": 0.37113, + "recall_at_100": 0.56557, + "recall_at_1000": 0.88199, + "precision_at_1": 0.1039, + "precision_at_3": 0.08658, + "precision_at_5": 0.09091, + "precision_at_10": 0.06234, + "precision_at_20": 0.04286, + "precision_at_100": 0.01519, + "precision_at_1000": 0.00257, + "mrr_at_1": 0.103896, + "mrr_at_3": 0.151515, + "mrr_at_5": 0.178788, + "mrr_at_10": 0.190651, + "mrr_at_20": 0.19787, + "mrr_at_100": 0.203325, + "mrr_at_1000": 0.204302, + "nauc_ndcg_at_1_max": 0.627717, + "nauc_ndcg_at_1_std": 0.303669, + "nauc_ndcg_at_1_diff1": 0.375567, + "nauc_ndcg_at_3_max": 0.326655, + "nauc_ndcg_at_3_std": 0.333402, + "nauc_ndcg_at_3_diff1": 0.211835, + "nauc_ndcg_at_5_max": 0.256618, + "nauc_ndcg_at_5_std": 0.271016, + "nauc_ndcg_at_5_diff1": 0.187421, + "nauc_ndcg_at_10_max": 0.264803, + "nauc_ndcg_at_10_std": 0.310172, + "nauc_ndcg_at_10_diff1": 0.171662, + "nauc_ndcg_at_20_max": 0.238175, + "nauc_ndcg_at_20_std": 0.292946, + "nauc_ndcg_at_20_diff1": 0.109598, + "nauc_ndcg_at_100_max": 0.271901, + "nauc_ndcg_at_100_std": 0.327711, + "nauc_ndcg_at_100_diff1": 0.123203, + "nauc_ndcg_at_1000_max": 0.280915, + "nauc_ndcg_at_1000_std": 0.296708, + "nauc_ndcg_at_1000_diff1": 0.131857, + "nauc_map_at_1_max": 0.477375, + "nauc_map_at_1_std": 0.282397, + "nauc_map_at_1_diff1": 0.467255, + "nauc_map_at_3_max": 0.323551, + "nauc_map_at_3_std": 0.327473, + "nauc_map_at_3_diff1": 0.271138, + "nauc_map_at_5_max": 0.302607, + "nauc_map_at_5_std": 0.29522, + "nauc_map_at_5_diff1": 0.259685, + "nauc_map_at_10_max": 0.317145, + "nauc_map_at_10_std": 0.31741, + "nauc_map_at_10_diff1": 0.245643, + "nauc_map_at_20_max": 0.304463, + "nauc_map_at_20_std": 0.315133, + "nauc_map_at_20_diff1": 0.216805, + "nauc_map_at_100_max": 0.312066, + "nauc_map_at_100_std": 0.321564, + "nauc_map_at_100_diff1": 0.216911, + "nauc_map_at_1000_max": 0.313165, + "nauc_map_at_1000_std": 0.320496, + "nauc_map_at_1000_diff1": 0.217479, + "nauc_recall_at_1_max": 0.477375, + "nauc_recall_at_1_std": 0.282397, + "nauc_recall_at_1_diff1": 0.467255, + "nauc_recall_at_3_max": 0.174836, + "nauc_recall_at_3_std": 0.370701, + "nauc_recall_at_3_diff1": 0.082353, + "nauc_recall_at_5_max": 0.118732, + "nauc_recall_at_5_std": 0.289669, + "nauc_recall_at_5_diff1": 0.064173, + "nauc_recall_at_10_max": 0.095687, + "nauc_recall_at_10_std": 0.299739, + "nauc_recall_at_10_diff1": 0.039001, + "nauc_recall_at_20_max": 0.046175, + "nauc_recall_at_20_std": 0.255628, + "nauc_recall_at_20_diff1": -0.08713, + "nauc_recall_at_100_max": 0.128387, + "nauc_recall_at_100_std": 0.378483, + "nauc_recall_at_100_diff1": -0.058987, + "nauc_recall_at_1000_max": 0.061787, + "nauc_recall_at_1000_std": 0.203408, + "nauc_recall_at_1000_diff1": -0.191201, + "nauc_precision_at_1_max": 0.627717, + "nauc_precision_at_1_std": 0.303669, + "nauc_precision_at_1_diff1": 0.375567, + "nauc_precision_at_3_max": 0.312323, + "nauc_precision_at_3_std": 0.306325, + "nauc_precision_at_3_diff1": 0.146241, + "nauc_precision_at_5_max": 0.217625, + "nauc_precision_at_5_std": 0.201983, + "nauc_precision_at_5_diff1": 0.120486, + "nauc_precision_at_10_max": 0.261657, + "nauc_precision_at_10_std": 0.292689, + "nauc_precision_at_10_diff1": 0.097725, + "nauc_precision_at_20_max": 0.189939, + "nauc_precision_at_20_std": 0.223047, + "nauc_precision_at_20_diff1": -0.064008, + "nauc_precision_at_100_max": 0.152139, + "nauc_precision_at_100_std": 0.142336, + "nauc_precision_at_100_diff1": -0.063793, + "nauc_precision_at_1000_max": 0.031915, + "nauc_precision_at_1000_std": -0.061431, + "nauc_precision_at_1000_diff1": -0.116655, + "nauc_mrr_at_1_max": 0.627717, + "nauc_mrr_at_1_std": 0.303669, + "nauc_mrr_at_1_diff1": 0.375567, + "nauc_mrr_at_3_max": 0.44106, + "nauc_mrr_at_3_std": 0.279165, + "nauc_mrr_at_3_diff1": 0.25065, + "nauc_mrr_at_5_max": 0.386498, + "nauc_mrr_at_5_std": 0.251632, + "nauc_mrr_at_5_diff1": 0.208614, + "nauc_mrr_at_10_max": 0.378933, + "nauc_mrr_at_10_std": 0.266722, + "nauc_mrr_at_10_diff1": 0.210996, + "nauc_mrr_at_20_max": 0.373607, + "nauc_mrr_at_20_std": 0.257308, + "nauc_mrr_at_20_diff1": 0.203554, + "nauc_mrr_at_100_max": 0.383135, + "nauc_mrr_at_100_std": 0.26332, + "nauc_mrr_at_100_diff1": 0.208962, + "nauc_mrr_at_1000_max": 0.383227, + "nauc_mrr_at_1000_std": 0.26245, + "nauc_mrr_at_1000_diff1": 0.210074, + "main_score": 0.18908, + "hf_subset": "Bioinformatics", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.17045, + "ndcg_at_3": 0.17539, + "ndcg_at_5": 0.18045, + "ndcg_at_10": 0.2159, + "ndcg_at_20": 0.25046, + "ndcg_at_100": 0.30557, + "ndcg_at_1000": 0.35095, + "map_at_1": 0.07729, + "map_at_3": 0.12847, + "map_at_5": 0.13929, + "map_at_10": 0.15485, + "map_at_20": 0.16696, + "map_at_100": 0.17633, + "map_at_1000": 0.17882, + "recall_at_1": 0.07729, + "recall_at_3": 0.16414, + "recall_at_5": 0.20175, + "recall_at_10": 0.30253, + "recall_at_20": 0.41668, + "recall_at_100": 0.64831, + "recall_at_1000": 0.90606, + "precision_at_1": 0.17045, + "precision_at_3": 0.12121, + "precision_at_5": 0.08636, + "precision_at_10": 0.06591, + "precision_at_20": 0.04545, + "precision_at_100": 0.01534, + "precision_at_1000": 0.00241, + "mrr_at_1": 0.170455, + "mrr_at_3": 0.229167, + "mrr_at_5": 0.238826, + "mrr_at_10": 0.25593, + "mrr_at_20": 0.263252, + "mrr_at_100": 0.268471, + "mrr_at_1000": 0.26911, + "nauc_ndcg_at_1_max": 0.31708, + "nauc_ndcg_at_1_std": 0.065165, + "nauc_ndcg_at_1_diff1": 0.405074, + "nauc_ndcg_at_3_max": 0.327964, + "nauc_ndcg_at_3_std": 0.130697, + "nauc_ndcg_at_3_diff1": 0.43022, + "nauc_ndcg_at_5_max": 0.303319, + "nauc_ndcg_at_5_std": 0.11743, + "nauc_ndcg_at_5_diff1": 0.408974, + "nauc_ndcg_at_10_max": 0.298958, + "nauc_ndcg_at_10_std": 0.15254, + "nauc_ndcg_at_10_diff1": 0.368523, + "nauc_ndcg_at_20_max": 0.306033, + "nauc_ndcg_at_20_std": 0.145715, + "nauc_ndcg_at_20_diff1": 0.370348, + "nauc_ndcg_at_100_max": 0.334591, + "nauc_ndcg_at_100_std": 0.213273, + "nauc_ndcg_at_100_diff1": 0.384715, + "nauc_ndcg_at_1000_max": 0.323012, + "nauc_ndcg_at_1000_std": 0.196291, + "nauc_ndcg_at_1000_diff1": 0.381515, + "nauc_map_at_1_max": 0.15639, + "nauc_map_at_1_std": -0.038297, + "nauc_map_at_1_diff1": 0.30408, + "nauc_map_at_3_max": 0.305307, + "nauc_map_at_3_std": 0.09303, + "nauc_map_at_3_diff1": 0.404479, + "nauc_map_at_5_max": 0.30364, + "nauc_map_at_5_std": 0.093055, + "nauc_map_at_5_diff1": 0.401791, + "nauc_map_at_10_max": 0.303246, + "nauc_map_at_10_std": 0.110755, + "nauc_map_at_10_diff1": 0.387663, + "nauc_map_at_20_max": 0.317913, + "nauc_map_at_20_std": 0.12819, + "nauc_map_at_20_diff1": 0.398748, + "nauc_map_at_100_max": 0.326991, + "nauc_map_at_100_std": 0.140511, + "nauc_map_at_100_diff1": 0.399563, + "nauc_map_at_1000_max": 0.327137, + "nauc_map_at_1000_std": 0.139963, + "nauc_map_at_1000_diff1": 0.400514, + "nauc_recall_at_1_max": 0.15639, + "nauc_recall_at_1_std": -0.038297, + "nauc_recall_at_1_diff1": 0.30408, + "nauc_recall_at_3_max": 0.27415, + "nauc_recall_at_3_std": 0.108985, + "nauc_recall_at_3_diff1": 0.388616, + "nauc_recall_at_5_max": 0.210955, + "nauc_recall_at_5_std": 0.101036, + "nauc_recall_at_5_diff1": 0.344814, + "nauc_recall_at_10_max": 0.173582, + "nauc_recall_at_10_std": 0.130499, + "nauc_recall_at_10_diff1": 0.240241, + "nauc_recall_at_20_max": 0.177163, + "nauc_recall_at_20_std": 0.071243, + "nauc_recall_at_20_diff1": 0.220802, + "nauc_recall_at_100_max": 0.171795, + "nauc_recall_at_100_std": 0.281705, + "nauc_recall_at_100_diff1": 0.238579, + "nauc_recall_at_1000_max": -0.304432, + "nauc_recall_at_1000_std": 0.24231, + "nauc_recall_at_1000_diff1": 0.008093, + "nauc_precision_at_1_max": 0.31708, + "nauc_precision_at_1_std": 0.065165, + "nauc_precision_at_1_diff1": 0.405074, + "nauc_precision_at_3_max": 0.476783, + "nauc_precision_at_3_std": 0.255966, + "nauc_precision_at_3_diff1": 0.499911, + "nauc_precision_at_5_max": 0.46571, + "nauc_precision_at_5_std": 0.246567, + "nauc_precision_at_5_diff1": 0.487925, + "nauc_precision_at_10_max": 0.432444, + "nauc_precision_at_10_std": 0.340083, + "nauc_precision_at_10_diff1": 0.370474, + "nauc_precision_at_20_max": 0.417451, + "nauc_precision_at_20_std": 0.346824, + "nauc_precision_at_20_diff1": 0.39034, + "nauc_precision_at_100_max": 0.456264, + "nauc_precision_at_100_std": 0.448456, + "nauc_precision_at_100_diff1": 0.297295, + "nauc_precision_at_1000_max": 0.260005, + "nauc_precision_at_1000_std": 0.227846, + "nauc_precision_at_1000_diff1": 0.123616, + "nauc_mrr_at_1_max": 0.31708, + "nauc_mrr_at_1_std": 0.065165, + "nauc_mrr_at_1_diff1": 0.405074, + "nauc_mrr_at_3_max": 0.33048, + "nauc_mrr_at_3_std": 0.114578, + "nauc_mrr_at_3_diff1": 0.415839, + "nauc_mrr_at_5_max": 0.316684, + "nauc_mrr_at_5_std": 0.106859, + "nauc_mrr_at_5_diff1": 0.40667, + "nauc_mrr_at_10_max": 0.324608, + "nauc_mrr_at_10_std": 0.140124, + "nauc_mrr_at_10_diff1": 0.392316, + "nauc_mrr_at_20_max": 0.320493, + "nauc_mrr_at_20_std": 0.126871, + "nauc_mrr_at_20_diff1": 0.388278, + "nauc_mrr_at_100_max": 0.321067, + "nauc_mrr_at_100_std": 0.132065, + "nauc_mrr_at_100_diff1": 0.391672, + "nauc_mrr_at_1000_max": 0.320632, + "nauc_mrr_at_1000_std": 0.131615, + "nauc_mrr_at_1000_diff1": 0.391343, + "main_score": 0.2159, + "hf_subset": "Medical-Sciences", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.0, + "ndcg_at_3": 0.00621, + "ndcg_at_5": 0.00537, + "ndcg_at_10": 0.00677, + "ndcg_at_20": 0.0131, + "ndcg_at_100": 0.03119, + "ndcg_at_1000": 0.06839, + "map_at_1": 0.0, + "map_at_3": 0.00275, + "map_at_5": 0.00275, + "map_at_10": 0.00309, + "map_at_20": 0.00443, + "map_at_100": 0.00643, + "map_at_1000": 0.00753, + "recall_at_1": 0.0, + "recall_at_3": 0.00722, + "recall_at_5": 0.00722, + "recall_at_10": 0.01065, + "recall_at_20": 0.02646, + "recall_at_100": 0.11254, + "recall_at_1000": 0.35063, + "precision_at_1": 0.0, + "precision_at_3": 0.00687, + "precision_at_5": 0.00412, + "precision_at_10": 0.00309, + "precision_at_20": 0.00464, + "precision_at_100": 0.00268, + "precision_at_1000": 0.00092, + "mrr_at_1": 0.0, + "mrr_at_3": 0.008591, + "mrr_at_5": 0.008591, + "mrr_at_10": 0.009622, + "mrr_at_20": 0.013684, + "mrr_at_100": 0.016361, + "mrr_at_1000": 0.017591, + "nauc_ndcg_at_1_max": NaN, + "nauc_ndcg_at_1_std": NaN, + "nauc_ndcg_at_1_diff1": NaN, + "nauc_ndcg_at_3_max": -0.23441, + "nauc_ndcg_at_3_std": 0.262292, + "nauc_ndcg_at_3_diff1": 0.473236, + "nauc_ndcg_at_5_max": -0.180338, + "nauc_ndcg_at_5_std": 0.382756, + "nauc_ndcg_at_5_diff1": 0.559254, + "nauc_ndcg_at_10_max": 0.063661, + "nauc_ndcg_at_10_std": 0.442262, + "nauc_ndcg_at_10_diff1": 0.510599, + "nauc_ndcg_at_20_max": 0.110257, + "nauc_ndcg_at_20_std": 0.195975, + "nauc_ndcg_at_20_diff1": 0.373455, + "nauc_ndcg_at_100_max": 0.032992, + "nauc_ndcg_at_100_std": 0.160351, + "nauc_ndcg_at_100_diff1": 0.137738, + "nauc_ndcg_at_1000_max": 0.030661, + "nauc_ndcg_at_1000_std": 0.141355, + "nauc_ndcg_at_1000_diff1": 0.191488, + "nauc_map_at_1_max": NaN, + "nauc_map_at_1_std": NaN, + "nauc_map_at_1_diff1": NaN, + "nauc_map_at_3_max": -0.156027, + "nauc_map_at_3_std": 0.436916, + "nauc_map_at_3_diff1": 0.597928, + "nauc_map_at_5_max": -0.156027, + "nauc_map_at_5_std": 0.436916, + "nauc_map_at_5_diff1": 0.597928, + "nauc_map_at_10_max": -0.027579, + "nauc_map_at_10_std": 0.462883, + "nauc_map_at_10_diff1": 0.567479, + "nauc_map_at_20_max": 0.020158, + "nauc_map_at_20_std": 0.289368, + "nauc_map_at_20_diff1": 0.482783, + "nauc_map_at_100_max": 0.018675, + "nauc_map_at_100_std": 0.282257, + "nauc_map_at_100_diff1": 0.3279, + "nauc_map_at_1000_max": 0.019838, + "nauc_map_at_1000_std": 0.268734, + "nauc_map_at_1000_diff1": 0.328954, + "nauc_recall_at_1_max": NaN, + "nauc_recall_at_1_std": NaN, + "nauc_recall_at_1_diff1": NaN, + "nauc_recall_at_3_max": -0.095848, + "nauc_recall_at_3_std": 0.570984, + "nauc_recall_at_3_diff1": 0.693659, + "nauc_recall_at_5_max": -0.095848, + "nauc_recall_at_5_std": 0.570984, + "nauc_recall_at_5_diff1": 0.693659, + "nauc_recall_at_10_max": 0.257651, + "nauc_recall_at_10_std": 0.603122, + "nauc_recall_at_10_diff1": 0.574378, + "nauc_recall_at_20_max": 0.200512, + "nauc_recall_at_20_std": 0.18306, + "nauc_recall_at_20_diff1": 0.378952, + "nauc_recall_at_100_max": 0.006052, + "nauc_recall_at_100_std": 0.140657, + "nauc_recall_at_100_diff1": 0.016399, + "nauc_recall_at_1000_max": -0.020041, + "nauc_recall_at_1000_std": 0.12899, + "nauc_recall_at_1000_diff1": 0.105312, + "nauc_precision_at_1_max": NaN, + "nauc_precision_at_1_std": NaN, + "nauc_precision_at_1_diff1": NaN, + "nauc_precision_at_3_max": -0.240277, + "nauc_precision_at_3_std": 0.249222, + "nauc_precision_at_3_diff1": 0.463903, + "nauc_precision_at_5_max": -0.240277, + "nauc_precision_at_5_std": 0.249222, + "nauc_precision_at_5_diff1": 0.463903, + "nauc_precision_at_10_max": 0.173149, + "nauc_precision_at_10_std": 0.389685, + "nauc_precision_at_10_diff1": 0.417232, + "nauc_precision_at_20_max": 0.18291, + "nauc_precision_at_20_std": 0.127146, + "nauc_precision_at_20_diff1": 0.270351, + "nauc_precision_at_100_max": 0.069557, + "nauc_precision_at_100_std": 0.044225, + "nauc_precision_at_100_diff1": 0.11693, + "nauc_precision_at_1000_max": 0.103897, + "nauc_precision_at_1000_std": 0.033687, + "nauc_precision_at_1000_diff1": 0.199612, + "nauc_mrr_at_1_max": NaN, + "nauc_mrr_at_1_std": NaN, + "nauc_mrr_at_1_diff1": NaN, + "nauc_mrr_at_3_max": -0.307677, + "nauc_mrr_at_3_std": 0.099066, + "nauc_mrr_at_3_diff1": 0.356684, + "nauc_mrr_at_5_max": -0.307677, + "nauc_mrr_at_5_std": 0.099066, + "nauc_mrr_at_5_diff1": 0.356684, + "nauc_mrr_at_10_max": -0.167569, + "nauc_mrr_at_10_std": 0.160303, + "nauc_mrr_at_10_diff1": 0.35317, + "nauc_mrr_at_20_max": -0.068978, + "nauc_mrr_at_20_std": 0.119996, + "nauc_mrr_at_20_diff1": 0.281581, + "nauc_mrr_at_100_max": -0.051062, + "nauc_mrr_at_100_std": 0.125501, + "nauc_mrr_at_100_diff1": 0.256271, + "nauc_mrr_at_1000_max": -0.048021, + "nauc_mrr_at_1000_std": 0.121803, + "nauc_mrr_at_1000_diff1": 0.262036, + "main_score": 0.00677, + "hf_subset": "MedXpertQA-Exam", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.02542, + "ndcg_at_3": 0.02525, + "ndcg_at_5": 0.02551, + "ndcg_at_10": 0.03986, + "ndcg_at_20": 0.04689, + "ndcg_at_100": 0.0632, + "ndcg_at_1000": 0.1048, + "map_at_1": 0.00593, + "map_at_3": 0.01345, + "map_at_5": 0.01684, + "map_at_10": 0.02388, + "map_at_20": 0.02628, + "map_at_100": 0.02859, + "map_at_1000": 0.03008, + "recall_at_1": 0.00593, + "recall_at_3": 0.01716, + "recall_at_5": 0.02564, + "recall_at_10": 0.05819, + "recall_at_20": 0.07663, + "recall_at_100": 0.13471, + "recall_at_1000": 0.35799, + "precision_at_1": 0.02542, + "precision_at_3": 0.0226, + "precision_at_5": 0.01864, + "precision_at_10": 0.01949, + "precision_at_20": 0.01356, + "precision_at_100": 0.00508, + "precision_at_1000": 0.00147, + "mrr_at_1": 0.025424, + "mrr_at_3": 0.038136, + "mrr_at_5": 0.040254, + "mrr_at_10": 0.048147, + "mrr_at_20": 0.051199, + "mrr_at_100": 0.05409, + "mrr_at_1000": 0.055495, + "nauc_ndcg_at_1_max": -0.315641, + "nauc_ndcg_at_1_std": 0.776529, + "nauc_ndcg_at_1_diff1": 0.419383, + "nauc_ndcg_at_3_max": -0.366277, + "nauc_ndcg_at_3_std": 0.719558, + "nauc_ndcg_at_3_diff1": 0.345964, + "nauc_ndcg_at_5_max": -0.379433, + "nauc_ndcg_at_5_std": 0.717288, + "nauc_ndcg_at_5_diff1": 0.263523, + "nauc_ndcg_at_10_max": -0.375535, + "nauc_ndcg_at_10_std": 0.602015, + "nauc_ndcg_at_10_diff1": 0.129358, + "nauc_ndcg_at_20_max": -0.334061, + "nauc_ndcg_at_20_std": 0.574679, + "nauc_ndcg_at_20_diff1": 0.120157, + "nauc_ndcg_at_100_max": -0.30412, + "nauc_ndcg_at_100_std": 0.552435, + "nauc_ndcg_at_100_diff1": 0.093504, + "nauc_ndcg_at_1000_max": -0.298588, + "nauc_ndcg_at_1000_std": 0.483579, + "nauc_ndcg_at_1000_diff1": 0.045532, + "nauc_map_at_1_max": -0.308328, + "nauc_map_at_1_std": 0.760567, + "nauc_map_at_1_diff1": 0.377911, + "nauc_map_at_3_max": -0.348752, + "nauc_map_at_3_std": 0.789623, + "nauc_map_at_3_diff1": 0.413029, + "nauc_map_at_5_max": -0.359439, + "nauc_map_at_5_std": 0.789799, + "nauc_map_at_5_diff1": 0.307425, + "nauc_map_at_10_max": -0.362121, + "nauc_map_at_10_std": 0.708817, + "nauc_map_at_10_diff1": 0.21065, + "nauc_map_at_20_max": -0.348361, + "nauc_map_at_20_std": 0.688942, + "nauc_map_at_20_diff1": 0.196766, + "nauc_map_at_100_max": -0.347468, + "nauc_map_at_100_std": 0.672905, + "nauc_map_at_100_diff1": 0.186951, + "nauc_map_at_1000_max": -0.347641, + "nauc_map_at_1000_std": 0.663329, + "nauc_map_at_1000_diff1": 0.179125, + "nauc_recall_at_1_max": -0.308328, + "nauc_recall_at_1_std": 0.760567, + "nauc_recall_at_1_diff1": 0.377911, + "nauc_recall_at_3_max": -0.373286, + "nauc_recall_at_3_std": 0.752917, + "nauc_recall_at_3_diff1": 0.377497, + "nauc_recall_at_5_max": -0.398747, + "nauc_recall_at_5_std": 0.723785, + "nauc_recall_at_5_diff1": 0.234843, + "nauc_recall_at_10_max": -0.401648, + "nauc_recall_at_10_std": 0.487953, + "nauc_recall_at_10_diff1": 0.002734, + "nauc_recall_at_20_max": -0.330112, + "nauc_recall_at_20_std": 0.45734, + "nauc_recall_at_20_diff1": 0.005828, + "nauc_recall_at_100_max": -0.274751, + "nauc_recall_at_100_std": 0.453597, + "nauc_recall_at_100_diff1": -0.002974, + "nauc_recall_at_1000_max": -0.248013, + "nauc_recall_at_1000_std": 0.324935, + "nauc_recall_at_1000_diff1": -0.077184, + "nauc_precision_at_1_max": -0.315641, + "nauc_precision_at_1_std": 0.776529, + "nauc_precision_at_1_diff1": 0.419383, + "nauc_precision_at_3_max": -0.372121, + "nauc_precision_at_3_std": 0.70916, + "nauc_precision_at_3_diff1": 0.317641, + "nauc_precision_at_5_max": -0.381698, + "nauc_precision_at_5_std": 0.727533, + "nauc_precision_at_5_diff1": 0.202297, + "nauc_precision_at_10_max": -0.347757, + "nauc_precision_at_10_std": 0.598951, + "nauc_precision_at_10_diff1": 0.066253, + "nauc_precision_at_20_max": -0.261227, + "nauc_precision_at_20_std": 0.546921, + "nauc_precision_at_20_diff1": 0.07404, + "nauc_precision_at_100_max": -0.194217, + "nauc_precision_at_100_std": 0.5019, + "nauc_precision_at_100_diff1": 0.038605, + "nauc_precision_at_1000_max": -0.166839, + "nauc_precision_at_1000_std": 0.286289, + "nauc_precision_at_1000_diff1": -0.018004, + "nauc_mrr_at_1_max": -0.315641, + "nauc_mrr_at_1_std": 0.776529, + "nauc_mrr_at_1_diff1": 0.419383, + "nauc_mrr_at_3_max": -0.366452, + "nauc_mrr_at_3_std": 0.666985, + "nauc_mrr_at_3_diff1": 0.27441, + "nauc_mrr_at_5_max": -0.377666, + "nauc_mrr_at_5_std": 0.649227, + "nauc_mrr_at_5_diff1": 0.265216, + "nauc_mrr_at_10_max": -0.370951, + "nauc_mrr_at_10_std": 0.586884, + "nauc_mrr_at_10_diff1": 0.186991, + "nauc_mrr_at_20_max": -0.343864, + "nauc_mrr_at_20_std": 0.57437, + "nauc_mrr_at_20_diff1": 0.186524, + "nauc_mrr_at_100_max": -0.33584, + "nauc_mrr_at_100_std": 0.570417, + "nauc_mrr_at_100_diff1": 0.183984, + "nauc_mrr_at_1000_max": -0.338874, + "nauc_mrr_at_1000_std": 0.56787, + "nauc_mrr_at_1000_diff1": 0.180159, + "main_score": 0.03986, + "hf_subset": "MedQA-Diag", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.0, + "ndcg_at_3": 0.00679, + "ndcg_at_5": 0.00679, + "ndcg_at_10": 0.00815, + "ndcg_at_20": 0.01831, + "ndcg_at_100": 0.04028, + "ndcg_at_1000": 0.09594, + "map_at_1": 0.0, + "map_at_3": 0.005, + "map_at_5": 0.005, + "map_at_10": 0.00548, + "map_at_20": 0.00839, + "map_at_100": 0.01103, + "map_at_1000": 0.01268, + "recall_at_1": 0.0, + "recall_at_3": 0.01, + "recall_at_5": 0.01, + "recall_at_10": 0.01333, + "recall_at_20": 0.04611, + "recall_at_100": 0.14256, + "recall_at_1000": 0.53311, + "precision_at_1": 0.0, + "precision_at_3": 0.00444, + "precision_at_5": 0.00267, + "precision_at_10": 0.002, + "precision_at_20": 0.004, + "precision_at_100": 0.00307, + "precision_at_1000": 0.00113, + "mrr_at_1": 0.0, + "mrr_at_3": 0.006667, + "mrr_at_5": 0.006667, + "mrr_at_10": 0.007619, + "mrr_at_20": 0.011538, + "mrr_at_100": 0.015788, + "mrr_at_1000": 0.017257, + "nauc_ndcg_at_1_max": NaN, + "nauc_ndcg_at_1_std": NaN, + "nauc_ndcg_at_1_diff1": NaN, + "nauc_ndcg_at_3_max": 0.079704, + "nauc_ndcg_at_3_std": -0.121966, + "nauc_ndcg_at_3_diff1": 0.010865, + "nauc_ndcg_at_5_max": 0.079704, + "nauc_ndcg_at_5_std": -0.121966, + "nauc_ndcg_at_5_diff1": 0.010865, + "nauc_ndcg_at_10_max": -0.003039, + "nauc_ndcg_at_10_std": -0.15483, + "nauc_ndcg_at_10_diff1": -0.025367, + "nauc_ndcg_at_20_max": -0.179927, + "nauc_ndcg_at_20_std": -0.182187, + "nauc_ndcg_at_20_diff1": -0.184792, + "nauc_ndcg_at_100_max": -0.218944, + "nauc_ndcg_at_100_std": -0.197275, + "nauc_ndcg_at_100_diff1": -0.091777, + "nauc_ndcg_at_1000_max": -0.2471, + "nauc_ndcg_at_1000_std": -0.161713, + "nauc_ndcg_at_1000_diff1": -0.082099, + "nauc_map_at_1_max": NaN, + "nauc_map_at_1_std": NaN, + "nauc_map_at_1_diff1": NaN, + "nauc_map_at_3_max": 0.10974, + "nauc_map_at_3_std": -0.115643, + "nauc_map_at_3_diff1": 0.049369, + "nauc_map_at_5_max": 0.10974, + "nauc_map_at_5_std": -0.115643, + "nauc_map_at_5_diff1": 0.049369, + "nauc_map_at_10_max": 0.064103, + "nauc_map_at_10_std": -0.133281, + "nauc_map_at_10_diff1": 0.027181, + "nauc_map_at_20_max": -0.08256, + "nauc_map_at_20_std": -0.174873, + "nauc_map_at_20_diff1": -0.106571, + "nauc_map_at_100_max": -0.110279, + "nauc_map_at_100_std": -0.168166, + "nauc_map_at_100_diff1": -0.093414, + "nauc_map_at_1000_max": -0.111225, + "nauc_map_at_1000_std": -0.167787, + "nauc_map_at_1000_diff1": -0.090164, + "nauc_recall_at_1_max": NaN, + "nauc_recall_at_1_std": NaN, + "nauc_recall_at_1_diff1": NaN, + "nauc_recall_at_3_max": 0.10974, + "nauc_recall_at_3_std": -0.115643, + "nauc_recall_at_3_diff1": 0.049369, + "nauc_recall_at_5_max": 0.10974, + "nauc_recall_at_5_std": -0.115643, + "nauc_recall_at_5_diff1": 0.049369, + "nauc_recall_at_10_max": -0.021465, + "nauc_recall_at_10_std": -0.166354, + "nauc_recall_at_10_diff1": -0.014422, + "nauc_recall_at_20_max": -0.248157, + "nauc_recall_at_20_std": -0.202615, + "nauc_recall_at_20_diff1": -0.234201, + "nauc_recall_at_100_max": -0.262607, + "nauc_recall_at_100_std": -0.198, + "nauc_recall_at_100_diff1": -0.065473, + "nauc_recall_at_1000_max": -0.279255, + "nauc_recall_at_1000_std": -0.093231, + "nauc_recall_at_1000_diff1": -0.05497, + "nauc_precision_at_1_max": NaN, + "nauc_precision_at_1_std": NaN, + "nauc_precision_at_1_diff1": NaN, + "nauc_precision_at_3_max": 0.002683, + "nauc_precision_at_3_std": -0.138181, + "nauc_precision_at_3_diff1": -0.087872, + "nauc_precision_at_5_max": 0.002683, + "nauc_precision_at_5_std": -0.138181, + "nauc_precision_at_5_diff1": -0.087872, + "nauc_precision_at_10_max": -0.136571, + "nauc_precision_at_10_std": -0.198283, + "nauc_precision_at_10_diff1": -0.12718, + "nauc_precision_at_20_max": -0.219278, + "nauc_precision_at_20_std": -0.135095, + "nauc_precision_at_20_diff1": -0.235153, + "nauc_precision_at_100_max": -0.224585, + "nauc_precision_at_100_std": -0.193788, + "nauc_precision_at_100_diff1": -0.094507, + "nauc_precision_at_1000_max": -0.233871, + "nauc_precision_at_1000_std": -0.115073, + "nauc_precision_at_1000_diff1": -0.075662, + "nauc_mrr_at_1_max": NaN, + "nauc_mrr_at_1_std": NaN, + "nauc_mrr_at_1_diff1": NaN, + "nauc_mrr_at_3_max": 0.002683, + "nauc_mrr_at_3_std": -0.138181, + "nauc_mrr_at_3_diff1": -0.087872, + "nauc_mrr_at_5_max": 0.002683, + "nauc_mrr_at_5_std": -0.138181, + "nauc_mrr_at_5_diff1": -0.087872, + "nauc_mrr_at_10_max": -0.049537, + "nauc_mrr_at_10_std": -0.160719, + "nauc_mrr_at_10_diff1": -0.102613, + "nauc_mrr_at_20_max": -0.125029, + "nauc_mrr_at_20_std": -0.163896, + "nauc_mrr_at_20_diff1": -0.153743, + "nauc_mrr_at_100_max": -0.16669, + "nauc_mrr_at_100_std": -0.205252, + "nauc_mrr_at_100_diff1": -0.11308, + "nauc_mrr_at_1000_max": -0.162496, + "nauc_mrr_at_1000_std": -0.205747, + "nauc_mrr_at_1000_diff1": -0.109774, + "main_score": 0.00815, + "hf_subset": "PMC-Treatment", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.10526, + "ndcg_at_3": 0.08697, + "ndcg_at_5": 0.1057, + "ndcg_at_10": 0.13341, + "ndcg_at_20": 0.15165, + "ndcg_at_100": 0.18926, + "ndcg_at_1000": 0.23908, + "map_at_1": 0.04386, + "map_at_3": 0.0636, + "map_at_5": 0.07405, + "map_at_10": 0.08616, + "map_at_20": 0.09162, + "map_at_100": 0.09812, + "map_at_1000": 0.10017, + "recall_at_1": 0.04386, + "recall_at_3": 0.0848, + "recall_at_5": 0.12646, + "recall_at_10": 0.19518, + "recall_at_20": 0.25512, + "recall_at_100": 0.41155, + "recall_at_1000": 0.74269, + "precision_at_1": 0.10526, + "precision_at_3": 0.05848, + "precision_at_5": 0.05088, + "precision_at_10": 0.04123, + "precision_at_20": 0.02719, + "precision_at_100": 0.00904, + "precision_at_1000": 0.00161, + "mrr_at_1": 0.105263, + "mrr_at_3": 0.138889, + "mrr_at_5": 0.152485, + "mrr_at_10": 0.165299, + "mrr_at_20": 0.16985, + "mrr_at_100": 0.174817, + "mrr_at_1000": 0.176075, + "nauc_ndcg_at_1_max": -0.041032, + "nauc_ndcg_at_1_std": -0.007044, + "nauc_ndcg_at_1_diff1": 0.348895, + "nauc_ndcg_at_3_max": -0.12244, + "nauc_ndcg_at_3_std": -0.072535, + "nauc_ndcg_at_3_diff1": 0.327792, + "nauc_ndcg_at_5_max": -0.069766, + "nauc_ndcg_at_5_std": -0.056464, + "nauc_ndcg_at_5_diff1": 0.337758, + "nauc_ndcg_at_10_max": -0.008262, + "nauc_ndcg_at_10_std": -0.032423, + "nauc_ndcg_at_10_diff1": 0.32996, + "nauc_ndcg_at_20_max": 0.023658, + "nauc_ndcg_at_20_std": -0.033967, + "nauc_ndcg_at_20_diff1": 0.343655, + "nauc_ndcg_at_100_max": -0.00573, + "nauc_ndcg_at_100_std": 0.045892, + "nauc_ndcg_at_100_diff1": 0.294375, + "nauc_ndcg_at_1000_max": -0.018195, + "nauc_ndcg_at_1000_std": 0.030856, + "nauc_ndcg_at_1000_diff1": 0.29507, + "nauc_map_at_1_max": -0.090946, + "nauc_map_at_1_std": -0.055799, + "nauc_map_at_1_diff1": 0.263009, + "nauc_map_at_3_max": -0.140615, + "nauc_map_at_3_std": -0.08282, + "nauc_map_at_3_diff1": 0.29654, + "nauc_map_at_5_max": -0.089233, + "nauc_map_at_5_std": -0.069089, + "nauc_map_at_5_diff1": 0.324684, + "nauc_map_at_10_max": -0.046981, + "nauc_map_at_10_std": -0.062124, + "nauc_map_at_10_diff1": 0.325055, + "nauc_map_at_20_max": -0.028799, + "nauc_map_at_20_std": -0.059344, + "nauc_map_at_20_diff1": 0.330206, + "nauc_map_at_100_max": -0.031931, + "nauc_map_at_100_std": -0.040064, + "nauc_map_at_100_diff1": 0.318651, + "nauc_map_at_1000_max": -0.032891, + "nauc_map_at_1000_std": -0.039953, + "nauc_map_at_1000_diff1": 0.319753, + "nauc_recall_at_1_max": -0.090946, + "nauc_recall_at_1_std": -0.055799, + "nauc_recall_at_1_diff1": 0.263009, + "nauc_recall_at_3_max": -0.170859, + "nauc_recall_at_3_std": -0.094269, + "nauc_recall_at_3_diff1": 0.286054, + "nauc_recall_at_5_max": -0.042088, + "nauc_recall_at_5_std": -0.049402, + "nauc_recall_at_5_diff1": 0.323449, + "nauc_recall_at_10_max": 0.064468, + "nauc_recall_at_10_std": -0.003743, + "nauc_recall_at_10_diff1": 0.300245, + "nauc_recall_at_20_max": 0.123059, + "nauc_recall_at_20_std": -0.01353, + "nauc_recall_at_20_diff1": 0.335687, + "nauc_recall_at_100_max": 0.0198, + "nauc_recall_at_100_std": 0.189512, + "nauc_recall_at_100_diff1": 0.1891, + "nauc_recall_at_1000_max": -0.079526, + "nauc_recall_at_1000_std": 0.176607, + "nauc_recall_at_1000_diff1": 0.102298, + "nauc_precision_at_1_max": -0.041032, + "nauc_precision_at_1_std": -0.007044, + "nauc_precision_at_1_diff1": 0.348895, + "nauc_precision_at_3_max": -0.108644, + "nauc_precision_at_3_std": -0.078123, + "nauc_precision_at_3_diff1": 0.3477, + "nauc_precision_at_5_max": -0.036784, + "nauc_precision_at_5_std": -0.04188, + "nauc_precision_at_5_diff1": 0.363794, + "nauc_precision_at_10_max": 0.082672, + "nauc_precision_at_10_std": -0.002988, + "nauc_precision_at_10_diff1": 0.352652, + "nauc_precision_at_20_max": 0.130431, + "nauc_precision_at_20_std": -0.002628, + "nauc_precision_at_20_diff1": 0.336316, + "nauc_precision_at_100_max": 0.060434, + "nauc_precision_at_100_std": 0.17004, + "nauc_precision_at_100_diff1": 0.179298, + "nauc_precision_at_1000_max": 0.056213, + "nauc_precision_at_1000_std": 0.078092, + "nauc_precision_at_1000_diff1": 0.112955, + "nauc_mrr_at_1_max": -0.041032, + "nauc_mrr_at_1_std": -0.007044, + "nauc_mrr_at_1_diff1": 0.348895, + "nauc_mrr_at_3_max": -0.074947, + "nauc_mrr_at_3_std": -0.048648, + "nauc_mrr_at_3_diff1": 0.357568, + "nauc_mrr_at_5_max": -0.066205, + "nauc_mrr_at_5_std": -0.041549, + "nauc_mrr_at_5_diff1": 0.347477, + "nauc_mrr_at_10_max": -0.046695, + "nauc_mrr_at_10_std": -0.02095, + "nauc_mrr_at_10_diff1": 0.34123, + "nauc_mrr_at_20_max": -0.042978, + "nauc_mrr_at_20_std": -0.027832, + "nauc_mrr_at_20_diff1": 0.345998, + "nauc_mrr_at_100_max": -0.047826, + "nauc_mrr_at_100_std": -0.019071, + "nauc_mrr_at_100_diff1": 0.338904, + "nauc_mrr_at_1000_max": -0.048031, + "nauc_mrr_at_1000_std": -0.0191, + "nauc_mrr_at_1000_diff1": 0.33949, + "main_score": 0.13341, + "hf_subset": "PMC-Clinical", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.08527, + "ndcg_at_3": 0.06733, + "ndcg_at_5": 0.07178, + "ndcg_at_10": 0.08555, + "ndcg_at_20": 0.095, + "ndcg_at_100": 0.1406, + "ndcg_at_1000": 0.2125, + "map_at_1": 0.02545, + "map_at_3": 0.03811, + "map_at_5": 0.04448, + "map_at_10": 0.04936, + "map_at_20": 0.05203, + "map_at_100": 0.05848, + "map_at_1000": 0.06205, + "recall_at_1": 0.02545, + "recall_at_3": 0.04948, + "recall_at_5": 0.07041, + "recall_at_10": 0.1022, + "recall_at_20": 0.13062, + "recall_at_100": 0.30181, + "recall_at_1000": 0.70142, + "precision_at_1": 0.08527, + "precision_at_3": 0.05943, + "precision_at_5": 0.04961, + "precision_at_10": 0.03643, + "precision_at_20": 0.02248, + "precision_at_100": 0.01085, + "precision_at_1000": 0.00253, + "mrr_at_1": 0.085271, + "mrr_at_3": 0.118863, + "mrr_at_5": 0.129716, + "mrr_at_10": 0.139627, + "mrr_at_20": 0.142143, + "mrr_at_100": 0.148429, + "mrr_at_1000": 0.149748, + "nauc_ndcg_at_1_max": 0.15867, + "nauc_ndcg_at_1_std": 0.254745, + "nauc_ndcg_at_1_diff1": 0.113002, + "nauc_ndcg_at_3_max": 0.206189, + "nauc_ndcg_at_3_std": 0.272201, + "nauc_ndcg_at_3_diff1": 0.133345, + "nauc_ndcg_at_5_max": 0.257141, + "nauc_ndcg_at_5_std": 0.247749, + "nauc_ndcg_at_5_diff1": 0.067346, + "nauc_ndcg_at_10_max": 0.243432, + "nauc_ndcg_at_10_std": 0.221585, + "nauc_ndcg_at_10_diff1": 0.041621, + "nauc_ndcg_at_20_max": 0.239112, + "nauc_ndcg_at_20_std": 0.236709, + "nauc_ndcg_at_20_diff1": 0.043664, + "nauc_ndcg_at_100_max": 0.266528, + "nauc_ndcg_at_100_std": 0.257662, + "nauc_ndcg_at_100_diff1": 0.051517, + "nauc_ndcg_at_1000_max": 0.283148, + "nauc_ndcg_at_1000_std": 0.32464, + "nauc_ndcg_at_1000_diff1": 0.046663, + "nauc_map_at_1_max": 0.154494, + "nauc_map_at_1_std": 0.249574, + "nauc_map_at_1_diff1": 0.190231, + "nauc_map_at_3_max": 0.196107, + "nauc_map_at_3_std": 0.279239, + "nauc_map_at_3_diff1": 0.132714, + "nauc_map_at_5_max": 0.253857, + "nauc_map_at_5_std": 0.269455, + "nauc_map_at_5_diff1": 0.068762, + "nauc_map_at_10_max": 0.247467, + "nauc_map_at_10_std": 0.247794, + "nauc_map_at_10_diff1": 0.058364, + "nauc_map_at_20_max": 0.251249, + "nauc_map_at_20_std": 0.255984, + "nauc_map_at_20_diff1": 0.055624, + "nauc_map_at_100_max": 0.253238, + "nauc_map_at_100_std": 0.255182, + "nauc_map_at_100_diff1": 0.064327, + "nauc_map_at_1000_max": 0.255024, + "nauc_map_at_1000_std": 0.264155, + "nauc_map_at_1000_diff1": 0.0622, + "nauc_recall_at_1_max": 0.154494, + "nauc_recall_at_1_std": 0.249574, + "nauc_recall_at_1_diff1": 0.190231, + "nauc_recall_at_3_max": 0.199179, + "nauc_recall_at_3_std": 0.267391, + "nauc_recall_at_3_diff1": 0.138475, + "nauc_recall_at_5_max": 0.300965, + "nauc_recall_at_5_std": 0.217638, + "nauc_recall_at_5_diff1": 0.003929, + "nauc_recall_at_10_max": 0.211695, + "nauc_recall_at_10_std": 0.13265, + "nauc_recall_at_10_diff1": -0.043325, + "nauc_recall_at_20_max": 0.182498, + "nauc_recall_at_20_std": 0.154232, + "nauc_recall_at_20_diff1": -0.008387, + "nauc_recall_at_100_max": 0.23756, + "nauc_recall_at_100_std": 0.208534, + "nauc_recall_at_100_diff1": 0.027887, + "nauc_recall_at_1000_max": 0.265401, + "nauc_recall_at_1000_std": 0.377488, + "nauc_recall_at_1000_diff1": 0.022805, + "nauc_precision_at_1_max": 0.15867, + "nauc_precision_at_1_std": 0.254745, + "nauc_precision_at_1_diff1": 0.113002, + "nauc_precision_at_3_max": 0.245138, + "nauc_precision_at_3_std": 0.29632, + "nauc_precision_at_3_diff1": 0.117056, + "nauc_precision_at_5_max": 0.312959, + "nauc_precision_at_5_std": 0.233476, + "nauc_precision_at_5_diff1": 0.003748, + "nauc_precision_at_10_max": 0.293748, + "nauc_precision_at_10_std": 0.22154, + "nauc_precision_at_10_diff1": -0.026917, + "nauc_precision_at_20_max": 0.292143, + "nauc_precision_at_20_std": 0.27935, + "nauc_precision_at_20_diff1": -0.052829, + "nauc_precision_at_100_max": 0.321894, + "nauc_precision_at_100_std": 0.292671, + "nauc_precision_at_100_diff1": -0.034731, + "nauc_precision_at_1000_max": 0.256151, + "nauc_precision_at_1000_std": 0.361736, + "nauc_precision_at_1000_diff1": -0.058485, + "nauc_mrr_at_1_max": 0.15867, + "nauc_mrr_at_1_std": 0.254745, + "nauc_mrr_at_1_diff1": 0.113002, + "nauc_mrr_at_3_max": 0.20282, + "nauc_mrr_at_3_std": 0.272771, + "nauc_mrr_at_3_diff1": 0.157211, + "nauc_mrr_at_5_max": 0.219628, + "nauc_mrr_at_5_std": 0.245468, + "nauc_mrr_at_5_diff1": 0.13264, + "nauc_mrr_at_10_max": 0.21463, + "nauc_mrr_at_10_std": 0.243898, + "nauc_mrr_at_10_diff1": 0.113338, + "nauc_mrr_at_20_max": 0.207915, + "nauc_mrr_at_20_std": 0.243288, + "nauc_mrr_at_20_diff1": 0.117407, + "nauc_mrr_at_100_max": 0.21201, + "nauc_mrr_at_100_std": 0.245874, + "nauc_mrr_at_100_diff1": 0.113925, + "nauc_mrr_at_1000_max": 0.211178, + "nauc_mrr_at_1000_std": 0.245479, + "nauc_mrr_at_1000_diff1": 0.114773, + "main_score": 0.08555, + "hf_subset": "IIYi-Clinical", + "languages": [ + "eng-Latn" + ] + } + ] + }, + "evaluation_time": 864.7787539958954, + "kg_co2_emissions": null +} \ No newline at end of file diff --git a/results/intfloat__multilingual-e5-small/fd1525a9fd15316a2d503bf26ab031a61d056e98/R2MEDRetrieval.json b/results/intfloat__multilingual-e5-small/fd1525a9fd15316a2d503bf26ab031a61d056e98/R2MEDRetrieval.json new file mode 100644 index 0000000000..509e96d848 --- /dev/null +++ b/results/intfloat__multilingual-e5-small/fd1525a9fd15316a2d503bf26ab031a61d056e98/R2MEDRetrieval.json @@ -0,0 +1,1187 @@ +{ + "dataset_revision": "1.0", + "task_name": "R2MEDRetrieval", + "mteb_version": "1.38.20", + "scores": { + "test": [ + { + "ndcg_at_1": 0.07767, + "ndcg_at_3": 0.04616, + "ndcg_at_5": 0.03781, + "ndcg_at_10": 0.04222, + "ndcg_at_20": 0.0494, + "ndcg_at_100": 0.06675, + "ndcg_at_1000": 0.08561, + "map_at_1": 0.01603, + "map_at_3": 0.02086, + "map_at_5": 0.02086, + "map_at_10": 0.02453, + "map_at_20": 0.02625, + "map_at_100": 0.02864, + "map_at_1000": 0.0292, + "recall_at_1": 0.01603, + "recall_at_3": 0.02446, + "recall_at_5": 0.02446, + "recall_at_10": 0.04113, + "recall_at_20": 0.06168, + "recall_at_100": 0.12713, + "recall_at_1000": 0.23656, + "precision_at_1": 0.07767, + "precision_at_3": 0.03883, + "precision_at_5": 0.0233, + "precision_at_10": 0.01845, + "precision_at_20": 0.01214, + "precision_at_100": 0.00456, + "precision_at_1000": 0.00088, + "mrr_at_1": 0.07767, + "mrr_at_3": 0.085761, + "mrr_at_5": 0.085761, + "mrr_at_10": 0.090076, + "mrr_at_20": 0.093732, + "mrr_at_100": 0.097428, + "mrr_at_1000": 0.097873, + "nauc_ndcg_at_1_max": 0.405794, + "nauc_ndcg_at_1_std": -0.067784, + "nauc_ndcg_at_1_diff1": 0.40183, + "nauc_ndcg_at_3_max": 0.328963, + "nauc_ndcg_at_3_std": -0.09363, + "nauc_ndcg_at_3_diff1": 0.367631, + "nauc_ndcg_at_5_max": 0.34591, + "nauc_ndcg_at_5_std": -0.105387, + "nauc_ndcg_at_5_diff1": 0.367738, + "nauc_ndcg_at_10_max": 0.320211, + "nauc_ndcg_at_10_std": -0.126862, + "nauc_ndcg_at_10_diff1": 0.412992, + "nauc_ndcg_at_20_max": 0.291586, + "nauc_ndcg_at_20_std": -0.123078, + "nauc_ndcg_at_20_diff1": 0.384161, + "nauc_ndcg_at_100_max": 0.248621, + "nauc_ndcg_at_100_std": -0.096937, + "nauc_ndcg_at_100_diff1": 0.331505, + "nauc_ndcg_at_1000_max": 0.267619, + "nauc_ndcg_at_1000_std": -0.05467, + "nauc_ndcg_at_1000_diff1": 0.334612, + "nauc_map_at_1_max": 0.48915, + "nauc_map_at_1_std": -0.075221, + "nauc_map_at_1_diff1": 0.43227, + "nauc_map_at_3_max": 0.419479, + "nauc_map_at_3_std": -0.120643, + "nauc_map_at_3_diff1": 0.369656, + "nauc_map_at_5_max": 0.419479, + "nauc_map_at_5_std": -0.120643, + "nauc_map_at_5_diff1": 0.369656, + "nauc_map_at_10_max": 0.39717, + "nauc_map_at_10_std": -0.14165, + "nauc_map_at_10_diff1": 0.425627, + "nauc_map_at_20_max": 0.379227, + "nauc_map_at_20_std": -0.140055, + "nauc_map_at_20_diff1": 0.412648, + "nauc_map_at_100_max": 0.347389, + "nauc_map_at_100_std": -0.134893, + "nauc_map_at_100_diff1": 0.397308, + "nauc_map_at_1000_max": 0.348749, + "nauc_map_at_1000_std": -0.134811, + "nauc_map_at_1000_diff1": 0.398482, + "nauc_recall_at_1_max": 0.48915, + "nauc_recall_at_1_std": -0.075221, + "nauc_recall_at_1_diff1": 0.43227, + "nauc_recall_at_3_max": 0.351164, + "nauc_recall_at_3_std": -0.130447, + "nauc_recall_at_3_diff1": 0.319765, + "nauc_recall_at_5_max": 0.351164, + "nauc_recall_at_5_std": -0.130447, + "nauc_recall_at_5_diff1": 0.319765, + "nauc_recall_at_10_max": 0.244621, + "nauc_recall_at_10_std": -0.164187, + "nauc_recall_at_10_diff1": 0.444339, + "nauc_recall_at_20_max": 0.189504, + "nauc_recall_at_20_std": -0.136025, + "nauc_recall_at_20_diff1": 0.342221, + "nauc_recall_at_100_max": 0.118683, + "nauc_recall_at_100_std": -0.067678, + "nauc_recall_at_100_diff1": 0.197704, + "nauc_recall_at_1000_max": 0.173398, + "nauc_recall_at_1000_std": 0.022622, + "nauc_recall_at_1000_diff1": 0.2045, + "nauc_precision_at_1_max": 0.405794, + "nauc_precision_at_1_std": -0.067784, + "nauc_precision_at_1_diff1": 0.40183, + "nauc_precision_at_3_max": 0.297399, + "nauc_precision_at_3_std": -0.1114, + "nauc_precision_at_3_diff1": 0.363706, + "nauc_precision_at_5_max": 0.297399, + "nauc_precision_at_5_std": -0.1114, + "nauc_precision_at_5_diff1": 0.363706, + "nauc_precision_at_10_max": 0.26833, + "nauc_precision_at_10_std": -0.186967, + "nauc_precision_at_10_diff1": 0.496986, + "nauc_precision_at_20_max": 0.206381, + "nauc_precision_at_20_std": -0.17364, + "nauc_precision_at_20_diff1": 0.437037, + "nauc_precision_at_100_max": 0.20673, + "nauc_precision_at_100_std": -0.087342, + "nauc_precision_at_100_diff1": 0.345524, + "nauc_precision_at_1000_max": 0.251359, + "nauc_precision_at_1000_std": 0.052452, + "nauc_precision_at_1000_diff1": 0.324216, + "nauc_mrr_at_1_max": 0.405794, + "nauc_mrr_at_1_std": -0.067784, + "nauc_mrr_at_1_diff1": 0.40183, + "nauc_mrr_at_3_max": 0.319566, + "nauc_mrr_at_3_std": -0.061516, + "nauc_mrr_at_3_diff1": 0.347981, + "nauc_mrr_at_5_max": 0.319566, + "nauc_mrr_at_5_std": -0.061516, + "nauc_mrr_at_5_diff1": 0.347981, + "nauc_mrr_at_10_max": 0.297622, + "nauc_mrr_at_10_std": -0.065046, + "nauc_mrr_at_10_diff1": 0.351523, + "nauc_mrr_at_20_max": 0.29236, + "nauc_mrr_at_20_std": -0.062481, + "nauc_mrr_at_20_diff1": 0.345543, + "nauc_mrr_at_100_max": 0.292104, + "nauc_mrr_at_100_std": -0.0596, + "nauc_mrr_at_100_diff1": 0.344351, + "nauc_mrr_at_1000_max": 0.291862, + "nauc_mrr_at_1000_std": -0.059178, + "nauc_mrr_at_1000_diff1": 0.344445, + "main_score": 0.04222, + "hf_subset": "Biology", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.09091, + "ndcg_at_3": 0.10443, + "ndcg_at_5": 0.12299, + "ndcg_at_10": 0.14663, + "ndcg_at_20": 0.17072, + "ndcg_at_100": 0.21475, + "ndcg_at_1000": 0.27246, + "map_at_1": 0.03541, + "map_at_3": 0.06942, + "map_at_5": 0.08505, + "map_at_10": 0.0964, + "map_at_20": 0.10389, + "map_at_100": 0.1118, + "map_at_1000": 0.1145, + "recall_at_1": 0.03541, + "recall_at_3": 0.11203, + "recall_at_5": 0.15737, + "recall_at_10": 0.22058, + "recall_at_20": 0.29128, + "recall_at_100": 0.4701, + "recall_at_1000": 0.82035, + "precision_at_1": 0.09091, + "precision_at_3": 0.08225, + "precision_at_5": 0.07792, + "precision_at_10": 0.05325, + "precision_at_20": 0.03701, + "precision_at_100": 0.01286, + "precision_at_1000": 0.00238, + "mrr_at_1": 0.090909, + "mrr_at_3": 0.134199, + "mrr_at_5": 0.152381, + "mrr_at_10": 0.164786, + "mrr_at_20": 0.172068, + "mrr_at_100": 0.175864, + "mrr_at_1000": 0.176964, + "nauc_ndcg_at_1_max": -0.034123, + "nauc_ndcg_at_1_std": -0.24545, + "nauc_ndcg_at_1_diff1": 0.097795, + "nauc_ndcg_at_3_max": 0.013381, + "nauc_ndcg_at_3_std": -0.020282, + "nauc_ndcg_at_3_diff1": 0.032529, + "nauc_ndcg_at_5_max": 0.079953, + "nauc_ndcg_at_5_std": 0.028782, + "nauc_ndcg_at_5_diff1": 0.070775, + "nauc_ndcg_at_10_max": 0.148506, + "nauc_ndcg_at_10_std": 0.081323, + "nauc_ndcg_at_10_diff1": 0.091152, + "nauc_ndcg_at_20_max": 0.147467, + "nauc_ndcg_at_20_std": 0.148572, + "nauc_ndcg_at_20_diff1": 0.036292, + "nauc_ndcg_at_100_max": 0.183212, + "nauc_ndcg_at_100_std": 0.176093, + "nauc_ndcg_at_100_diff1": 0.1366, + "nauc_ndcg_at_1000_max": 0.157556, + "nauc_ndcg_at_1000_std": 0.139505, + "nauc_ndcg_at_1000_diff1": 0.105061, + "nauc_map_at_1_max": -0.159392, + "nauc_map_at_1_std": -0.319263, + "nauc_map_at_1_diff1": 0.138859, + "nauc_map_at_3_max": -0.042874, + "nauc_map_at_3_std": -0.095718, + "nauc_map_at_3_diff1": 0.056174, + "nauc_map_at_5_max": 0.01983, + "nauc_map_at_5_std": -0.022016, + "nauc_map_at_5_diff1": 0.078317, + "nauc_map_at_10_max": 0.08274, + "nauc_map_at_10_std": 0.028339, + "nauc_map_at_10_diff1": 0.093638, + "nauc_map_at_20_max": 0.083548, + "nauc_map_at_20_std": 0.062214, + "nauc_map_at_20_diff1": 0.068509, + "nauc_map_at_100_max": 0.088045, + "nauc_map_at_100_std": 0.064181, + "nauc_map_at_100_diff1": 0.085016, + "nauc_map_at_1000_max": 0.086804, + "nauc_map_at_1000_std": 0.062699, + "nauc_map_at_1000_diff1": 0.083943, + "nauc_recall_at_1_max": -0.159392, + "nauc_recall_at_1_std": -0.319263, + "nauc_recall_at_1_diff1": 0.138859, + "nauc_recall_at_3_max": 0.057676, + "nauc_recall_at_3_std": 0.042995, + "nauc_recall_at_3_diff1": 0.052911, + "nauc_recall_at_5_max": 0.136633, + "nauc_recall_at_5_std": 0.09839, + "nauc_recall_at_5_diff1": 0.084382, + "nauc_recall_at_10_max": 0.243707, + "nauc_recall_at_10_std": 0.156432, + "nauc_recall_at_10_diff1": 0.109291, + "nauc_recall_at_20_max": 0.226026, + "nauc_recall_at_20_std": 0.267691, + "nauc_recall_at_20_diff1": -0.007315, + "nauc_recall_at_100_max": 0.303481, + "nauc_recall_at_100_std": 0.376658, + "nauc_recall_at_100_diff1": 0.26339, + "nauc_recall_at_1000_max": 0.232818, + "nauc_recall_at_1000_std": 0.407081, + "nauc_recall_at_1000_diff1": 0.091322, + "nauc_precision_at_1_max": -0.034123, + "nauc_precision_at_1_std": -0.24545, + "nauc_precision_at_1_diff1": 0.097795, + "nauc_precision_at_3_max": 0.072043, + "nauc_precision_at_3_std": 0.068151, + "nauc_precision_at_3_diff1": -0.040205, + "nauc_precision_at_5_max": 0.162216, + "nauc_precision_at_5_std": 0.147757, + "nauc_precision_at_5_diff1": 0.032153, + "nauc_precision_at_10_max": 0.229944, + "nauc_precision_at_10_std": 0.22187, + "nauc_precision_at_10_diff1": 0.03366, + "nauc_precision_at_20_max": 0.216057, + "nauc_precision_at_20_std": 0.351146, + "nauc_precision_at_20_diff1": -0.064091, + "nauc_precision_at_100_max": 0.266083, + "nauc_precision_at_100_std": 0.261346, + "nauc_precision_at_100_diff1": 0.168203, + "nauc_precision_at_1000_max": 0.125141, + "nauc_precision_at_1000_std": 0.0332, + "nauc_precision_at_1000_diff1": 0.091405, + "nauc_mrr_at_1_max": -0.034123, + "nauc_mrr_at_1_std": -0.24545, + "nauc_mrr_at_1_diff1": 0.097795, + "nauc_mrr_at_3_max": 0.046955, + "nauc_mrr_at_3_std": -0.013663, + "nauc_mrr_at_3_diff1": 0.046578, + "nauc_mrr_at_5_max": 0.060566, + "nauc_mrr_at_5_std": -0.03043, + "nauc_mrr_at_5_diff1": 0.064302, + "nauc_mrr_at_10_max": 0.063839, + "nauc_mrr_at_10_std": -0.028191, + "nauc_mrr_at_10_diff1": 0.06574, + "nauc_mrr_at_20_max": 0.066182, + "nauc_mrr_at_20_std": -0.01192, + "nauc_mrr_at_20_diff1": 0.05516, + "nauc_mrr_at_100_max": 0.071745, + "nauc_mrr_at_100_std": -0.010743, + "nauc_mrr_at_100_diff1": 0.067641, + "nauc_mrr_at_1000_max": 0.0709, + "nauc_mrr_at_1000_std": -0.0123, + "nauc_mrr_at_1000_diff1": 0.06695, + "main_score": 0.14663, + "hf_subset": "Bioinformatics", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.10227, + "ndcg_at_3": 0.124, + "ndcg_at_5": 0.14089, + "ndcg_at_10": 0.15384, + "ndcg_at_20": 0.17603, + "ndcg_at_100": 0.225, + "ndcg_at_1000": 0.27287, + "map_at_1": 0.05436, + "map_at_3": 0.09081, + "map_at_5": 0.10479, + "map_at_10": 0.11355, + "map_at_20": 0.12091, + "map_at_100": 0.12774, + "map_at_1000": 0.12989, + "recall_at_1": 0.05436, + "recall_at_3": 0.12294, + "recall_at_5": 0.1707, + "recall_at_10": 0.20425, + "recall_at_20": 0.27386, + "recall_at_100": 0.49161, + "recall_at_1000": 0.77501, + "precision_at_1": 0.10227, + "precision_at_3": 0.08333, + "precision_at_5": 0.075, + "precision_at_10": 0.04773, + "precision_at_20": 0.03182, + "precision_at_100": 0.0117, + "precision_at_1000": 0.00206, + "mrr_at_1": 0.102273, + "mrr_at_3": 0.155303, + "mrr_at_5": 0.172917, + "mrr_at_10": 0.176231, + "mrr_at_20": 0.181498, + "mrr_at_100": 0.187209, + "mrr_at_1000": 0.188182, + "nauc_ndcg_at_1_max": 0.102939, + "nauc_ndcg_at_1_std": -0.044934, + "nauc_ndcg_at_1_diff1": 0.147915, + "nauc_ndcg_at_3_max": -0.035369, + "nauc_ndcg_at_3_std": -0.205694, + "nauc_ndcg_at_3_diff1": -0.047964, + "nauc_ndcg_at_5_max": 0.070781, + "nauc_ndcg_at_5_std": -0.124569, + "nauc_ndcg_at_5_diff1": -0.027228, + "nauc_ndcg_at_10_max": 0.076457, + "nauc_ndcg_at_10_std": -0.107155, + "nauc_ndcg_at_10_diff1": -0.057903, + "nauc_ndcg_at_20_max": 0.089907, + "nauc_ndcg_at_20_std": -0.09066, + "nauc_ndcg_at_20_diff1": -0.045988, + "nauc_ndcg_at_100_max": 0.097426, + "nauc_ndcg_at_100_std": -0.095675, + "nauc_ndcg_at_100_diff1": -0.04532, + "nauc_ndcg_at_1000_max": 0.09034, + "nauc_ndcg_at_1000_std": -0.04997, + "nauc_ndcg_at_1000_diff1": -0.021807, + "nauc_map_at_1_max": -0.070137, + "nauc_map_at_1_std": -0.177271, + "nauc_map_at_1_diff1": 0.064443, + "nauc_map_at_3_max": -0.04736, + "nauc_map_at_3_std": -0.239202, + "nauc_map_at_3_diff1": -0.066173, + "nauc_map_at_5_max": 0.028367, + "nauc_map_at_5_std": -0.184701, + "nauc_map_at_5_diff1": -0.035659, + "nauc_map_at_10_max": 0.043601, + "nauc_map_at_10_std": -0.159907, + "nauc_map_at_10_diff1": -0.057346, + "nauc_map_at_20_max": 0.048658, + "nauc_map_at_20_std": -0.151898, + "nauc_map_at_20_diff1": -0.059019, + "nauc_map_at_100_max": 0.048808, + "nauc_map_at_100_std": -0.151123, + "nauc_map_at_100_diff1": -0.061973, + "nauc_map_at_1000_max": 0.049868, + "nauc_map_at_1000_std": -0.14754, + "nauc_map_at_1000_diff1": -0.059943, + "nauc_recall_at_1_max": -0.070137, + "nauc_recall_at_1_std": -0.177271, + "nauc_recall_at_1_diff1": 0.064443, + "nauc_recall_at_3_max": -0.076041, + "nauc_recall_at_3_std": -0.246507, + "nauc_recall_at_3_diff1": -0.11126, + "nauc_recall_at_5_max": 0.086093, + "nauc_recall_at_5_std": -0.103857, + "nauc_recall_at_5_diff1": -0.052608, + "nauc_recall_at_10_max": 0.089439, + "nauc_recall_at_10_std": -0.077087, + "nauc_recall_at_10_diff1": -0.095862, + "nauc_recall_at_20_max": 0.109206, + "nauc_recall_at_20_std": -0.038109, + "nauc_recall_at_20_diff1": -0.050455, + "nauc_recall_at_100_max": 0.092186, + "nauc_recall_at_100_std": -0.044434, + "nauc_recall_at_100_diff1": -0.03653, + "nauc_recall_at_1000_max": 0.01036, + "nauc_recall_at_1000_std": 0.21424, + "nauc_recall_at_1000_diff1": 0.042999, + "nauc_precision_at_1_max": 0.102939, + "nauc_precision_at_1_std": -0.044934, + "nauc_precision_at_1_diff1": 0.147915, + "nauc_precision_at_3_max": 0.04273, + "nauc_precision_at_3_std": -0.180559, + "nauc_precision_at_3_diff1": -0.058096, + "nauc_precision_at_5_max": 0.23273, + "nauc_precision_at_5_std": -0.002412, + "nauc_precision_at_5_diff1": 0.008277, + "nauc_precision_at_10_max": 0.221005, + "nauc_precision_at_10_std": 0.031731, + "nauc_precision_at_10_diff1": -0.052443, + "nauc_precision_at_20_max": 0.244713, + "nauc_precision_at_20_std": 0.06623, + "nauc_precision_at_20_diff1": -0.01779, + "nauc_precision_at_100_max": 0.251866, + "nauc_precision_at_100_std": 0.026356, + "nauc_precision_at_100_diff1": 0.007412, + "nauc_precision_at_1000_max": 0.171851, + "nauc_precision_at_1000_std": 0.181787, + "nauc_precision_at_1000_diff1": 0.148828, + "nauc_mrr_at_1_max": 0.102939, + "nauc_mrr_at_1_std": -0.044934, + "nauc_mrr_at_1_diff1": 0.147915, + "nauc_mrr_at_3_max": 0.032461, + "nauc_mrr_at_3_std": -0.09979, + "nauc_mrr_at_3_diff1": 0.016387, + "nauc_mrr_at_5_max": 0.092772, + "nauc_mrr_at_5_std": -0.049629, + "nauc_mrr_at_5_diff1": 0.02637, + "nauc_mrr_at_10_max": 0.079798, + "nauc_mrr_at_10_std": -0.06126, + "nauc_mrr_at_10_diff1": 0.024044, + "nauc_mrr_at_20_max": 0.084817, + "nauc_mrr_at_20_std": -0.06229, + "nauc_mrr_at_20_diff1": 0.03, + "nauc_mrr_at_100_max": 0.084887, + "nauc_mrr_at_100_std": -0.061844, + "nauc_mrr_at_100_diff1": 0.030495, + "nauc_mrr_at_1000_max": 0.083764, + "nauc_mrr_at_1000_std": -0.061383, + "nauc_mrr_at_1000_diff1": 0.030322, + "main_score": 0.15384, + "hf_subset": "Medical-Sciences", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.02062, + "ndcg_at_3": 0.00968, + "ndcg_at_5": 0.00984, + "ndcg_at_10": 0.01176, + "ndcg_at_20": 0.01642, + "ndcg_at_100": 0.02496, + "ndcg_at_1000": 0.05843, + "map_at_1": 0.00491, + "map_at_3": 0.00491, + "map_at_5": 0.00542, + "map_at_10": 0.00631, + "map_at_20": 0.00738, + "map_at_100": 0.00815, + "map_at_1000": 0.00889, + "recall_at_1": 0.00491, + "recall_at_3": 0.00491, + "recall_at_5": 0.00697, + "recall_at_10": 0.01247, + "recall_at_20": 0.02518, + "recall_at_100": 0.06273, + "recall_at_1000": 0.28332, + "precision_at_1": 0.02062, + "precision_at_3": 0.00687, + "precision_at_5": 0.00619, + "precision_at_10": 0.00515, + "precision_at_20": 0.00464, + "precision_at_100": 0.00196, + "precision_at_1000": 0.00082, + "mrr_at_1": 0.020619, + "mrr_at_3": 0.020619, + "mrr_at_5": 0.023196, + "mrr_at_10": 0.024485, + "mrr_at_20": 0.026788, + "mrr_at_100": 0.028625, + "mrr_at_1000": 0.029561, + "nauc_ndcg_at_1_max": -0.111748, + "nauc_ndcg_at_1_std": 0.012265, + "nauc_ndcg_at_1_diff1": 0.323888, + "nauc_ndcg_at_3_max": -0.111748, + "nauc_ndcg_at_3_std": 0.012265, + "nauc_ndcg_at_3_diff1": 0.323888, + "nauc_ndcg_at_5_max": -0.077276, + "nauc_ndcg_at_5_std": -0.00972, + "nauc_ndcg_at_5_diff1": 0.22532, + "nauc_ndcg_at_10_max": -0.107241, + "nauc_ndcg_at_10_std": -0.031939, + "nauc_ndcg_at_10_diff1": 0.087523, + "nauc_ndcg_at_20_max": -0.118688, + "nauc_ndcg_at_20_std": -0.089767, + "nauc_ndcg_at_20_diff1": 0.012831, + "nauc_ndcg_at_100_max": -0.086502, + "nauc_ndcg_at_100_std": -0.077155, + "nauc_ndcg_at_100_diff1": 0.093833, + "nauc_ndcg_at_1000_max": -0.065219, + "nauc_ndcg_at_1000_std": -0.016508, + "nauc_ndcg_at_1000_diff1": 0.147454, + "nauc_map_at_1_max": -0.028359, + "nauc_map_at_1_std": 0.046049, + "nauc_map_at_1_diff1": 0.323888, + "nauc_map_at_3_max": -0.028359, + "nauc_map_at_3_std": 0.046049, + "nauc_map_at_3_diff1": 0.323888, + "nauc_map_at_5_max": -0.032524, + "nauc_map_at_5_std": 0.022038, + "nauc_map_at_5_diff1": 0.262683, + "nauc_map_at_10_max": -0.061574, + "nauc_map_at_10_std": -0.000973, + "nauc_map_at_10_diff1": 0.174114, + "nauc_map_at_20_max": -0.079722, + "nauc_map_at_20_std": -0.038515, + "nauc_map_at_20_diff1": 0.118889, + "nauc_map_at_100_max": -0.075638, + "nauc_map_at_100_std": -0.039382, + "nauc_map_at_100_diff1": 0.120161, + "nauc_map_at_1000_max": -0.070654, + "nauc_map_at_1000_std": -0.032562, + "nauc_map_at_1000_diff1": 0.129112, + "nauc_recall_at_1_max": -0.028359, + "nauc_recall_at_1_std": 0.046049, + "nauc_recall_at_1_diff1": 0.323888, + "nauc_recall_at_3_max": -0.028359, + "nauc_recall_at_3_std": 0.046049, + "nauc_recall_at_3_diff1": 0.323888, + "nauc_recall_at_5_max": -0.041324, + "nauc_recall_at_5_std": -0.028689, + "nauc_recall_at_5_diff1": 0.133377, + "nauc_recall_at_10_max": -0.149988, + "nauc_recall_at_10_std": -0.070103, + "nauc_recall_at_10_diff1": -0.093333, + "nauc_recall_at_20_max": -0.153346, + "nauc_recall_at_20_std": -0.158005, + "nauc_recall_at_20_diff1": -0.142882, + "nauc_recall_at_100_max": -0.116509, + "nauc_recall_at_100_std": -0.112392, + "nauc_recall_at_100_diff1": 0.031856, + "nauc_recall_at_1000_max": -0.082856, + "nauc_recall_at_1000_std": 0.045946, + "nauc_recall_at_1000_diff1": 0.108123, + "nauc_precision_at_1_max": -0.111748, + "nauc_precision_at_1_std": 0.012265, + "nauc_precision_at_1_diff1": 0.323888, + "nauc_precision_at_3_max": -0.111748, + "nauc_precision_at_3_std": 0.012265, + "nauc_precision_at_3_diff1": 0.323888, + "nauc_precision_at_5_max": -0.098563, + "nauc_precision_at_5_std": -0.060702, + "nauc_precision_at_5_diff1": 0.109186, + "nauc_precision_at_10_max": -0.156996, + "nauc_precision_at_10_std": -0.092187, + "nauc_precision_at_10_diff1": -0.081952, + "nauc_precision_at_20_max": -0.148009, + "nauc_precision_at_20_std": -0.142116, + "nauc_precision_at_20_diff1": -0.087785, + "nauc_precision_at_100_max": -0.035982, + "nauc_precision_at_100_std": -0.098352, + "nauc_precision_at_100_diff1": 0.168574, + "nauc_precision_at_1000_max": 0.0177, + "nauc_precision_at_1000_std": -0.053511, + "nauc_precision_at_1000_diff1": 0.197817, + "nauc_mrr_at_1_max": -0.111748, + "nauc_mrr_at_1_std": 0.012265, + "nauc_mrr_at_1_diff1": 0.323888, + "nauc_mrr_at_3_max": -0.111748, + "nauc_mrr_at_3_std": 0.012265, + "nauc_mrr_at_3_diff1": 0.323888, + "nauc_mrr_at_5_max": -0.107353, + "nauc_mrr_at_5_std": -0.012057, + "nauc_mrr_at_5_diff1": 0.25232, + "nauc_mrr_at_10_max": -0.123655, + "nauc_mrr_at_10_std": -0.015222, + "nauc_mrr_at_10_diff1": 0.217088, + "nauc_mrr_at_20_max": -0.120215, + "nauc_mrr_at_20_std": -0.033016, + "nauc_mrr_at_20_diff1": 0.180807, + "nauc_mrr_at_100_max": -0.100153, + "nauc_mrr_at_100_std": -0.025619, + "nauc_mrr_at_100_diff1": 0.204795, + "nauc_mrr_at_1000_max": -0.100718, + "nauc_mrr_at_1000_std": -0.026192, + "nauc_mrr_at_1000_diff1": 0.204212, + "main_score": 0.01176, + "hf_subset": "MedXpertQA-Exam", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.00847, + "ndcg_at_3": 0.02274, + "ndcg_at_5": 0.02287, + "ndcg_at_10": 0.02841, + "ndcg_at_20": 0.03271, + "ndcg_at_100": 0.05017, + "ndcg_at_1000": 0.09347, + "map_at_1": 0.00169, + "map_at_3": 0.01121, + "map_at_5": 0.01392, + "map_at_10": 0.01586, + "map_at_20": 0.01682, + "map_at_100": 0.01905, + "map_at_1000": 0.0204, + "recall_at_1": 0.00169, + "recall_at_3": 0.01921, + "recall_at_5": 0.02698, + "recall_at_10": 0.04068, + "recall_at_20": 0.05213, + "recall_at_100": 0.11796, + "recall_at_1000": 0.35466, + "precision_at_1": 0.00847, + "precision_at_3": 0.02542, + "precision_at_5": 0.02034, + "precision_at_10": 0.01441, + "precision_at_20": 0.00932, + "precision_at_100": 0.00432, + "precision_at_1000": 0.00144, + "mrr_at_1": 0.008475, + "mrr_at_3": 0.028249, + "mrr_at_5": 0.031638, + "mrr_at_10": 0.035334, + "mrr_at_20": 0.037722, + "mrr_at_100": 0.041161, + "mrr_at_1000": 0.042636, + "nauc_ndcg_at_1_max": -0.207793, + "nauc_ndcg_at_1_std": -0.579509, + "nauc_ndcg_at_1_diff1": -0.071437, + "nauc_ndcg_at_3_max": -0.063776, + "nauc_ndcg_at_3_std": 0.357197, + "nauc_ndcg_at_3_diff1": -0.311466, + "nauc_ndcg_at_5_max": -0.051465, + "nauc_ndcg_at_5_std": 0.342469, + "nauc_ndcg_at_5_diff1": -0.256401, + "nauc_ndcg_at_10_max": -0.084827, + "nauc_ndcg_at_10_std": 0.33909, + "nauc_ndcg_at_10_diff1": -0.256679, + "nauc_ndcg_at_20_max": -0.052647, + "nauc_ndcg_at_20_std": 0.283033, + "nauc_ndcg_at_20_diff1": -0.186807, + "nauc_ndcg_at_100_max": -0.096395, + "nauc_ndcg_at_100_std": 0.314986, + "nauc_ndcg_at_100_diff1": -0.20402, + "nauc_ndcg_at_1000_max": -0.097282, + "nauc_ndcg_at_1000_std": 0.346635, + "nauc_ndcg_at_1000_diff1": -0.231319, + "nauc_map_at_1_max": -0.207793, + "nauc_map_at_1_std": -0.579509, + "nauc_map_at_1_diff1": -0.071437, + "nauc_map_at_3_max": -0.035644, + "nauc_map_at_3_std": 0.403824, + "nauc_map_at_3_diff1": -0.323891, + "nauc_map_at_5_max": -0.015037, + "nauc_map_at_5_std": 0.421568, + "nauc_map_at_5_diff1": -0.283744, + "nauc_map_at_10_max": -0.035075, + "nauc_map_at_10_std": 0.404024, + "nauc_map_at_10_diff1": -0.28798, + "nauc_map_at_20_max": -0.019413, + "nauc_map_at_20_std": 0.386182, + "nauc_map_at_20_diff1": -0.259815, + "nauc_map_at_100_max": -0.033964, + "nauc_map_at_100_std": 0.38545, + "nauc_map_at_100_diff1": -0.266657, + "nauc_map_at_1000_max": -0.035331, + "nauc_map_at_1000_std": 0.393586, + "nauc_map_at_1000_diff1": -0.269957, + "nauc_recall_at_1_max": -0.207793, + "nauc_recall_at_1_std": -0.579509, + "nauc_recall_at_1_diff1": -0.071437, + "nauc_recall_at_3_max": -0.035275, + "nauc_recall_at_3_std": 0.453877, + "nauc_recall_at_3_diff1": -0.328188, + "nauc_recall_at_5_max": -0.061079, + "nauc_recall_at_5_std": 0.3565, + "nauc_recall_at_5_diff1": -0.223945, + "nauc_recall_at_10_max": -0.126096, + "nauc_recall_at_10_std": 0.350381, + "nauc_recall_at_10_diff1": -0.232042, + "nauc_recall_at_20_max": -0.075999, + "nauc_recall_at_20_std": 0.237484, + "nauc_recall_at_20_diff1": -0.13979, + "nauc_recall_at_100_max": -0.151187, + "nauc_recall_at_100_std": 0.272644, + "nauc_recall_at_100_diff1": -0.165172, + "nauc_recall_at_1000_max": -0.171562, + "nauc_recall_at_1000_std": 0.283301, + "nauc_recall_at_1000_diff1": -0.199838, + "nauc_precision_at_1_max": -0.207793, + "nauc_precision_at_1_std": -0.579509, + "nauc_precision_at_1_diff1": -0.071437, + "nauc_precision_at_3_max": -0.065455, + "nauc_precision_at_3_std": 0.449919, + "nauc_precision_at_3_diff1": -0.334147, + "nauc_precision_at_5_max": -0.036128, + "nauc_precision_at_5_std": 0.402325, + "nauc_precision_at_5_diff1": -0.276662, + "nauc_precision_at_10_max": -0.068833, + "nauc_precision_at_10_std": 0.373089, + "nauc_precision_at_10_diff1": -0.26693, + "nauc_precision_at_20_max": -2.2e-05, + "nauc_precision_at_20_std": 0.271351, + "nauc_precision_at_20_diff1": -0.10276, + "nauc_precision_at_100_max": -0.05814, + "nauc_precision_at_100_std": 0.371304, + "nauc_precision_at_100_diff1": -0.168223, + "nauc_precision_at_1000_max": 0.004952, + "nauc_precision_at_1000_std": 0.354337, + "nauc_precision_at_1000_diff1": -0.163933, + "nauc_mrr_at_1_max": -0.207793, + "nauc_mrr_at_1_std": -0.579509, + "nauc_mrr_at_1_diff1": -0.071437, + "nauc_mrr_at_3_max": -0.096046, + "nauc_mrr_at_3_std": 0.189026, + "nauc_mrr_at_3_diff1": -0.258993, + "nauc_mrr_at_5_max": -0.095078, + "nauc_mrr_at_5_std": 0.156914, + "nauc_mrr_at_5_diff1": -0.230789, + "nauc_mrr_at_10_max": -0.109041, + "nauc_mrr_at_10_std": 0.176877, + "nauc_mrr_at_10_diff1": -0.227401, + "nauc_mrr_at_20_max": -0.095018, + "nauc_mrr_at_20_std": 0.148014, + "nauc_mrr_at_20_diff1": -0.179651, + "nauc_mrr_at_100_max": -0.10585, + "nauc_mrr_at_100_std": 0.159619, + "nauc_mrr_at_100_diff1": -0.182057, + "nauc_mrr_at_1000_max": -0.101868, + "nauc_mrr_at_1000_std": 0.160298, + "nauc_mrr_at_1000_diff1": -0.186783, + "main_score": 0.02841, + "hf_subset": "MedQA-Diag", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.0, + "ndcg_at_3": 0.00679, + "ndcg_at_5": 0.00679, + "ndcg_at_10": 0.00898, + "ndcg_at_20": 0.01235, + "ndcg_at_100": 0.02415, + "ndcg_at_1000": 0.04631, + "map_at_1": 0.0, + "map_at_3": 0.005, + "map_at_5": 0.005, + "map_at_10": 0.00606, + "map_at_20": 0.00677, + "map_at_100": 0.00812, + "map_at_1000": 0.00873, + "recall_at_1": 0.0, + "recall_at_3": 0.01, + "recall_at_5": 0.01, + "recall_at_10": 0.01556, + "recall_at_20": 0.02656, + "recall_at_100": 0.08033, + "recall_at_1000": 0.23256, + "precision_at_1": 0.0, + "precision_at_3": 0.00444, + "precision_at_5": 0.00267, + "precision_at_10": 0.00267, + "precision_at_20": 0.00267, + "precision_at_100": 0.0016, + "precision_at_1000": 0.00049, + "mrr_at_1": 0.0, + "mrr_at_3": 0.006667, + "mrr_at_5": 0.006667, + "mrr_at_10": 0.007333, + "mrr_at_20": 0.008903, + "mrr_at_100": 0.01137, + "mrr_at_1000": 0.012199, + "nauc_ndcg_at_1_max": NaN, + "nauc_ndcg_at_1_std": NaN, + "nauc_ndcg_at_1_diff1": NaN, + "nauc_ndcg_at_3_max": 0.182662, + "nauc_ndcg_at_3_std": 1.0, + "nauc_ndcg_at_3_diff1": -0.005716, + "nauc_ndcg_at_5_max": 0.182662, + "nauc_ndcg_at_5_std": 1.0, + "nauc_ndcg_at_5_diff1": -0.005716, + "nauc_ndcg_at_10_max": 0.314262, + "nauc_ndcg_at_10_std": 0.841398, + "nauc_ndcg_at_10_diff1": 0.191459, + "nauc_ndcg_at_20_max": 0.470759, + "nauc_ndcg_at_20_std": 0.739151, + "nauc_ndcg_at_20_diff1": 0.202906, + "nauc_ndcg_at_100_max": 0.28005, + "nauc_ndcg_at_100_std": 0.373105, + "nauc_ndcg_at_100_diff1": 0.153493, + "nauc_ndcg_at_1000_max": 0.183478, + "nauc_ndcg_at_1000_std": 0.264074, + "nauc_ndcg_at_1000_diff1": 0.063184, + "nauc_map_at_1_max": NaN, + "nauc_map_at_1_std": NaN, + "nauc_map_at_1_diff1": NaN, + "nauc_map_at_3_max": 0.121009, + "nauc_map_at_3_std": 1.0, + "nauc_map_at_3_diff1": -0.056077, + "nauc_map_at_5_max": 0.121009, + "nauc_map_at_5_std": 1.0, + "nauc_map_at_5_diff1": -0.056077, + "nauc_map_at_10_max": 0.249415, + "nauc_map_at_10_std": 0.942212, + "nauc_map_at_10_diff1": 0.081486, + "nauc_map_at_20_max": 0.320546, + "nauc_map_at_20_std": 0.899326, + "nauc_map_at_20_diff1": 0.112567, + "nauc_map_at_100_max": 0.266083, + "nauc_map_at_100_std": 0.757462, + "nauc_map_at_100_diff1": 0.099167, + "nauc_map_at_1000_max": 0.256213, + "nauc_map_at_1000_std": 0.730778, + "nauc_map_at_1000_diff1": 0.090565, + "nauc_recall_at_1_max": NaN, + "nauc_recall_at_1_std": NaN, + "nauc_recall_at_1_diff1": NaN, + "nauc_recall_at_3_max": 0.121009, + "nauc_recall_at_3_std": 1.0, + "nauc_recall_at_3_diff1": -0.056077, + "nauc_recall_at_5_max": 0.121009, + "nauc_recall_at_5_std": 1.0, + "nauc_recall_at_5_diff1": -0.056077, + "nauc_recall_at_10_max": 0.338342, + "nauc_recall_at_10_std": 0.775039, + "nauc_recall_at_10_diff1": 0.248649, + "nauc_recall_at_20_max": 0.574225, + "nauc_recall_at_20_std": 0.663399, + "nauc_recall_at_20_diff1": 0.27877, + "nauc_recall_at_100_max": 0.246445, + "nauc_recall_at_100_std": 0.180102, + "nauc_recall_at_100_diff1": 0.164577, + "nauc_recall_at_1000_max": 0.100633, + "nauc_recall_at_1000_std": 0.075731, + "nauc_recall_at_1000_diff1": 0.025192, + "nauc_precision_at_1_max": NaN, + "nauc_precision_at_1_std": NaN, + "nauc_precision_at_1_diff1": NaN, + "nauc_precision_at_3_max": 0.340757, + "nauc_precision_at_3_std": 1.0, + "nauc_precision_at_3_diff1": 0.123424, + "nauc_precision_at_5_max": 0.340757, + "nauc_precision_at_5_std": 1.0, + "nauc_precision_at_5_diff1": 0.123424, + "nauc_precision_at_10_max": 0.501342, + "nauc_precision_at_10_std": 0.606319, + "nauc_precision_at_10_diff1": 0.477193, + "nauc_precision_at_20_max": 0.666152, + "nauc_precision_at_20_std": 0.483398, + "nauc_precision_at_20_diff1": 0.241246, + "nauc_precision_at_100_max": 0.329042, + "nauc_precision_at_100_std": 0.1545, + "nauc_precision_at_100_diff1": 0.185233, + "nauc_precision_at_1000_max": 0.154104, + "nauc_precision_at_1000_std": 0.110465, + "nauc_precision_at_1000_diff1": 0.010083, + "nauc_mrr_at_1_max": NaN, + "nauc_mrr_at_1_std": NaN, + "nauc_mrr_at_1_diff1": NaN, + "nauc_mrr_at_3_max": 0.340757, + "nauc_mrr_at_3_std": 1.0, + "nauc_mrr_at_3_diff1": 0.123424, + "nauc_mrr_at_5_max": 0.340757, + "nauc_mrr_at_5_std": 1.0, + "nauc_mrr_at_5_diff1": 0.123424, + "nauc_mrr_at_10_max": 0.33922, + "nauc_mrr_at_10_std": 0.856843, + "nauc_mrr_at_10_diff1": 0.203112, + "nauc_mrr_at_20_max": 0.429101, + "nauc_mrr_at_20_std": 0.774951, + "nauc_mrr_at_20_diff1": 0.177119, + "nauc_mrr_at_100_max": 0.336383, + "nauc_mrr_at_100_std": 0.619434, + "nauc_mrr_at_100_diff1": 0.148331, + "nauc_mrr_at_1000_max": 0.324074, + "nauc_mrr_at_1000_std": 0.607261, + "nauc_mrr_at_1000_diff1": 0.137801, + "main_score": 0.00898, + "hf_subset": "PMC-Treatment", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.07895, + "ndcg_at_3": 0.07718, + "ndcg_at_5": 0.09722, + "ndcg_at_10": 0.11381, + "ndcg_at_20": 0.13045, + "ndcg_at_100": 0.18165, + "ndcg_at_1000": 0.2239, + "map_at_1": 0.03874, + "map_at_3": 0.05763, + "map_at_5": 0.07013, + "map_at_10": 0.07673, + "map_at_20": 0.08158, + "map_at_100": 0.08962, + "map_at_1000": 0.09122, + "recall_at_1": 0.03874, + "recall_at_3": 0.07822, + "recall_at_5": 0.12354, + "recall_at_10": 0.16155, + "recall_at_20": 0.2193, + "recall_at_100": 0.44883, + "recall_at_1000": 0.72515, + "precision_at_1": 0.07895, + "precision_at_3": 0.05556, + "precision_at_5": 0.04912, + "precision_at_10": 0.03421, + "precision_at_20": 0.02237, + "precision_at_100": 0.00912, + "precision_at_1000": 0.00154, + "mrr_at_1": 0.078947, + "mrr_at_3": 0.109649, + "mrr_at_5": 0.123684, + "mrr_at_10": 0.134231, + "mrr_at_20": 0.138773, + "mrr_at_100": 0.144821, + "mrr_at_1000": 0.146121, + "nauc_ndcg_at_1_max": -0.029813, + "nauc_ndcg_at_1_std": -0.253541, + "nauc_ndcg_at_1_diff1": 0.594857, + "nauc_ndcg_at_3_max": 0.016203, + "nauc_ndcg_at_3_std": -0.131043, + "nauc_ndcg_at_3_diff1": 0.308728, + "nauc_ndcg_at_5_max": 0.036864, + "nauc_ndcg_at_5_std": -0.063292, + "nauc_ndcg_at_5_diff1": 0.230282, + "nauc_ndcg_at_10_max": 0.016595, + "nauc_ndcg_at_10_std": -0.037054, + "nauc_ndcg_at_10_diff1": 0.198948, + "nauc_ndcg_at_20_max": 0.012824, + "nauc_ndcg_at_20_std": 0.012068, + "nauc_ndcg_at_20_diff1": 0.162606, + "nauc_ndcg_at_100_max": -0.02813, + "nauc_ndcg_at_100_std": 0.007869, + "nauc_ndcg_at_100_diff1": 0.089704, + "nauc_ndcg_at_1000_max": 0.021671, + "nauc_ndcg_at_1000_std": 0.028456, + "nauc_ndcg_at_1000_diff1": 0.132557, + "nauc_map_at_1_max": -0.000614, + "nauc_map_at_1_std": -0.221685, + "nauc_map_at_1_diff1": 0.547923, + "nauc_map_at_3_max": 0.020891, + "nauc_map_at_3_std": -0.155146, + "nauc_map_at_3_diff1": 0.357983, + "nauc_map_at_5_max": 0.042446, + "nauc_map_at_5_std": -0.08958, + "nauc_map_at_5_diff1": 0.28406, + "nauc_map_at_10_max": 0.026037, + "nauc_map_at_10_std": -0.072652, + "nauc_map_at_10_diff1": 0.260027, + "nauc_map_at_20_max": 0.028212, + "nauc_map_at_20_std": -0.044744, + "nauc_map_at_20_diff1": 0.244503, + "nauc_map_at_100_max": 0.02032, + "nauc_map_at_100_std": -0.042854, + "nauc_map_at_100_diff1": 0.223101, + "nauc_map_at_1000_max": 0.022682, + "nauc_map_at_1000_std": -0.042472, + "nauc_map_at_1000_diff1": 0.22512, + "nauc_recall_at_1_max": -0.000614, + "nauc_recall_at_1_std": -0.221685, + "nauc_recall_at_1_diff1": 0.547923, + "nauc_recall_at_3_max": 0.00575, + "nauc_recall_at_3_std": -0.095103, + "nauc_recall_at_3_diff1": 0.185979, + "nauc_recall_at_5_max": 0.038026, + "nauc_recall_at_5_std": 0.026586, + "nauc_recall_at_5_diff1": 0.083814, + "nauc_recall_at_10_max": -0.004139, + "nauc_recall_at_10_std": 0.04904, + "nauc_recall_at_10_diff1": 0.045643, + "nauc_recall_at_20_max": -0.01125, + "nauc_recall_at_20_std": 0.153478, + "nauc_recall_at_20_diff1": -0.023156, + "nauc_recall_at_100_max": -0.147538, + "nauc_recall_at_100_std": 0.110578, + "nauc_recall_at_100_diff1": -0.178052, + "nauc_recall_at_1000_max": 0.013217, + "nauc_recall_at_1000_std": 0.264942, + "nauc_recall_at_1000_diff1": -0.108535, + "nauc_precision_at_1_max": -0.029813, + "nauc_precision_at_1_std": -0.253541, + "nauc_precision_at_1_diff1": 0.594857, + "nauc_precision_at_3_max": 0.009818, + "nauc_precision_at_3_std": -0.080853, + "nauc_precision_at_3_diff1": 0.223298, + "nauc_precision_at_5_max": -0.000707, + "nauc_precision_at_5_std": 0.013532, + "nauc_precision_at_5_diff1": 0.095972, + "nauc_precision_at_10_max": -0.028754, + "nauc_precision_at_10_std": 0.081624, + "nauc_precision_at_10_diff1": 0.053371, + "nauc_precision_at_20_max": -0.026487, + "nauc_precision_at_20_std": 0.147651, + "nauc_precision_at_20_diff1": 0.019487, + "nauc_precision_at_100_max": -0.067239, + "nauc_precision_at_100_std": 0.085618, + "nauc_precision_at_100_diff1": -0.093835, + "nauc_precision_at_1000_max": 0.137949, + "nauc_precision_at_1000_std": 0.150472, + "nauc_precision_at_1000_diff1": 0.063588, + "nauc_mrr_at_1_max": -0.029813, + "nauc_mrr_at_1_std": -0.253541, + "nauc_mrr_at_1_diff1": 0.594857, + "nauc_mrr_at_3_max": 0.037161, + "nauc_mrr_at_3_std": -0.176845, + "nauc_mrr_at_3_diff1": 0.382215, + "nauc_mrr_at_5_max": 0.027289, + "nauc_mrr_at_5_std": -0.140813, + "nauc_mrr_at_5_diff1": 0.341139, + "nauc_mrr_at_10_max": 0.028741, + "nauc_mrr_at_10_std": -0.12725, + "nauc_mrr_at_10_diff1": 0.326778, + "nauc_mrr_at_20_max": 0.020196, + "nauc_mrr_at_20_std": -0.121871, + "nauc_mrr_at_20_diff1": 0.313857, + "nauc_mrr_at_100_max": 0.021305, + "nauc_mrr_at_100_std": -0.121516, + "nauc_mrr_at_100_diff1": 0.308072, + "nauc_mrr_at_1000_max": 0.022533, + "nauc_mrr_at_1000_std": -0.122107, + "nauc_mrr_at_1000_diff1": 0.309685, + "main_score": 0.11381, + "hf_subset": "PMC-Clinical", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.05426, + "ndcg_at_3": 0.04438, + "ndcg_at_5": 0.04173, + "ndcg_at_10": 0.0502, + "ndcg_at_20": 0.0607, + "ndcg_at_100": 0.09083, + "ndcg_at_1000": 0.14256, + "map_at_1": 0.01279, + "map_at_3": 0.0205, + "map_at_5": 0.02379, + "map_at_10": 0.02654, + "map_at_20": 0.02958, + "map_at_100": 0.03351, + "map_at_1000": 0.0355, + "recall_at_1": 0.01279, + "recall_at_3": 0.02842, + "recall_at_5": 0.03811, + "recall_at_10": 0.05775, + "recall_at_20": 0.08514, + "recall_at_100": 0.19755, + "recall_at_1000": 0.49005, + "precision_at_1": 0.05426, + "precision_at_3": 0.04134, + "precision_at_5": 0.03256, + "precision_at_10": 0.02403, + "precision_at_20": 0.01705, + "precision_at_100": 0.0076, + "precision_at_1000": 0.00182, + "mrr_at_1": 0.054264, + "mrr_at_3": 0.073643, + "mrr_at_5": 0.077519, + "mrr_at_10": 0.08824, + "mrr_at_20": 0.091627, + "mrr_at_100": 0.096737, + "mrr_at_1000": 0.098044, + "nauc_ndcg_at_1_max": 0.129825, + "nauc_ndcg_at_1_std": 0.250267, + "nauc_ndcg_at_1_diff1": 0.114289, + "nauc_ndcg_at_3_max": 0.137967, + "nauc_ndcg_at_3_std": 0.179744, + "nauc_ndcg_at_3_diff1": 0.130586, + "nauc_ndcg_at_5_max": 0.175776, + "nauc_ndcg_at_5_std": 0.193804, + "nauc_ndcg_at_5_diff1": 0.112905, + "nauc_ndcg_at_10_max": 0.19821, + "nauc_ndcg_at_10_std": 0.240122, + "nauc_ndcg_at_10_diff1": 0.093087, + "nauc_ndcg_at_20_max": 0.227179, + "nauc_ndcg_at_20_std": 0.262485, + "nauc_ndcg_at_20_diff1": 0.076719, + "nauc_ndcg_at_100_max": 0.2545, + "nauc_ndcg_at_100_std": 0.273445, + "nauc_ndcg_at_100_diff1": 0.063113, + "nauc_ndcg_at_1000_max": 0.252716, + "nauc_ndcg_at_1000_std": 0.291237, + "nauc_ndcg_at_1000_diff1": 0.07779, + "nauc_map_at_1_max": 0.05198, + "nauc_map_at_1_std": 0.311592, + "nauc_map_at_1_diff1": 0.077468, + "nauc_map_at_3_max": 0.096128, + "nauc_map_at_3_std": 0.196051, + "nauc_map_at_3_diff1": 0.104611, + "nauc_map_at_5_max": 0.158988, + "nauc_map_at_5_std": 0.221987, + "nauc_map_at_5_diff1": 0.118588, + "nauc_map_at_10_max": 0.169475, + "nauc_map_at_10_std": 0.238833, + "nauc_map_at_10_diff1": 0.107366, + "nauc_map_at_20_max": 0.192494, + "nauc_map_at_20_std": 0.253685, + "nauc_map_at_20_diff1": 0.096556, + "nauc_map_at_100_max": 0.196316, + "nauc_map_at_100_std": 0.256395, + "nauc_map_at_100_diff1": 0.093854, + "nauc_map_at_1000_max": 0.198414, + "nauc_map_at_1000_std": 0.261291, + "nauc_map_at_1000_diff1": 0.094259, + "nauc_recall_at_1_max": 0.05198, + "nauc_recall_at_1_std": 0.311592, + "nauc_recall_at_1_diff1": 0.077468, + "nauc_recall_at_3_max": 0.123147, + "nauc_recall_at_3_std": 0.162926, + "nauc_recall_at_3_diff1": 0.091353, + "nauc_recall_at_5_max": 0.210389, + "nauc_recall_at_5_std": 0.171859, + "nauc_recall_at_5_diff1": 0.116914, + "nauc_recall_at_10_max": 0.229118, + "nauc_recall_at_10_std": 0.245832, + "nauc_recall_at_10_diff1": 0.072708, + "nauc_recall_at_20_max": 0.274253, + "nauc_recall_at_20_std": 0.270942, + "nauc_recall_at_20_diff1": 0.04157, + "nauc_recall_at_100_max": 0.2838, + "nauc_recall_at_100_std": 0.25856, + "nauc_recall_at_100_diff1": 0.019804, + "nauc_recall_at_1000_max": 0.209565, + "nauc_recall_at_1000_std": 0.243951, + "nauc_recall_at_1000_diff1": 0.052763, + "nauc_precision_at_1_max": 0.129825, + "nauc_precision_at_1_std": 0.250267, + "nauc_precision_at_1_diff1": 0.114289, + "nauc_precision_at_3_max": 0.15622, + "nauc_precision_at_3_std": 0.149857, + "nauc_precision_at_3_diff1": 0.153534, + "nauc_precision_at_5_max": 0.241365, + "nauc_precision_at_5_std": 0.195953, + "nauc_precision_at_5_diff1": 0.146313, + "nauc_precision_at_10_max": 0.229931, + "nauc_precision_at_10_std": 0.272129, + "nauc_precision_at_10_diff1": 0.092657, + "nauc_precision_at_20_max": 0.261459, + "nauc_precision_at_20_std": 0.318611, + "nauc_precision_at_20_diff1": 0.057454, + "nauc_precision_at_100_max": 0.310076, + "nauc_precision_at_100_std": 0.329621, + "nauc_precision_at_100_diff1": 0.038868, + "nauc_precision_at_1000_max": 0.25392, + "nauc_precision_at_1000_std": 0.301009, + "nauc_precision_at_1000_diff1": 0.060284, + "nauc_mrr_at_1_max": 0.129825, + "nauc_mrr_at_1_std": 0.250267, + "nauc_mrr_at_1_diff1": 0.114289, + "nauc_mrr_at_3_max": 0.178036, + "nauc_mrr_at_3_std": 0.227151, + "nauc_mrr_at_3_diff1": 0.096214, + "nauc_mrr_at_5_max": 0.182738, + "nauc_mrr_at_5_std": 0.200718, + "nauc_mrr_at_5_diff1": 0.105598, + "nauc_mrr_at_10_max": 0.183706, + "nauc_mrr_at_10_std": 0.225601, + "nauc_mrr_at_10_diff1": 0.090533, + "nauc_mrr_at_20_max": 0.187058, + "nauc_mrr_at_20_std": 0.228852, + "nauc_mrr_at_20_diff1": 0.089431, + "nauc_mrr_at_100_max": 0.192842, + "nauc_mrr_at_100_std": 0.23012, + "nauc_mrr_at_100_diff1": 0.083125, + "nauc_mrr_at_1000_max": 0.192581, + "nauc_mrr_at_1000_std": 0.229352, + "nauc_mrr_at_1000_diff1": 0.084303, + "main_score": 0.0502, + "hf_subset": "IIYi-Clinical", + "languages": [ + "eng-Latn" + ] + } + ] + }, + "evaluation_time": 304.3181188106537, + "kg_co2_emissions": null +} \ No newline at end of file diff --git a/results/sentence-transformers__all-mpnet-base-v2/9a3225965996d404b775526de6dbfe85d3368642/R2MEDRetrieval.json b/results/sentence-transformers__all-mpnet-base-v2/9a3225965996d404b775526de6dbfe85d3368642/R2MEDRetrieval.json new file mode 100644 index 0000000000..799e61bc7f --- /dev/null +++ b/results/sentence-transformers__all-mpnet-base-v2/9a3225965996d404b775526de6dbfe85d3368642/R2MEDRetrieval.json @@ -0,0 +1,1187 @@ +{ + "dataset_revision": "1.0", + "task_name": "R2MEDRetrieval", + "mteb_version": "1.38.20", + "scores": { + "test": [ + { + "ndcg_at_1": 0.15534, + "ndcg_at_3": 0.13908, + "ndcg_at_5": 0.13501, + "ndcg_at_10": 0.15523, + "ndcg_at_20": 0.19321, + "ndcg_at_100": 0.25813, + "ndcg_at_1000": 0.32595, + "map_at_1": 0.03541, + "map_at_3": 0.07903, + "map_at_5": 0.08866, + "map_at_10": 0.10351, + "map_at_20": 0.1171, + "map_at_100": 0.13018, + "map_at_1000": 0.13416, + "recall_at_1": 0.03541, + "recall_at_3": 0.09825, + "recall_at_5": 0.12522, + "recall_at_10": 0.18074, + "recall_at_20": 0.28637, + "recall_at_100": 0.53202, + "recall_at_1000": 0.92056, + "precision_at_1": 0.15534, + "precision_at_3": 0.12621, + "precision_at_5": 0.09515, + "precision_at_10": 0.07184, + "precision_at_20": 0.05534, + "precision_at_100": 0.02058, + "precision_at_1000": 0.00334, + "mrr_at_1": 0.145631, + "mrr_at_3": 0.194175, + "mrr_at_5": 0.203398, + "mrr_at_10": 0.217688, + "mrr_at_20": 0.227213, + "mrr_at_100": 0.231521, + "mrr_at_1000": 0.232427, + "nauc_ndcg_at_1_max": 0.095024, + "nauc_ndcg_at_1_std": -0.113628, + "nauc_ndcg_at_1_diff1": 0.114951, + "nauc_ndcg_at_3_max": 0.074069, + "nauc_ndcg_at_3_std": -0.211497, + "nauc_ndcg_at_3_diff1": 0.160804, + "nauc_ndcg_at_5_max": 0.13752, + "nauc_ndcg_at_5_std": -0.197143, + "nauc_ndcg_at_5_diff1": 0.18805, + "nauc_ndcg_at_10_max": 0.127887, + "nauc_ndcg_at_10_std": -0.203505, + "nauc_ndcg_at_10_diff1": 0.237664, + "nauc_ndcg_at_20_max": 0.090725, + "nauc_ndcg_at_20_std": -0.225001, + "nauc_ndcg_at_20_diff1": 0.272629, + "nauc_ndcg_at_100_max": 0.075838, + "nauc_ndcg_at_100_std": -0.236398, + "nauc_ndcg_at_100_diff1": 0.255768, + "nauc_ndcg_at_1000_max": 0.104519, + "nauc_ndcg_at_1000_std": -0.201941, + "nauc_ndcg_at_1000_diff1": 0.262565, + "nauc_map_at_1_max": 0.225498, + "nauc_map_at_1_std": -0.113399, + "nauc_map_at_1_diff1": 0.123715, + "nauc_map_at_3_max": 0.181559, + "nauc_map_at_3_std": -0.220649, + "nauc_map_at_3_diff1": 0.138722, + "nauc_map_at_5_max": 0.205706, + "nauc_map_at_5_std": -0.195206, + "nauc_map_at_5_diff1": 0.165287, + "nauc_map_at_10_max": 0.183134, + "nauc_map_at_10_std": -0.205682, + "nauc_map_at_10_diff1": 0.216736, + "nauc_map_at_20_max": 0.164334, + "nauc_map_at_20_std": -0.213882, + "nauc_map_at_20_diff1": 0.234181, + "nauc_map_at_100_max": 0.151721, + "nauc_map_at_100_std": -0.217534, + "nauc_map_at_100_diff1": 0.235429, + "nauc_map_at_1000_max": 0.153967, + "nauc_map_at_1000_std": -0.215689, + "nauc_map_at_1000_diff1": 0.236517, + "nauc_recall_at_1_max": 0.225498, + "nauc_recall_at_1_std": -0.113399, + "nauc_recall_at_1_diff1": 0.123715, + "nauc_recall_at_3_max": 0.126542, + "nauc_recall_at_3_std": -0.244866, + "nauc_recall_at_3_diff1": 0.125932, + "nauc_recall_at_5_max": 0.196977, + "nauc_recall_at_5_std": -0.159331, + "nauc_recall_at_5_diff1": 0.179507, + "nauc_recall_at_10_max": 0.133683, + "nauc_recall_at_10_std": -0.184059, + "nauc_recall_at_10_diff1": 0.283263, + "nauc_recall_at_20_max": 0.032714, + "nauc_recall_at_20_std": -0.222894, + "nauc_recall_at_20_diff1": 0.317803, + "nauc_recall_at_100_max": 0.016503, + "nauc_recall_at_100_std": -0.226613, + "nauc_recall_at_100_diff1": 0.266964, + "nauc_recall_at_1000_max": 0.238382, + "nauc_recall_at_1000_std": 0.202228, + "nauc_recall_at_1000_diff1": 0.504585, + "nauc_precision_at_1_max": 0.095024, + "nauc_precision_at_1_std": -0.113628, + "nauc_precision_at_1_diff1": 0.114951, + "nauc_precision_at_3_max": 0.067652, + "nauc_precision_at_3_std": -0.239805, + "nauc_precision_at_3_diff1": 0.165241, + "nauc_precision_at_5_max": 0.104022, + "nauc_precision_at_5_std": -0.216625, + "nauc_precision_at_5_diff1": 0.204526, + "nauc_precision_at_10_max": 0.039239, + "nauc_precision_at_10_std": -0.250163, + "nauc_precision_at_10_diff1": 0.325465, + "nauc_precision_at_20_max": -0.035362, + "nauc_precision_at_20_std": -0.261832, + "nauc_precision_at_20_diff1": 0.331851, + "nauc_precision_at_100_max": -0.088695, + "nauc_precision_at_100_std": -0.219005, + "nauc_precision_at_100_diff1": 0.208391, + "nauc_precision_at_1000_max": -0.094984, + "nauc_precision_at_1000_std": -0.123447, + "nauc_precision_at_1000_diff1": 0.121016, + "nauc_mrr_at_1_max": 0.137189, + "nauc_mrr_at_1_std": -0.08811, + "nauc_mrr_at_1_diff1": 0.163713, + "nauc_mrr_at_3_max": 0.07864, + "nauc_mrr_at_3_std": -0.163752, + "nauc_mrr_at_3_diff1": 0.177341, + "nauc_mrr_at_5_max": 0.093464, + "nauc_mrr_at_5_std": -0.153016, + "nauc_mrr_at_5_diff1": 0.178017, + "nauc_mrr_at_10_max": 0.081879, + "nauc_mrr_at_10_std": -0.1613, + "nauc_mrr_at_10_diff1": 0.201439, + "nauc_mrr_at_20_max": 0.072088, + "nauc_mrr_at_20_std": -0.170078, + "nauc_mrr_at_20_diff1": 0.20408, + "nauc_mrr_at_100_max": 0.072651, + "nauc_mrr_at_100_std": -0.174157, + "nauc_mrr_at_100_diff1": 0.19837, + "nauc_mrr_at_1000_max": 0.073738, + "nauc_mrr_at_1000_std": -0.172803, + "nauc_mrr_at_1000_diff1": 0.198873, + "main_score": 0.15523, + "hf_subset": "Biology", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.27273, + "ndcg_at_3": 0.28239, + "ndcg_at_5": 0.30915, + "ndcg_at_10": 0.36162, + "ndcg_at_20": 0.39404, + "ndcg_at_100": 0.44338, + "ndcg_at_1000": 0.47546, + "map_at_1": 0.13919, + "map_at_3": 0.20787, + "map_at_5": 0.23782, + "map_at_10": 0.26641, + "map_at_20": 0.278, + "map_at_100": 0.28924, + "map_at_1000": 0.29203, + "recall_at_1": 0.13919, + "recall_at_3": 0.26424, + "recall_at_5": 0.34865, + "recall_at_10": 0.49437, + "recall_at_20": 0.593, + "recall_at_100": 0.77454, + "recall_at_1000": 0.94573, + "precision_at_1": 0.27273, + "precision_at_3": 0.19048, + "precision_at_5": 0.15584, + "precision_at_10": 0.11558, + "precision_at_20": 0.07208, + "precision_at_100": 0.02156, + "precision_at_1000": 0.00282, + "mrr_at_1": 0.272727, + "mrr_at_3": 0.361472, + "mrr_at_5": 0.379004, + "mrr_at_10": 0.401144, + "mrr_at_20": 0.405827, + "mrr_at_100": 0.408384, + "mrr_at_1000": 0.408659, + "nauc_ndcg_at_1_max": -0.082348, + "nauc_ndcg_at_1_std": -0.009264, + "nauc_ndcg_at_1_diff1": -0.027691, + "nauc_ndcg_at_3_max": 0.087519, + "nauc_ndcg_at_3_std": 0.037376, + "nauc_ndcg_at_3_diff1": 0.068376, + "nauc_ndcg_at_5_max": 0.098692, + "nauc_ndcg_at_5_std": -0.013028, + "nauc_ndcg_at_5_diff1": 0.042721, + "nauc_ndcg_at_10_max": 0.114417, + "nauc_ndcg_at_10_std": 0.021142, + "nauc_ndcg_at_10_diff1": 0.037894, + "nauc_ndcg_at_20_max": 0.089621, + "nauc_ndcg_at_20_std": 0.026568, + "nauc_ndcg_at_20_diff1": -0.035275, + "nauc_ndcg_at_100_max": 0.059175, + "nauc_ndcg_at_100_std": 0.030595, + "nauc_ndcg_at_100_diff1": -0.062205, + "nauc_ndcg_at_1000_max": 0.054459, + "nauc_ndcg_at_1000_std": 0.039675, + "nauc_ndcg_at_1000_diff1": -0.041997, + "nauc_map_at_1_max": -0.063688, + "nauc_map_at_1_std": -0.110593, + "nauc_map_at_1_diff1": 0.154514, + "nauc_map_at_3_max": 0.073178, + "nauc_map_at_3_std": -0.003097, + "nauc_map_at_3_diff1": 0.13016, + "nauc_map_at_5_max": 0.095376, + "nauc_map_at_5_std": -0.010931, + "nauc_map_at_5_diff1": 0.096749, + "nauc_map_at_10_max": 0.086818, + "nauc_map_at_10_std": -0.008646, + "nauc_map_at_10_diff1": 0.087877, + "nauc_map_at_20_max": 0.081768, + "nauc_map_at_20_std": -0.002996, + "nauc_map_at_20_diff1": 0.057881, + "nauc_map_at_100_max": 0.072339, + "nauc_map_at_100_std": -0.003247, + "nauc_map_at_100_diff1": 0.045529, + "nauc_map_at_1000_max": 0.071114, + "nauc_map_at_1000_std": -0.001218, + "nauc_map_at_1000_diff1": 0.046154, + "nauc_recall_at_1_max": -0.063688, + "nauc_recall_at_1_std": -0.110593, + "nauc_recall_at_1_diff1": 0.154514, + "nauc_recall_at_3_max": 0.175504, + "nauc_recall_at_3_std": 0.028333, + "nauc_recall_at_3_diff1": 0.143905, + "nauc_recall_at_5_max": 0.171812, + "nauc_recall_at_5_std": -0.035098, + "nauc_recall_at_5_diff1": 0.056208, + "nauc_recall_at_10_max": 0.20442, + "nauc_recall_at_10_std": 0.04698, + "nauc_recall_at_10_diff1": 0.076513, + "nauc_recall_at_20_max": 0.134021, + "nauc_recall_at_20_std": 0.055781, + "nauc_recall_at_20_diff1": -0.127236, + "nauc_recall_at_100_max": -0.003792, + "nauc_recall_at_100_std": 0.042217, + "nauc_recall_at_100_diff1": -0.268943, + "nauc_recall_at_1000_max": -0.093103, + "nauc_recall_at_1000_std": 0.161049, + "nauc_recall_at_1000_diff1": -0.071175, + "nauc_precision_at_1_max": -0.082348, + "nauc_precision_at_1_std": -0.009264, + "nauc_precision_at_1_diff1": -0.027691, + "nauc_precision_at_3_max": 0.114503, + "nauc_precision_at_3_std": 0.14029, + "nauc_precision_at_3_diff1": -0.077456, + "nauc_precision_at_5_max": 0.105985, + "nauc_precision_at_5_std": 0.051547, + "nauc_precision_at_5_diff1": -0.152162, + "nauc_precision_at_10_max": 0.0469, + "nauc_precision_at_10_std": 0.109368, + "nauc_precision_at_10_diff1": -0.260808, + "nauc_precision_at_20_max": -0.026378, + "nauc_precision_at_20_std": 0.12229, + "nauc_precision_at_20_diff1": -0.399066, + "nauc_precision_at_100_max": -0.077484, + "nauc_precision_at_100_std": 0.135208, + "nauc_precision_at_100_diff1": -0.338875, + "nauc_precision_at_1000_max": -0.099466, + "nauc_precision_at_1000_std": 0.127953, + "nauc_precision_at_1000_diff1": -0.227243, + "nauc_mrr_at_1_max": -0.082348, + "nauc_mrr_at_1_std": -0.009264, + "nauc_mrr_at_1_diff1": -0.027691, + "nauc_mrr_at_3_max": 0.038357, + "nauc_mrr_at_3_std": 0.046907, + "nauc_mrr_at_3_diff1": -0.01772, + "nauc_mrr_at_5_max": 0.022751, + "nauc_mrr_at_5_std": 0.013754, + "nauc_mrr_at_5_diff1": -0.037839, + "nauc_mrr_at_10_max": 0.032486, + "nauc_mrr_at_10_std": 0.033919, + "nauc_mrr_at_10_diff1": -0.043146, + "nauc_mrr_at_20_max": 0.027922, + "nauc_mrr_at_20_std": 0.031883, + "nauc_mrr_at_20_diff1": -0.04839, + "nauc_mrr_at_100_max": 0.025617, + "nauc_mrr_at_100_std": 0.030089, + "nauc_mrr_at_100_diff1": -0.045743, + "nauc_mrr_at_1000_max": 0.025687, + "nauc_mrr_at_1000_std": 0.030135, + "nauc_mrr_at_1000_diff1": -0.045812, + "main_score": 0.36162, + "hf_subset": "Bioinformatics", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.30682, + "ndcg_at_3": 0.32315, + "ndcg_at_5": 0.34845, + "ndcg_at_10": 0.38395, + "ndcg_at_20": 0.42899, + "ndcg_at_100": 0.48331, + "ndcg_at_1000": 0.50912, + "map_at_1": 0.16935, + "map_at_3": 0.25401, + "map_at_5": 0.2804, + "map_at_10": 0.30124, + "map_at_20": 0.31973, + "map_at_100": 0.33131, + "map_at_1000": 0.33316, + "recall_at_1": 0.16935, + "recall_at_3": 0.32078, + "recall_at_5": 0.40152, + "recall_at_10": 0.48573, + "recall_at_20": 0.61642, + "recall_at_100": 0.83107, + "recall_at_1000": 0.97243, + "precision_at_1": 0.30682, + "precision_at_3": 0.21212, + "precision_at_5": 0.16364, + "precision_at_10": 0.11136, + "precision_at_20": 0.07557, + "precision_at_100": 0.02182, + "precision_at_1000": 0.00269, + "mrr_at_1": 0.306818, + "mrr_at_3": 0.399621, + "mrr_at_5": 0.416667, + "mrr_at_10": 0.427791, + "mrr_at_20": 0.435802, + "mrr_at_100": 0.439492, + "mrr_at_1000": 0.439759, + "nauc_ndcg_at_1_max": 0.193745, + "nauc_ndcg_at_1_std": 0.040073, + "nauc_ndcg_at_1_diff1": 0.035287, + "nauc_ndcg_at_3_max": 0.214278, + "nauc_ndcg_at_3_std": -0.018711, + "nauc_ndcg_at_3_diff1": 0.13384, + "nauc_ndcg_at_5_max": 0.250019, + "nauc_ndcg_at_5_std": -0.020599, + "nauc_ndcg_at_5_diff1": 0.131115, + "nauc_ndcg_at_10_max": 0.28836, + "nauc_ndcg_at_10_std": -0.018975, + "nauc_ndcg_at_10_diff1": 0.114983, + "nauc_ndcg_at_20_max": 0.283607, + "nauc_ndcg_at_20_std": -0.03572, + "nauc_ndcg_at_20_diff1": 0.116425, + "nauc_ndcg_at_100_max": 0.284109, + "nauc_ndcg_at_100_std": -0.003873, + "nauc_ndcg_at_100_diff1": 0.123498, + "nauc_ndcg_at_1000_max": 0.27442, + "nauc_ndcg_at_1000_std": 0.006788, + "nauc_ndcg_at_1000_diff1": 0.121073, + "nauc_map_at_1_max": 0.079302, + "nauc_map_at_1_std": -0.070075, + "nauc_map_at_1_diff1": 0.132368, + "nauc_map_at_3_max": 0.174659, + "nauc_map_at_3_std": -0.028023, + "nauc_map_at_3_diff1": 0.198441, + "nauc_map_at_5_max": 0.196905, + "nauc_map_at_5_std": -0.030487, + "nauc_map_at_5_diff1": 0.171764, + "nauc_map_at_10_max": 0.224483, + "nauc_map_at_10_std": -0.024016, + "nauc_map_at_10_diff1": 0.15538, + "nauc_map_at_20_max": 0.223835, + "nauc_map_at_20_std": -0.037168, + "nauc_map_at_20_diff1": 0.147906, + "nauc_map_at_100_max": 0.226777, + "nauc_map_at_100_std": -0.030628, + "nauc_map_at_100_diff1": 0.149042, + "nauc_map_at_1000_max": 0.226619, + "nauc_map_at_1000_std": -0.029091, + "nauc_map_at_1000_diff1": 0.149395, + "nauc_recall_at_1_max": 0.079302, + "nauc_recall_at_1_std": -0.070075, + "nauc_recall_at_1_diff1": 0.132368, + "nauc_recall_at_3_max": 0.213536, + "nauc_recall_at_3_std": -0.05598, + "nauc_recall_at_3_diff1": 0.207572, + "nauc_recall_at_5_max": 0.289884, + "nauc_recall_at_5_std": -0.046818, + "nauc_recall_at_5_diff1": 0.16811, + "nauc_recall_at_10_max": 0.369725, + "nauc_recall_at_10_std": -0.047284, + "nauc_recall_at_10_diff1": 0.125413, + "nauc_recall_at_20_max": 0.325573, + "nauc_recall_at_20_std": -0.12504, + "nauc_recall_at_20_diff1": 0.143917, + "nauc_recall_at_100_max": 0.31294, + "nauc_recall_at_100_std": -0.073676, + "nauc_recall_at_100_diff1": 0.156653, + "nauc_recall_at_1000_max": 0.159189, + "nauc_recall_at_1000_std": -0.141772, + "nauc_recall_at_1000_diff1": 0.406303, + "nauc_precision_at_1_max": 0.193745, + "nauc_precision_at_1_std": 0.040073, + "nauc_precision_at_1_diff1": 0.035287, + "nauc_precision_at_3_max": 0.336425, + "nauc_precision_at_3_std": 0.132047, + "nauc_precision_at_3_diff1": 0.032793, + "nauc_precision_at_5_max": 0.379867, + "nauc_precision_at_5_std": 0.134052, + "nauc_precision_at_5_diff1": -0.027787, + "nauc_precision_at_10_max": 0.38892, + "nauc_precision_at_10_std": 0.0944, + "nauc_precision_at_10_diff1": -0.094108, + "nauc_precision_at_20_max": 0.301304, + "nauc_precision_at_20_std": 0.062721, + "nauc_precision_at_20_diff1": -0.102637, + "nauc_precision_at_100_max": 0.233607, + "nauc_precision_at_100_std": 0.175706, + "nauc_precision_at_100_diff1": -0.048542, + "nauc_precision_at_1000_max": 0.116567, + "nauc_precision_at_1000_std": 0.202155, + "nauc_precision_at_1000_diff1": -0.113067, + "nauc_mrr_at_1_max": 0.193745, + "nauc_mrr_at_1_std": 0.040073, + "nauc_mrr_at_1_diff1": 0.035287, + "nauc_mrr_at_3_max": 0.224866, + "nauc_mrr_at_3_std": -0.003314, + "nauc_mrr_at_3_diff1": 0.023064, + "nauc_mrr_at_5_max": 0.255181, + "nauc_mrr_at_5_std": 0.013521, + "nauc_mrr_at_5_diff1": 0.024056, + "nauc_mrr_at_10_max": 0.264859, + "nauc_mrr_at_10_std": 0.01291, + "nauc_mrr_at_10_diff1": 0.027, + "nauc_mrr_at_20_max": 0.261815, + "nauc_mrr_at_20_std": 0.018058, + "nauc_mrr_at_20_diff1": 0.036335, + "nauc_mrr_at_100_max": 0.257998, + "nauc_mrr_at_100_std": 0.018542, + "nauc_mrr_at_100_diff1": 0.035152, + "nauc_mrr_at_1000_max": 0.25785, + "nauc_mrr_at_1000_std": 0.018227, + "nauc_mrr_at_1000_diff1": 0.035532, + "main_score": 0.38395, + "hf_subset": "Medical-Sciences", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.03093, + "ndcg_at_3": 0.0411, + "ndcg_at_5": 0.04338, + "ndcg_at_10": 0.04591, + "ndcg_at_20": 0.05652, + "ndcg_at_100": 0.07803, + "ndcg_at_1000": 0.12952, + "map_at_1": 0.01581, + "map_at_3": 0.02876, + "map_at_5": 0.03219, + "map_at_10": 0.03337, + "map_at_20": 0.03573, + "map_at_100": 0.0385, + "map_at_1000": 0.04032, + "recall_at_1": 0.01581, + "recall_at_3": 0.04563, + "recall_at_5": 0.05422, + "recall_at_10": 0.05972, + "recall_at_20": 0.09203, + "recall_at_100": 0.18716, + "recall_at_1000": 0.50236, + "precision_at_1": 0.03093, + "precision_at_3": 0.02749, + "precision_at_5": 0.02062, + "precision_at_10": 0.01237, + "precision_at_20": 0.01082, + "precision_at_100": 0.00474, + "precision_at_1000": 0.00142, + "mrr_at_1": 0.030928, + "mrr_at_3": 0.053265, + "mrr_at_5": 0.055842, + "mrr_at_10": 0.057315, + "mrr_at_20": 0.062065, + "mrr_at_100": 0.064353, + "mrr_at_1000": 0.065854, + "nauc_ndcg_at_1_max": 0.063353, + "nauc_ndcg_at_1_std": -0.154868, + "nauc_ndcg_at_1_diff1": -0.127943, + "nauc_ndcg_at_3_max": -0.071377, + "nauc_ndcg_at_3_std": -0.031092, + "nauc_ndcg_at_3_diff1": -0.310818, + "nauc_ndcg_at_5_max": -0.029859, + "nauc_ndcg_at_5_std": 0.0266, + "nauc_ndcg_at_5_diff1": -0.3125, + "nauc_ndcg_at_10_max": -0.00574, + "nauc_ndcg_at_10_std": 0.050877, + "nauc_ndcg_at_10_diff1": -0.293722, + "nauc_ndcg_at_20_max": 0.014712, + "nauc_ndcg_at_20_std": 0.111725, + "nauc_ndcg_at_20_diff1": -0.193271, + "nauc_ndcg_at_100_max": 0.052746, + "nauc_ndcg_at_100_std": 0.158148, + "nauc_ndcg_at_100_diff1": -0.185674, + "nauc_ndcg_at_1000_max": 0.080763, + "nauc_ndcg_at_1000_std": 0.181922, + "nauc_ndcg_at_1000_diff1": -0.14101, + "nauc_map_at_1_max": 0.133569, + "nauc_map_at_1_std": -0.104544, + "nauc_map_at_1_diff1": -0.342843, + "nauc_map_at_3_max": -0.015455, + "nauc_map_at_3_std": -0.030725, + "nauc_map_at_3_diff1": -0.367599, + "nauc_map_at_5_max": -0.010941, + "nauc_map_at_5_std": 0.041485, + "nauc_map_at_5_diff1": -0.365932, + "nauc_map_at_10_max": -0.007733, + "nauc_map_at_10_std": 0.048136, + "nauc_map_at_10_diff1": -0.352082, + "nauc_map_at_20_max": -0.00148, + "nauc_map_at_20_std": 0.068789, + "nauc_map_at_20_diff1": -0.313437, + "nauc_map_at_100_max": 0.005572, + "nauc_map_at_100_std": 0.078007, + "nauc_map_at_100_diff1": -0.299576, + "nauc_map_at_1000_max": 0.008573, + "nauc_map_at_1000_std": 0.080325, + "nauc_map_at_1000_diff1": -0.295496, + "nauc_recall_at_1_max": 0.133569, + "nauc_recall_at_1_std": -0.104544, + "nauc_recall_at_1_diff1": -0.342843, + "nauc_recall_at_3_max": -0.075674, + "nauc_recall_at_3_std": 0.005817, + "nauc_recall_at_3_diff1": -0.362321, + "nauc_recall_at_5_max": -0.05002, + "nauc_recall_at_5_std": 0.073526, + "nauc_recall_at_5_diff1": -0.339266, + "nauc_recall_at_10_max": -0.007803, + "nauc_recall_at_10_std": 0.113243, + "nauc_recall_at_10_diff1": -0.308846, + "nauc_recall_at_20_max": 0.038544, + "nauc_recall_at_20_std": 0.229884, + "nauc_recall_at_20_diff1": -0.07518, + "nauc_recall_at_100_max": 0.113237, + "nauc_recall_at_100_std": 0.282072, + "nauc_recall_at_100_diff1": -0.104113, + "nauc_recall_at_1000_max": 0.197645, + "nauc_recall_at_1000_std": 0.322173, + "nauc_recall_at_1000_diff1": 0.028744, + "nauc_precision_at_1_max": 0.063353, + "nauc_precision_at_1_std": -0.154868, + "nauc_precision_at_1_diff1": -0.127943, + "nauc_precision_at_3_max": -0.112285, + "nauc_precision_at_3_std": -0.001059, + "nauc_precision_at_3_diff1": -0.260322, + "nauc_precision_at_5_max": -0.064659, + "nauc_precision_at_5_std": 0.057443, + "nauc_precision_at_5_diff1": -0.233597, + "nauc_precision_at_10_max": -0.018655, + "nauc_precision_at_10_std": 0.104517, + "nauc_precision_at_10_diff1": -0.19262, + "nauc_precision_at_20_max": 0.027579, + "nauc_precision_at_20_std": 0.184997, + "nauc_precision_at_20_diff1": -0.036527, + "nauc_precision_at_100_max": 0.126146, + "nauc_precision_at_100_std": 0.265476, + "nauc_precision_at_100_diff1": -0.085771, + "nauc_precision_at_1000_max": 0.067002, + "nauc_precision_at_1000_std": 0.189296, + "nauc_precision_at_1000_diff1": -0.045615, + "nauc_mrr_at_1_max": 0.063353, + "nauc_mrr_at_1_std": -0.154868, + "nauc_mrr_at_1_diff1": -0.127943, + "nauc_mrr_at_3_max": -0.052754, + "nauc_mrr_at_3_std": -0.052022, + "nauc_mrr_at_3_diff1": -0.225353, + "nauc_mrr_at_5_max": -0.035371, + "nauc_mrr_at_5_std": -0.068872, + "nauc_mrr_at_5_diff1": -0.200003, + "nauc_mrr_at_10_max": -0.008766, + "nauc_mrr_at_10_std": -0.041406, + "nauc_mrr_at_10_diff1": -0.196719, + "nauc_mrr_at_20_max": -0.000765, + "nauc_mrr_at_20_std": -0.01058, + "nauc_mrr_at_20_diff1": -0.176066, + "nauc_mrr_at_100_max": -0.002869, + "nauc_mrr_at_100_std": -0.012419, + "nauc_mrr_at_100_diff1": -0.177429, + "nauc_mrr_at_1000_max": -0.001722, + "nauc_mrr_at_1000_std": -0.011012, + "nauc_mrr_at_1000_diff1": -0.177441, + "main_score": 0.04591, + "hf_subset": "MedXpertQA-Exam", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.05085, + "ndcg_at_3": 0.0416, + "ndcg_at_5": 0.05113, + "ndcg_at_10": 0.06213, + "ndcg_at_20": 0.07155, + "ndcg_at_100": 0.1014, + "ndcg_at_1000": 0.15876, + "map_at_1": 0.01985, + "map_at_3": 0.02512, + "map_at_5": 0.03459, + "map_at_10": 0.03944, + "map_at_20": 0.04275, + "map_at_100": 0.04675, + "map_at_1000": 0.04918, + "recall_at_1": 0.01985, + "recall_at_3": 0.02896, + "recall_at_5": 0.05644, + "recall_at_10": 0.0832, + "recall_at_20": 0.10773, + "recall_at_100": 0.22014, + "recall_at_1000": 0.52326, + "precision_at_1": 0.05085, + "precision_at_3": 0.03107, + "precision_at_5": 0.03559, + "precision_at_10": 0.02712, + "precision_at_20": 0.01822, + "precision_at_100": 0.00805, + "precision_at_1000": 0.00218, + "mrr_at_1": 0.050847, + "mrr_at_3": 0.066384, + "mrr_at_5": 0.075282, + "mrr_at_10": 0.083202, + "mrr_at_20": 0.085919, + "mrr_at_100": 0.089682, + "mrr_at_1000": 0.091089, + "nauc_ndcg_at_1_max": -0.132794, + "nauc_ndcg_at_1_std": 0.025103, + "nauc_ndcg_at_1_diff1": 0.142831, + "nauc_ndcg_at_3_max": -0.044596, + "nauc_ndcg_at_3_std": 0.105209, + "nauc_ndcg_at_3_diff1": 0.02917, + "nauc_ndcg_at_5_max": -0.035984, + "nauc_ndcg_at_5_std": 0.088965, + "nauc_ndcg_at_5_diff1": 0.038039, + "nauc_ndcg_at_10_max": -0.066296, + "nauc_ndcg_at_10_std": 0.138248, + "nauc_ndcg_at_10_diff1": 0.026675, + "nauc_ndcg_at_20_max": -0.003683, + "nauc_ndcg_at_20_std": 0.223134, + "nauc_ndcg_at_20_diff1": 0.028008, + "nauc_ndcg_at_100_max": -0.04869, + "nauc_ndcg_at_100_std": 0.265541, + "nauc_ndcg_at_100_diff1": -0.016902, + "nauc_ndcg_at_1000_max": -0.039701, + "nauc_ndcg_at_1000_std": 0.268838, + "nauc_ndcg_at_1000_diff1": -0.007946, + "nauc_map_at_1_max": -0.288589, + "nauc_map_at_1_std": 0.004342, + "nauc_map_at_1_diff1": -0.002927, + "nauc_map_at_3_max": -0.109017, + "nauc_map_at_3_std": 0.067695, + "nauc_map_at_3_diff1": 0.037958, + "nauc_map_at_5_max": -0.037185, + "nauc_map_at_5_std": 0.095649, + "nauc_map_at_5_diff1": 0.059187, + "nauc_map_at_10_max": -0.041835, + "nauc_map_at_10_std": 0.126995, + "nauc_map_at_10_diff1": 0.040818, + "nauc_map_at_20_max": -0.010959, + "nauc_map_at_20_std": 0.178007, + "nauc_map_at_20_diff1": 0.051971, + "nauc_map_at_100_max": -0.019962, + "nauc_map_at_100_std": 0.194813, + "nauc_map_at_100_diff1": 0.039881, + "nauc_map_at_1000_max": -0.021585, + "nauc_map_at_1000_std": 0.197207, + "nauc_map_at_1000_diff1": 0.036776, + "nauc_recall_at_1_max": -0.288589, + "nauc_recall_at_1_std": 0.004342, + "nauc_recall_at_1_diff1": -0.002927, + "nauc_recall_at_3_max": -0.040005, + "nauc_recall_at_3_std": 0.13151, + "nauc_recall_at_3_diff1": -0.007052, + "nauc_recall_at_5_max": -0.006853, + "nauc_recall_at_5_std": 0.088112, + "nauc_recall_at_5_diff1": 0.030998, + "nauc_recall_at_10_max": -0.087521, + "nauc_recall_at_10_std": 0.14102, + "nauc_recall_at_10_diff1": 0.032631, + "nauc_recall_at_20_max": 0.051522, + "nauc_recall_at_20_std": 0.299015, + "nauc_recall_at_20_diff1": 0.018264, + "nauc_recall_at_100_max": -0.055237, + "nauc_recall_at_100_std": 0.346265, + "nauc_recall_at_100_diff1": -0.06595, + "nauc_recall_at_1000_max": -0.035636, + "nauc_recall_at_1000_std": 0.315919, + "nauc_recall_at_1000_diff1": -0.011725, + "nauc_precision_at_1_max": -0.132794, + "nauc_precision_at_1_std": 0.025103, + "nauc_precision_at_1_diff1": 0.142831, + "nauc_precision_at_3_max": 0.102631, + "nauc_precision_at_3_std": 0.176676, + "nauc_precision_at_3_diff1": 0.044967, + "nauc_precision_at_5_max": 0.080514, + "nauc_precision_at_5_std": 0.150463, + "nauc_precision_at_5_diff1": 0.082893, + "nauc_precision_at_10_max": -0.024514, + "nauc_precision_at_10_std": 0.225683, + "nauc_precision_at_10_diff1": -0.012407, + "nauc_precision_at_20_max": 0.059743, + "nauc_precision_at_20_std": 0.362097, + "nauc_precision_at_20_diff1": 0.016138, + "nauc_precision_at_100_max": -0.055613, + "nauc_precision_at_100_std": 0.368129, + "nauc_precision_at_100_diff1": -0.065689, + "nauc_precision_at_1000_max": -0.027027, + "nauc_precision_at_1000_std": 0.264027, + "nauc_precision_at_1000_diff1": -0.047019, + "nauc_mrr_at_1_max": -0.132794, + "nauc_mrr_at_1_std": 0.025103, + "nauc_mrr_at_1_diff1": 0.142831, + "nauc_mrr_at_3_max": -0.063903, + "nauc_mrr_at_3_std": 0.10602, + "nauc_mrr_at_3_diff1": 0.023964, + "nauc_mrr_at_5_max": -0.077605, + "nauc_mrr_at_5_std": 0.067243, + "nauc_mrr_at_5_diff1": 0.024887, + "nauc_mrr_at_10_max": -0.108714, + "nauc_mrr_at_10_std": 0.096231, + "nauc_mrr_at_10_diff1": 0.007736, + "nauc_mrr_at_20_max": -0.093951, + "nauc_mrr_at_20_std": 0.113136, + "nauc_mrr_at_20_diff1": 0.006158, + "nauc_mrr_at_100_max": -0.098477, + "nauc_mrr_at_100_std": 0.114566, + "nauc_mrr_at_100_diff1": 0.001147, + "nauc_mrr_at_1000_max": -0.096681, + "nauc_mrr_at_1000_std": 0.114212, + "nauc_mrr_at_1000_diff1": 0.003841, + "main_score": 0.06213, + "hf_subset": "MedQA-Diag", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.15333, + "ndcg_at_3": 0.14994, + "ndcg_at_5": 0.16202, + "ndcg_at_10": 0.17719, + "ndcg_at_20": 0.2064, + "ndcg_at_100": 0.2483, + "ndcg_at_1000": 0.2889, + "map_at_1": 0.08933, + "map_at_3": 0.11826, + "map_at_5": 0.12848, + "map_at_10": 0.1353, + "map_at_20": 0.14341, + "map_at_100": 0.15011, + "map_at_1000": 0.1517, + "recall_at_1": 0.08933, + "recall_at_3": 0.14411, + "recall_at_5": 0.18356, + "recall_at_10": 0.222, + "recall_at_20": 0.32589, + "recall_at_100": 0.51311, + "recall_at_1000": 0.79089, + "precision_at_1": 0.15333, + "precision_at_3": 0.09556, + "precision_at_5": 0.07067, + "precision_at_10": 0.04333, + "precision_at_20": 0.03033, + "precision_at_100": 0.01007, + "precision_at_1000": 0.00157, + "mrr_at_1": 0.153333, + "mrr_at_3": 0.2, + "mrr_at_5": 0.212, + "mrr_at_10": 0.218275, + "mrr_at_20": 0.226633, + "mrr_at_100": 0.230998, + "mrr_at_1000": 0.231883, + "nauc_ndcg_at_1_max": 0.289301, + "nauc_ndcg_at_1_std": 0.00821, + "nauc_ndcg_at_1_diff1": 0.385082, + "nauc_ndcg_at_3_max": 0.339525, + "nauc_ndcg_at_3_std": 0.02163, + "nauc_ndcg_at_3_diff1": 0.290447, + "nauc_ndcg_at_5_max": 0.283409, + "nauc_ndcg_at_5_std": 0.00928, + "nauc_ndcg_at_5_diff1": 0.271381, + "nauc_ndcg_at_10_max": 0.27158, + "nauc_ndcg_at_10_std": 0.018232, + "nauc_ndcg_at_10_diff1": 0.265924, + "nauc_ndcg_at_20_max": 0.262893, + "nauc_ndcg_at_20_std": 0.029102, + "nauc_ndcg_at_20_diff1": 0.2957, + "nauc_ndcg_at_100_max": 0.284341, + "nauc_ndcg_at_100_std": 0.085407, + "nauc_ndcg_at_100_diff1": 0.275823, + "nauc_ndcg_at_1000_max": 0.30257, + "nauc_ndcg_at_1000_std": 0.097917, + "nauc_ndcg_at_1000_diff1": 0.255468, + "nauc_map_at_1_max": 0.288259, + "nauc_map_at_1_std": 0.040245, + "nauc_map_at_1_diff1": 0.320348, + "nauc_map_at_3_max": 0.348107, + "nauc_map_at_3_std": 0.033943, + "nauc_map_at_3_diff1": 0.318978, + "nauc_map_at_5_max": 0.318333, + "nauc_map_at_5_std": 0.02007, + "nauc_map_at_5_diff1": 0.301351, + "nauc_map_at_10_max": 0.309463, + "nauc_map_at_10_std": 0.02393, + "nauc_map_at_10_diff1": 0.295983, + "nauc_map_at_20_max": 0.305749, + "nauc_map_at_20_std": 0.030204, + "nauc_map_at_20_diff1": 0.308662, + "nauc_map_at_100_max": 0.307921, + "nauc_map_at_100_std": 0.040939, + "nauc_map_at_100_diff1": 0.302431, + "nauc_map_at_1000_max": 0.309212, + "nauc_map_at_1000_std": 0.042444, + "nauc_map_at_1000_diff1": 0.300814, + "nauc_recall_at_1_max": 0.288259, + "nauc_recall_at_1_std": 0.040245, + "nauc_recall_at_1_diff1": 0.320348, + "nauc_recall_at_3_max": 0.328178, + "nauc_recall_at_3_std": 0.044702, + "nauc_recall_at_3_diff1": 0.270488, + "nauc_recall_at_5_max": 0.198594, + "nauc_recall_at_5_std": -0.011649, + "nauc_recall_at_5_diff1": 0.192189, + "nauc_recall_at_10_max": 0.16748, + "nauc_recall_at_10_std": 0.01958, + "nauc_recall_at_10_diff1": 0.182416, + "nauc_recall_at_20_max": 0.108174, + "nauc_recall_at_20_std": 0.024079, + "nauc_recall_at_20_diff1": 0.240939, + "nauc_recall_at_100_max": 0.16568, + "nauc_recall_at_100_std": 0.19047, + "nauc_recall_at_100_diff1": 0.191626, + "nauc_recall_at_1000_max": 0.204164, + "nauc_recall_at_1000_std": 0.337548, + "nauc_recall_at_1000_diff1": 0.021968, + "nauc_precision_at_1_max": 0.289301, + "nauc_precision_at_1_std": 0.00821, + "nauc_precision_at_1_diff1": 0.385082, + "nauc_precision_at_3_max": 0.3821, + "nauc_precision_at_3_std": 0.00894, + "nauc_precision_at_3_diff1": 0.259073, + "nauc_precision_at_5_max": 0.294823, + "nauc_precision_at_5_std": -0.007218, + "nauc_precision_at_5_diff1": 0.227878, + "nauc_precision_at_10_max": 0.26481, + "nauc_precision_at_10_std": -0.017532, + "nauc_precision_at_10_diff1": 0.199691, + "nauc_precision_at_20_max": 0.289677, + "nauc_precision_at_20_std": 0.031906, + "nauc_precision_at_20_diff1": 0.268527, + "nauc_precision_at_100_max": 0.321923, + "nauc_precision_at_100_std": 0.183058, + "nauc_precision_at_100_diff1": 0.158945, + "nauc_precision_at_1000_max": 0.281829, + "nauc_precision_at_1000_std": 0.177019, + "nauc_precision_at_1000_diff1": -0.024554, + "nauc_mrr_at_1_max": 0.289301, + "nauc_mrr_at_1_std": 0.00821, + "nauc_mrr_at_1_diff1": 0.385082, + "nauc_mrr_at_3_max": 0.308311, + "nauc_mrr_at_3_std": 0.00996, + "nauc_mrr_at_3_diff1": 0.298559, + "nauc_mrr_at_5_max": 0.280089, + "nauc_mrr_at_5_std": -0.003413, + "nauc_mrr_at_5_diff1": 0.285801, + "nauc_mrr_at_10_max": 0.28214, + "nauc_mrr_at_10_std": 0.000909, + "nauc_mrr_at_10_diff1": 0.286859, + "nauc_mrr_at_20_max": 0.281749, + "nauc_mrr_at_20_std": 0.004351, + "nauc_mrr_at_20_diff1": 0.289947, + "nauc_mrr_at_100_max": 0.283445, + "nauc_mrr_at_100_std": 0.011698, + "nauc_mrr_at_100_diff1": 0.286392, + "nauc_mrr_at_1000_max": 0.283251, + "nauc_mrr_at_1000_std": 0.011097, + "nauc_mrr_at_1000_diff1": 0.286479, + "main_score": 0.17719, + "hf_subset": "PMC-Treatment", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.09649, + "ndcg_at_3": 0.08309, + "ndcg_at_5": 0.09055, + "ndcg_at_10": 0.11269, + "ndcg_at_20": 0.12364, + "ndcg_at_100": 0.16348, + "ndcg_at_1000": 0.21874, + "map_at_1": 0.04678, + "map_at_3": 0.06798, + "map_at_5": 0.07113, + "map_at_10": 0.07894, + "map_at_20": 0.08202, + "map_at_100": 0.08802, + "map_at_1000": 0.09039, + "recall_at_1": 0.04678, + "recall_at_3": 0.08333, + "recall_at_5": 0.09649, + "recall_at_10": 0.15351, + "recall_at_20": 0.18787, + "recall_at_100": 0.36038, + "recall_at_1000": 0.73026, + "precision_at_1": 0.09649, + "precision_at_3": 0.05556, + "precision_at_5": 0.04035, + "precision_at_10": 0.03246, + "precision_at_20": 0.02061, + "precision_at_100": 0.00825, + "precision_at_1000": 0.00157, + "mrr_at_1": 0.096491, + "mrr_at_3": 0.114035, + "mrr_at_5": 0.122368, + "mrr_at_10": 0.135923, + "mrr_at_20": 0.138042, + "mrr_at_100": 0.143047, + "mrr_at_1000": 0.144553, + "nauc_ndcg_at_1_max": 0.183331, + "nauc_ndcg_at_1_std": 0.102548, + "nauc_ndcg_at_1_diff1": 0.215166, + "nauc_ndcg_at_3_max": 0.132033, + "nauc_ndcg_at_3_std": 0.1086, + "nauc_ndcg_at_3_diff1": 0.227536, + "nauc_ndcg_at_5_max": 0.096856, + "nauc_ndcg_at_5_std": 0.092915, + "nauc_ndcg_at_5_diff1": 0.198197, + "nauc_ndcg_at_10_max": 0.059408, + "nauc_ndcg_at_10_std": 0.111952, + "nauc_ndcg_at_10_diff1": 0.142167, + "nauc_ndcg_at_20_max": 0.062828, + "nauc_ndcg_at_20_std": 0.101527, + "nauc_ndcg_at_20_diff1": 0.142471, + "nauc_ndcg_at_100_max": 0.083531, + "nauc_ndcg_at_100_std": 0.175089, + "nauc_ndcg_at_100_diff1": 0.151455, + "nauc_ndcg_at_1000_max": 0.097876, + "nauc_ndcg_at_1000_std": 0.16494, + "nauc_ndcg_at_1000_diff1": 0.13139, + "nauc_map_at_1_max": 0.201437, + "nauc_map_at_1_std": 0.078649, + "nauc_map_at_1_diff1": 0.224644, + "nauc_map_at_3_max": 0.159042, + "nauc_map_at_3_std": 0.115235, + "nauc_map_at_3_diff1": 0.230389, + "nauc_map_at_5_max": 0.140282, + "nauc_map_at_5_std": 0.106865, + "nauc_map_at_5_diff1": 0.215648, + "nauc_map_at_10_max": 0.119698, + "nauc_map_at_10_std": 0.117679, + "nauc_map_at_10_diff1": 0.187, + "nauc_map_at_20_max": 0.120692, + "nauc_map_at_20_std": 0.113251, + "nauc_map_at_20_diff1": 0.187936, + "nauc_map_at_100_max": 0.120871, + "nauc_map_at_100_std": 0.128126, + "nauc_map_at_100_diff1": 0.186256, + "nauc_map_at_1000_max": 0.122218, + "nauc_map_at_1000_std": 0.128882, + "nauc_map_at_1000_diff1": 0.1846, + "nauc_recall_at_1_max": 0.201437, + "nauc_recall_at_1_std": 0.078649, + "nauc_recall_at_1_diff1": 0.224644, + "nauc_recall_at_3_max": 0.096637, + "nauc_recall_at_3_std": 0.100586, + "nauc_recall_at_3_diff1": 0.240753, + "nauc_recall_at_5_max": 0.040124, + "nauc_recall_at_5_std": 0.073198, + "nauc_recall_at_5_diff1": 0.188658, + "nauc_recall_at_10_max": -0.022752, + "nauc_recall_at_10_std": 0.124458, + "nauc_recall_at_10_diff1": 0.048102, + "nauc_recall_at_20_max": -0.004154, + "nauc_recall_at_20_std": 0.101348, + "nauc_recall_at_20_diff1": 0.060536, + "nauc_recall_at_100_max": 0.069918, + "nauc_recall_at_100_std": 0.319053, + "nauc_recall_at_100_diff1": 0.08314, + "nauc_recall_at_1000_max": 0.131871, + "nauc_recall_at_1000_std": 0.310385, + "nauc_recall_at_1000_diff1": -0.023785, + "nauc_precision_at_1_max": 0.183331, + "nauc_precision_at_1_std": 0.102548, + "nauc_precision_at_1_diff1": 0.215166, + "nauc_precision_at_3_max": 0.10987, + "nauc_precision_at_3_std": 0.095852, + "nauc_precision_at_3_diff1": 0.208765, + "nauc_precision_at_5_max": 0.031866, + "nauc_precision_at_5_std": 0.063035, + "nauc_precision_at_5_diff1": 0.142188, + "nauc_precision_at_10_max": -0.042267, + "nauc_precision_at_10_std": 0.073679, + "nauc_precision_at_10_diff1": 0.056724, + "nauc_precision_at_20_max": -0.030254, + "nauc_precision_at_20_std": 0.033406, + "nauc_precision_at_20_diff1": 0.051131, + "nauc_precision_at_100_max": 0.032172, + "nauc_precision_at_100_std": 0.164155, + "nauc_precision_at_100_diff1": 0.115171, + "nauc_precision_at_1000_max": 0.047195, + "nauc_precision_at_1000_std": 0.058535, + "nauc_precision_at_1000_diff1": 0.025818, + "nauc_mrr_at_1_max": 0.183331, + "nauc_mrr_at_1_std": 0.102548, + "nauc_mrr_at_1_diff1": 0.215166, + "nauc_mrr_at_3_max": 0.127212, + "nauc_mrr_at_3_std": 0.107384, + "nauc_mrr_at_3_diff1": 0.221289, + "nauc_mrr_at_5_max": 0.098586, + "nauc_mrr_at_5_std": 0.095679, + "nauc_mrr_at_5_diff1": 0.197824, + "nauc_mrr_at_10_max": 0.081558, + "nauc_mrr_at_10_std": 0.097476, + "nauc_mrr_at_10_diff1": 0.181458, + "nauc_mrr_at_20_max": 0.083058, + "nauc_mrr_at_20_std": 0.096899, + "nauc_mrr_at_20_diff1": 0.178553, + "nauc_mrr_at_100_max": 0.087749, + "nauc_mrr_at_100_std": 0.102196, + "nauc_mrr_at_100_diff1": 0.183727, + "nauc_mrr_at_1000_max": 0.088627, + "nauc_mrr_at_1000_std": 0.10207, + "nauc_mrr_at_1000_diff1": 0.182784, + "main_score": 0.11269, + "hf_subset": "PMC-Clinical", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.12403, + "ndcg_at_3": 0.11122, + "ndcg_at_5": 0.11954, + "ndcg_at_10": 0.14261, + "ndcg_at_20": 0.17073, + "ndcg_at_100": 0.24174, + "ndcg_at_1000": 0.31364, + "map_at_1": 0.03152, + "map_at_3": 0.06219, + "map_at_5": 0.07573, + "map_at_10": 0.0873, + "map_at_20": 0.09611, + "map_at_100": 0.11054, + "map_at_1000": 0.11486, + "recall_at_1": 0.03152, + "recall_at_3": 0.07946, + "recall_at_5": 0.12442, + "recall_at_10": 0.17907, + "recall_at_20": 0.25065, + "recall_at_100": 0.50478, + "recall_at_1000": 0.91072, + "precision_at_1": 0.12403, + "precision_at_3": 0.10078, + "precision_at_5": 0.08682, + "precision_at_10": 0.06357, + "precision_at_20": 0.04651, + "precision_at_100": 0.01907, + "precision_at_1000": 0.00324, + "mrr_at_1": 0.124031, + "mrr_at_3": 0.178295, + "mrr_at_5": 0.194574, + "mrr_at_10": 0.209047, + "mrr_at_20": 0.216911, + "mrr_at_100": 0.222884, + "mrr_at_1000": 0.224023, + "nauc_ndcg_at_1_max": 0.081215, + "nauc_ndcg_at_1_std": 0.225234, + "nauc_ndcg_at_1_diff1": 0.027003, + "nauc_ndcg_at_3_max": 0.211899, + "nauc_ndcg_at_3_std": 0.24152, + "nauc_ndcg_at_3_diff1": 0.092482, + "nauc_ndcg_at_5_max": 0.175427, + "nauc_ndcg_at_5_std": 0.198665, + "nauc_ndcg_at_5_diff1": 0.083512, + "nauc_ndcg_at_10_max": 0.17576, + "nauc_ndcg_at_10_std": 0.251793, + "nauc_ndcg_at_10_diff1": 0.09941, + "nauc_ndcg_at_20_max": 0.21698, + "nauc_ndcg_at_20_std": 0.256941, + "nauc_ndcg_at_20_diff1": 0.08473, + "nauc_ndcg_at_100_max": 0.202815, + "nauc_ndcg_at_100_std": 0.336523, + "nauc_ndcg_at_100_diff1": 0.048999, + "nauc_ndcg_at_1000_max": 0.230095, + "nauc_ndcg_at_1000_std": 0.358994, + "nauc_ndcg_at_1000_diff1": 0.017649, + "nauc_map_at_1_max": 0.110877, + "nauc_map_at_1_std": 0.189393, + "nauc_map_at_1_diff1": 0.127313, + "nauc_map_at_3_max": 0.24997, + "nauc_map_at_3_std": 0.218196, + "nauc_map_at_3_diff1": 0.225413, + "nauc_map_at_5_max": 0.213007, + "nauc_map_at_5_std": 0.199907, + "nauc_map_at_5_diff1": 0.16022, + "nauc_map_at_10_max": 0.197596, + "nauc_map_at_10_std": 0.23354, + "nauc_map_at_10_diff1": 0.147527, + "nauc_map_at_20_max": 0.221656, + "nauc_map_at_20_std": 0.237135, + "nauc_map_at_20_diff1": 0.145451, + "nauc_map_at_100_max": 0.223905, + "nauc_map_at_100_std": 0.268774, + "nauc_map_at_100_diff1": 0.125356, + "nauc_map_at_1000_max": 0.226809, + "nauc_map_at_1000_std": 0.272801, + "nauc_map_at_1000_diff1": 0.11886, + "nauc_recall_at_1_max": 0.110877, + "nauc_recall_at_1_std": 0.189393, + "nauc_recall_at_1_diff1": 0.127313, + "nauc_recall_at_3_max": 0.269948, + "nauc_recall_at_3_std": 0.247145, + "nauc_recall_at_3_diff1": 0.189007, + "nauc_recall_at_5_max": 0.147557, + "nauc_recall_at_5_std": 0.141814, + "nauc_recall_at_5_diff1": 0.070439, + "nauc_recall_at_10_max": 0.12576, + "nauc_recall_at_10_std": 0.217803, + "nauc_recall_at_10_diff1": 0.079287, + "nauc_recall_at_20_max": 0.194352, + "nauc_recall_at_20_std": 0.218706, + "nauc_recall_at_20_diff1": 0.051359, + "nauc_recall_at_100_max": 0.148755, + "nauc_recall_at_100_std": 0.354772, + "nauc_recall_at_100_diff1": -0.006155, + "nauc_recall_at_1000_max": 0.472985, + "nauc_recall_at_1000_std": 0.793883, + "nauc_recall_at_1000_diff1": -0.159094, + "nauc_precision_at_1_max": 0.081215, + "nauc_precision_at_1_std": 0.225234, + "nauc_precision_at_1_diff1": 0.027003, + "nauc_precision_at_3_max": 0.252506, + "nauc_precision_at_3_std": 0.262483, + "nauc_precision_at_3_diff1": 0.105419, + "nauc_precision_at_5_max": 0.176592, + "nauc_precision_at_5_std": 0.213663, + "nauc_precision_at_5_diff1": 0.035308, + "nauc_precision_at_10_max": 0.18502, + "nauc_precision_at_10_std": 0.31686, + "nauc_precision_at_10_diff1": 0.052119, + "nauc_precision_at_20_max": 0.259804, + "nauc_precision_at_20_std": 0.299217, + "nauc_precision_at_20_diff1": 0.018832, + "nauc_precision_at_100_max": 0.183841, + "nauc_precision_at_100_std": 0.439947, + "nauc_precision_at_100_diff1": -0.043608, + "nauc_precision_at_1000_max": 0.147583, + "nauc_precision_at_1000_std": 0.39051, + "nauc_precision_at_1000_diff1": -0.158286, + "nauc_mrr_at_1_max": 0.081215, + "nauc_mrr_at_1_std": 0.225234, + "nauc_mrr_at_1_diff1": 0.027003, + "nauc_mrr_at_3_max": 0.160892, + "nauc_mrr_at_3_std": 0.230477, + "nauc_mrr_at_3_diff1": 0.038908, + "nauc_mrr_at_5_max": 0.14682, + "nauc_mrr_at_5_std": 0.216873, + "nauc_mrr_at_5_diff1": 0.041967, + "nauc_mrr_at_10_max": 0.158861, + "nauc_mrr_at_10_std": 0.237572, + "nauc_mrr_at_10_diff1": 0.054431, + "nauc_mrr_at_20_max": 0.158863, + "nauc_mrr_at_20_std": 0.234761, + "nauc_mrr_at_20_diff1": 0.042497, + "nauc_mrr_at_100_max": 0.152963, + "nauc_mrr_at_100_std": 0.239143, + "nauc_mrr_at_100_diff1": 0.038719, + "nauc_mrr_at_1000_max": 0.154029, + "nauc_mrr_at_1000_std": 0.238959, + "nauc_mrr_at_1000_diff1": 0.038123, + "main_score": 0.14261, + "hf_subset": "IIYi-Clinical", + "languages": [ + "eng-Latn" + ] + } + ] + }, + "evaluation_time": 395.5722165107727, + "kg_co2_emissions": null +} \ No newline at end of file diff --git a/results/sentence-transformers__paraphrase-multilingual-MiniLM-L12-v2/bf3bf13ab40c3157080a7ab344c831b9ad18b5eb/R2MEDRetrieval.json b/results/sentence-transformers__paraphrase-multilingual-MiniLM-L12-v2/bf3bf13ab40c3157080a7ab344c831b9ad18b5eb/R2MEDRetrieval.json new file mode 100644 index 0000000000..78d5d5bc3f --- /dev/null +++ b/results/sentence-transformers__paraphrase-multilingual-MiniLM-L12-v2/bf3bf13ab40c3157080a7ab344c831b9ad18b5eb/R2MEDRetrieval.json @@ -0,0 +1,1187 @@ +{ + "dataset_revision": "1.0", + "task_name": "R2MEDRetrieval", + "mteb_version": "1.38.20", + "scores": { + "test": [ + { + "ndcg_at_1": 0.05825, + "ndcg_at_3": 0.05468, + "ndcg_at_5": 0.05625, + "ndcg_at_10": 0.07142, + "ndcg_at_20": 0.07841, + "ndcg_at_100": 0.11083, + "ndcg_at_1000": 0.17756, + "map_at_1": 0.0116, + "map_at_3": 0.02462, + "map_at_5": 0.02929, + "map_at_10": 0.03686, + "map_at_20": 0.03951, + "map_at_100": 0.04433, + "map_at_1000": 0.04751, + "recall_at_1": 0.0116, + "recall_at_3": 0.03792, + "recall_at_5": 0.052, + "recall_at_10": 0.09564, + "recall_at_20": 0.11047, + "recall_at_100": 0.22903, + "recall_at_1000": 0.60991, + "precision_at_1": 0.05825, + "precision_at_3": 0.05178, + "precision_at_5": 0.0466, + "precision_at_10": 0.03786, + "precision_at_20": 0.02379, + "precision_at_100": 0.00981, + "precision_at_1000": 0.00233, + "mrr_at_1": 0.048544, + "mrr_at_3": 0.084142, + "mrr_at_5": 0.09288, + "mrr_at_10": 0.105744, + "mrr_at_20": 0.107791, + "mrr_at_100": 0.112126, + "mrr_at_1000": 0.113602, + "nauc_ndcg_at_1_max": 0.009195, + "nauc_ndcg_at_1_std": 0.065854, + "nauc_ndcg_at_1_diff1": 0.098565, + "nauc_ndcg_at_3_max": -0.013032, + "nauc_ndcg_at_3_std": -0.122243, + "nauc_ndcg_at_3_diff1": 0.053149, + "nauc_ndcg_at_5_max": -0.065433, + "nauc_ndcg_at_5_std": -0.189931, + "nauc_ndcg_at_5_diff1": 0.11457, + "nauc_ndcg_at_10_max": -0.048396, + "nauc_ndcg_at_10_std": -0.21447, + "nauc_ndcg_at_10_diff1": 0.134437, + "nauc_ndcg_at_20_max": -0.062993, + "nauc_ndcg_at_20_std": -0.203391, + "nauc_ndcg_at_20_diff1": 0.111404, + "nauc_ndcg_at_100_max": -0.051284, + "nauc_ndcg_at_100_std": -0.174587, + "nauc_ndcg_at_100_diff1": 0.125746, + "nauc_ndcg_at_1000_max": -0.06382, + "nauc_ndcg_at_1000_std": -0.15909, + "nauc_ndcg_at_1000_diff1": 0.130638, + "nauc_map_at_1_max": 0.132142, + "nauc_map_at_1_std": 0.122919, + "nauc_map_at_1_diff1": 0.223099, + "nauc_map_at_3_max": 0.102403, + "nauc_map_at_3_std": -0.123203, + "nauc_map_at_3_diff1": 0.248759, + "nauc_map_at_5_max": 0.022344, + "nauc_map_at_5_std": -0.167828, + "nauc_map_at_5_diff1": 0.253858, + "nauc_map_at_10_max": -0.000265, + "nauc_map_at_10_std": -0.198221, + "nauc_map_at_10_diff1": 0.222182, + "nauc_map_at_20_max": -0.021248, + "nauc_map_at_20_std": -0.196754, + "nauc_map_at_20_diff1": 0.207259, + "nauc_map_at_100_max": -0.025352, + "nauc_map_at_100_std": -0.19266, + "nauc_map_at_100_diff1": 0.209275, + "nauc_map_at_1000_max": -0.026051, + "nauc_map_at_1000_std": -0.188893, + "nauc_map_at_1000_diff1": 0.20071, + "nauc_recall_at_1_max": 0.132142, + "nauc_recall_at_1_std": 0.122919, + "nauc_recall_at_1_diff1": 0.223099, + "nauc_recall_at_3_max": 0.04794, + "nauc_recall_at_3_std": -0.209039, + "nauc_recall_at_3_diff1": 0.152143, + "nauc_recall_at_5_max": -0.075492, + "nauc_recall_at_5_std": -0.259241, + "nauc_recall_at_5_diff1": 0.14242, + "nauc_recall_at_10_max": -0.065007, + "nauc_recall_at_10_std": -0.254356, + "nauc_recall_at_10_diff1": 0.127003, + "nauc_recall_at_20_max": -0.087991, + "nauc_recall_at_20_std": -0.23826, + "nauc_recall_at_20_diff1": 0.096738, + "nauc_recall_at_100_max": -0.049599, + "nauc_recall_at_100_std": -0.155486, + "nauc_recall_at_100_diff1": 0.122997, + "nauc_recall_at_1000_max": -0.069835, + "nauc_recall_at_1000_std": -0.110217, + "nauc_recall_at_1000_diff1": 0.175695, + "nauc_precision_at_1_max": 0.009195, + "nauc_precision_at_1_std": 0.065854, + "nauc_precision_at_1_diff1": 0.098565, + "nauc_precision_at_3_max": -0.043092, + "nauc_precision_at_3_std": -0.177396, + "nauc_precision_at_3_diff1": 0.01518, + "nauc_precision_at_5_max": -0.168293, + "nauc_precision_at_5_std": -0.262618, + "nauc_precision_at_5_diff1": 0.062604, + "nauc_precision_at_10_max": -0.150978, + "nauc_precision_at_10_std": -0.279912, + "nauc_precision_at_10_diff1": 0.046665, + "nauc_precision_at_20_max": -0.160288, + "nauc_precision_at_20_std": -0.237903, + "nauc_precision_at_20_diff1": 0.005104, + "nauc_precision_at_100_max": -0.091841, + "nauc_precision_at_100_std": -0.115552, + "nauc_precision_at_100_diff1": 0.053369, + "nauc_precision_at_1000_max": -0.088485, + "nauc_precision_at_1000_std": -0.090855, + "nauc_precision_at_1000_diff1": 0.017811, + "nauc_mrr_at_1_max": 0.110498, + "nauc_mrr_at_1_std": 0.092815, + "nauc_mrr_at_1_diff1": 0.232644, + "nauc_mrr_at_3_max": 0.011585, + "nauc_mrr_at_3_std": -0.045907, + "nauc_mrr_at_3_diff1": 0.075033, + "nauc_mrr_at_5_max": -0.028144, + "nauc_mrr_at_5_std": -0.082003, + "nauc_mrr_at_5_diff1": 0.069043, + "nauc_mrr_at_10_max": -0.020656, + "nauc_mrr_at_10_std": -0.096292, + "nauc_mrr_at_10_diff1": 0.079186, + "nauc_mrr_at_20_max": -0.017484, + "nauc_mrr_at_20_std": -0.102449, + "nauc_mrr_at_20_diff1": 0.07005, + "nauc_mrr_at_100_max": -0.011693, + "nauc_mrr_at_100_std": -0.103438, + "nauc_mrr_at_100_diff1": 0.073461, + "nauc_mrr_at_1000_max": -0.013822, + "nauc_mrr_at_1000_std": -0.103646, + "nauc_mrr_at_1000_diff1": 0.074616, + "main_score": 0.07142, + "hf_subset": "Biology", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.12987, + "ndcg_at_3": 0.118, + "ndcg_at_5": 0.13132, + "ndcg_at_10": 0.16026, + "ndcg_at_20": 0.17921, + "ndcg_at_100": 0.22855, + "ndcg_at_1000": 0.28083, + "map_at_1": 0.05813, + "map_at_3": 0.07972, + "map_at_5": 0.09184, + "map_at_10": 0.10473, + "map_at_20": 0.11063, + "map_at_100": 0.1188, + "map_at_1000": 0.12162, + "recall_at_1": 0.05813, + "recall_at_3": 0.10186, + "recall_at_5": 0.14808, + "recall_at_10": 0.23262, + "recall_at_20": 0.29323, + "recall_at_100": 0.48519, + "recall_at_1000": 0.7833, + "precision_at_1": 0.12987, + "precision_at_3": 0.08658, + "precision_at_5": 0.07013, + "precision_at_10": 0.04935, + "precision_at_20": 0.03312, + "precision_at_100": 0.01286, + "precision_at_1000": 0.00235, + "mrr_at_1": 0.12987, + "mrr_at_3": 0.175325, + "mrr_at_5": 0.192857, + "mrr_at_10": 0.209967, + "mrr_at_20": 0.212977, + "mrr_at_100": 0.219533, + "mrr_at_1000": 0.220317, + "nauc_ndcg_at_1_max": 0.156874, + "nauc_ndcg_at_1_std": 0.100443, + "nauc_ndcg_at_1_diff1": 0.084187, + "nauc_ndcg_at_3_max": 0.136945, + "nauc_ndcg_at_3_std": 0.031747, + "nauc_ndcg_at_3_diff1": -0.041138, + "nauc_ndcg_at_5_max": 0.198053, + "nauc_ndcg_at_5_std": 0.098528, + "nauc_ndcg_at_5_diff1": -0.06003, + "nauc_ndcg_at_10_max": 0.14431, + "nauc_ndcg_at_10_std": 0.097069, + "nauc_ndcg_at_10_diff1": -0.031808, + "nauc_ndcg_at_20_max": 0.137603, + "nauc_ndcg_at_20_std": 0.09989, + "nauc_ndcg_at_20_diff1": 0.006352, + "nauc_ndcg_at_100_max": 0.188671, + "nauc_ndcg_at_100_std": 0.207982, + "nauc_ndcg_at_100_diff1": -0.023444, + "nauc_ndcg_at_1000_max": 0.179192, + "nauc_ndcg_at_1000_std": 0.204544, + "nauc_ndcg_at_1000_diff1": -0.06389, + "nauc_map_at_1_max": 0.193066, + "nauc_map_at_1_std": 0.115141, + "nauc_map_at_1_diff1": -0.05672, + "nauc_map_at_3_max": 0.190807, + "nauc_map_at_3_std": 0.070303, + "nauc_map_at_3_diff1": -0.05127, + "nauc_map_at_5_max": 0.212485, + "nauc_map_at_5_std": 0.097713, + "nauc_map_at_5_diff1": -0.06524, + "nauc_map_at_10_max": 0.173735, + "nauc_map_at_10_std": 0.090387, + "nauc_map_at_10_diff1": -0.058057, + "nauc_map_at_20_max": 0.166816, + "nauc_map_at_20_std": 0.09171, + "nauc_map_at_20_diff1": -0.040563, + "nauc_map_at_100_max": 0.172143, + "nauc_map_at_100_std": 0.118566, + "nauc_map_at_100_diff1": -0.051098, + "nauc_map_at_1000_max": 0.173227, + "nauc_map_at_1000_std": 0.119464, + "nauc_map_at_1000_diff1": -0.053889, + "nauc_recall_at_1_max": 0.193066, + "nauc_recall_at_1_std": 0.115141, + "nauc_recall_at_1_diff1": -0.05672, + "nauc_recall_at_3_max": 0.21937, + "nauc_recall_at_3_std": 0.044608, + "nauc_recall_at_3_diff1": -0.06528, + "nauc_recall_at_5_max": 0.240762, + "nauc_recall_at_5_std": 0.1338, + "nauc_recall_at_5_diff1": -0.074512, + "nauc_recall_at_10_max": 0.104378, + "nauc_recall_at_10_std": 0.105834, + "nauc_recall_at_10_diff1": -0.027128, + "nauc_recall_at_20_max": 0.099194, + "nauc_recall_at_20_std": 0.100206, + "nauc_recall_at_20_diff1": 0.071474, + "nauc_recall_at_100_max": 0.18758, + "nauc_recall_at_100_std": 0.320627, + "nauc_recall_at_100_diff1": 0.000541, + "nauc_recall_at_1000_max": 0.159685, + "nauc_recall_at_1000_std": 0.445014, + "nauc_recall_at_1000_diff1": -0.169052, + "nauc_precision_at_1_max": 0.156874, + "nauc_precision_at_1_std": 0.100443, + "nauc_precision_at_1_diff1": 0.084187, + "nauc_precision_at_3_max": 0.065295, + "nauc_precision_at_3_std": 0.002171, + "nauc_precision_at_3_diff1": -0.033863, + "nauc_precision_at_5_max": 0.153213, + "nauc_precision_at_5_std": 0.104461, + "nauc_precision_at_5_diff1": -0.105124, + "nauc_precision_at_10_max": 0.04012, + "nauc_precision_at_10_std": 0.097157, + "nauc_precision_at_10_diff1": -0.077471, + "nauc_precision_at_20_max": -0.011234, + "nauc_precision_at_20_std": 0.099775, + "nauc_precision_at_20_diff1": -0.035056, + "nauc_precision_at_100_max": 0.203957, + "nauc_precision_at_100_std": 0.336156, + "nauc_precision_at_100_diff1": -0.05805, + "nauc_precision_at_1000_max": 0.092748, + "nauc_precision_at_1000_std": 0.141896, + "nauc_precision_at_1000_diff1": -0.128518, + "nauc_mrr_at_1_max": 0.156874, + "nauc_mrr_at_1_std": 0.100443, + "nauc_mrr_at_1_diff1": 0.084187, + "nauc_mrr_at_3_max": 0.115753, + "nauc_mrr_at_3_std": 0.031578, + "nauc_mrr_at_3_diff1": 0.017698, + "nauc_mrr_at_5_max": 0.128244, + "nauc_mrr_at_5_std": 0.062524, + "nauc_mrr_at_5_diff1": -0.002605, + "nauc_mrr_at_10_max": 0.107968, + "nauc_mrr_at_10_std": 0.059485, + "nauc_mrr_at_10_diff1": 0.010165, + "nauc_mrr_at_20_max": 0.114219, + "nauc_mrr_at_20_std": 0.062341, + "nauc_mrr_at_20_diff1": 0.01738, + "nauc_mrr_at_100_max": 0.113876, + "nauc_mrr_at_100_std": 0.066532, + "nauc_mrr_at_100_diff1": 0.013374, + "nauc_mrr_at_1000_max": 0.112841, + "nauc_mrr_at_1000_std": 0.066286, + "nauc_mrr_at_1000_diff1": 0.012579, + "main_score": 0.16026, + "hf_subset": "Bioinformatics", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.125, + "ndcg_at_3": 0.15196, + "ndcg_at_5": 0.18403, + "ndcg_at_10": 0.21096, + "ndcg_at_20": 0.23894, + "ndcg_at_100": 0.28915, + "ndcg_at_1000": 0.33125, + "map_at_1": 0.07492, + "map_at_3": 0.11521, + "map_at_5": 0.13672, + "map_at_10": 0.14962, + "map_at_20": 0.15884, + "map_at_100": 0.16868, + "map_at_1000": 0.17104, + "recall_at_1": 0.07492, + "recall_at_3": 0.15392, + "recall_at_5": 0.23094, + "recall_at_10": 0.30028, + "recall_at_20": 0.38964, + "recall_at_100": 0.58513, + "recall_at_1000": 0.83155, + "precision_at_1": 0.125, + "precision_at_3": 0.09848, + "precision_at_5": 0.09545, + "precision_at_10": 0.06818, + "precision_at_20": 0.04489, + "precision_at_100": 0.01534, + "precision_at_1000": 0.00225, + "mrr_at_1": 0.125, + "mrr_at_3": 0.185606, + "mrr_at_5": 0.212311, + "mrr_at_10": 0.227219, + "mrr_at_20": 0.233153, + "mrr_at_100": 0.236936, + "mrr_at_1000": 0.237994, + "nauc_ndcg_at_1_max": -0.008198, + "nauc_ndcg_at_1_std": 0.010771, + "nauc_ndcg_at_1_diff1": -0.047608, + "nauc_ndcg_at_3_max": 0.088451, + "nauc_ndcg_at_3_std": 0.059635, + "nauc_ndcg_at_3_diff1": -0.082557, + "nauc_ndcg_at_5_max": 0.132915, + "nauc_ndcg_at_5_std": 0.023311, + "nauc_ndcg_at_5_diff1": 0.019487, + "nauc_ndcg_at_10_max": 0.163631, + "nauc_ndcg_at_10_std": 0.043472, + "nauc_ndcg_at_10_diff1": 0.040885, + "nauc_ndcg_at_20_max": 0.171419, + "nauc_ndcg_at_20_std": 0.054788, + "nauc_ndcg_at_20_diff1": 0.077327, + "nauc_ndcg_at_100_max": 0.214519, + "nauc_ndcg_at_100_std": 0.151412, + "nauc_ndcg_at_100_diff1": 0.014985, + "nauc_ndcg_at_1000_max": 0.200064, + "nauc_ndcg_at_1000_std": 0.127311, + "nauc_ndcg_at_1000_diff1": 0.032736, + "nauc_map_at_1_max": 0.084579, + "nauc_map_at_1_std": 0.085039, + "nauc_map_at_1_diff1": -0.020529, + "nauc_map_at_3_max": 0.110465, + "nauc_map_at_3_std": 0.095345, + "nauc_map_at_3_diff1": -0.072138, + "nauc_map_at_5_max": 0.128367, + "nauc_map_at_5_std": 0.059601, + "nauc_map_at_5_diff1": -0.008097, + "nauc_map_at_10_max": 0.152198, + "nauc_map_at_10_std": 0.06438, + "nauc_map_at_10_diff1": 0.014627, + "nauc_map_at_20_max": 0.151827, + "nauc_map_at_20_std": 0.067425, + "nauc_map_at_20_diff1": 0.027719, + "nauc_map_at_100_max": 0.164466, + "nauc_map_at_100_std": 0.083986, + "nauc_map_at_100_diff1": 0.017305, + "nauc_map_at_1000_max": 0.164307, + "nauc_map_at_1000_std": 0.083887, + "nauc_map_at_1000_diff1": 0.0174, + "nauc_recall_at_1_max": 0.084579, + "nauc_recall_at_1_std": 0.085039, + "nauc_recall_at_1_diff1": -0.020529, + "nauc_recall_at_3_max": 0.112745, + "nauc_recall_at_3_std": 0.08677, + "nauc_recall_at_3_diff1": -0.089456, + "nauc_recall_at_5_max": 0.153969, + "nauc_recall_at_5_std": -0.012851, + "nauc_recall_at_5_diff1": 0.079562, + "nauc_recall_at_10_max": 0.199137, + "nauc_recall_at_10_std": 0.011957, + "nauc_recall_at_10_diff1": 0.114478, + "nauc_recall_at_20_max": 0.222221, + "nauc_recall_at_20_std": 0.048438, + "nauc_recall_at_20_diff1": 0.218549, + "nauc_recall_at_100_max": 0.319093, + "nauc_recall_at_100_std": 0.3333, + "nauc_recall_at_100_diff1": 0.046736, + "nauc_recall_at_1000_max": 0.317506, + "nauc_recall_at_1000_std": 0.28582, + "nauc_recall_at_1000_diff1": 0.3238, + "nauc_precision_at_1_max": -0.008198, + "nauc_precision_at_1_std": 0.010771, + "nauc_precision_at_1_diff1": -0.047608, + "nauc_precision_at_3_max": 0.09915, + "nauc_precision_at_3_std": 0.047127, + "nauc_precision_at_3_diff1": -0.086414, + "nauc_precision_at_5_max": 0.153822, + "nauc_precision_at_5_std": -0.026706, + "nauc_precision_at_5_diff1": 0.075502, + "nauc_precision_at_10_max": 0.219945, + "nauc_precision_at_10_std": 0.0538, + "nauc_precision_at_10_diff1": 0.103879, + "nauc_precision_at_20_max": 0.18711, + "nauc_precision_at_20_std": 0.060202, + "nauc_precision_at_20_diff1": 0.100587, + "nauc_precision_at_100_max": 0.274142, + "nauc_precision_at_100_std": 0.308047, + "nauc_precision_at_100_diff1": -0.08276, + "nauc_precision_at_1000_max": 0.173854, + "nauc_precision_at_1000_std": 0.207491, + "nauc_precision_at_1000_diff1": -0.114363, + "nauc_mrr_at_1_max": -0.008198, + "nauc_mrr_at_1_std": 0.010771, + "nauc_mrr_at_1_diff1": -0.047608, + "nauc_mrr_at_3_max": 0.062316, + "nauc_mrr_at_3_std": 0.017055, + "nauc_mrr_at_3_diff1": -0.066372, + "nauc_mrr_at_5_max": 0.068996, + "nauc_mrr_at_5_std": -0.005623, + "nauc_mrr_at_5_diff1": -0.023621, + "nauc_mrr_at_10_max": 0.086847, + "nauc_mrr_at_10_std": 0.024693, + "nauc_mrr_at_10_diff1": -0.025173, + "nauc_mrr_at_20_max": 0.088479, + "nauc_mrr_at_20_std": 0.024008, + "nauc_mrr_at_20_diff1": -0.020458, + "nauc_mrr_at_100_max": 0.090239, + "nauc_mrr_at_100_std": 0.03081, + "nauc_mrr_at_100_diff1": -0.024872, + "nauc_mrr_at_1000_max": 0.089383, + "nauc_mrr_at_1000_std": 0.029254, + "nauc_mrr_at_1000_diff1": -0.024505, + "main_score": 0.21096, + "hf_subset": "Medical-Sciences", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.01031, + "ndcg_at_3": 0.01031, + "ndcg_at_5": 0.01042, + "ndcg_at_10": 0.01042, + "ndcg_at_20": 0.01141, + "ndcg_at_100": 0.01578, + "ndcg_at_1000": 0.03391, + "map_at_1": 0.00258, + "map_at_3": 0.00498, + "map_at_5": 0.00601, + "map_at_10": 0.00601, + "map_at_20": 0.00617, + "map_at_100": 0.00689, + "map_at_1000": 0.0074, + "recall_at_1": 0.00258, + "recall_at_3": 0.0067, + "recall_at_5": 0.01186, + "recall_at_10": 0.01186, + "recall_at_20": 0.01443, + "recall_at_100": 0.02923, + "recall_at_1000": 0.13133, + "precision_at_1": 0.01031, + "precision_at_3": 0.01031, + "precision_at_5": 0.00825, + "precision_at_10": 0.00412, + "precision_at_20": 0.00258, + "precision_at_100": 0.00113, + "precision_at_1000": 0.00051, + "mrr_at_1": 0.010309, + "mrr_at_3": 0.015464, + "mrr_at_5": 0.017526, + "mrr_at_10": 0.017526, + "mrr_at_20": 0.01817, + "mrr_at_100": 0.019058, + "mrr_at_1000": 0.019826, + "nauc_ndcg_at_1_max": 0.323888, + "nauc_ndcg_at_1_std": 0.096724, + "nauc_ndcg_at_1_diff1": -0.072193, + "nauc_ndcg_at_3_max": 0.042327, + "nauc_ndcg_at_3_std": 0.007076, + "nauc_ndcg_at_3_diff1": 0.017455, + "nauc_ndcg_at_5_max": 0.122639, + "nauc_ndcg_at_5_std": 0.244541, + "nauc_ndcg_at_5_diff1": -0.066299, + "nauc_ndcg_at_10_max": 0.122639, + "nauc_ndcg_at_10_std": 0.244541, + "nauc_ndcg_at_10_diff1": -0.066299, + "nauc_ndcg_at_20_max": 0.105825, + "nauc_ndcg_at_20_std": 0.251389, + "nauc_ndcg_at_20_diff1": -0.110398, + "nauc_ndcg_at_100_max": 0.103348, + "nauc_ndcg_at_100_std": 0.245848, + "nauc_ndcg_at_100_diff1": -0.086061, + "nauc_ndcg_at_1000_max": 0.109639, + "nauc_ndcg_at_1000_std": 0.265305, + "nauc_ndcg_at_1000_diff1": -0.03092, + "nauc_map_at_1_max": 0.323888, + "nauc_map_at_1_std": 0.096724, + "nauc_map_at_1_diff1": -0.072193, + "nauc_map_at_3_max": 0.067772, + "nauc_map_at_3_std": 0.015178, + "nauc_map_at_3_diff1": 0.009353, + "nauc_map_at_5_max": 0.111678, + "nauc_map_at_5_std": 0.184004, + "nauc_map_at_5_diff1": -0.047145, + "nauc_map_at_10_max": 0.111678, + "nauc_map_at_10_std": 0.184004, + "nauc_map_at_10_diff1": -0.047145, + "nauc_map_at_20_max": 0.106881, + "nauc_map_at_20_std": 0.187654, + "nauc_map_at_20_diff1": -0.060975, + "nauc_map_at_100_max": 0.095213, + "nauc_map_at_100_std": 0.182389, + "nauc_map_at_100_diff1": -0.053981, + "nauc_map_at_1000_max": 0.10162, + "nauc_map_at_1000_std": 0.20094, + "nauc_map_at_1000_diff1": -0.055802, + "nauc_recall_at_1_max": 0.323888, + "nauc_recall_at_1_std": 0.096724, + "nauc_recall_at_1_diff1": -0.072193, + "nauc_recall_at_3_max": -0.002589, + "nauc_recall_at_3_std": -0.007225, + "nauc_recall_at_3_diff1": 0.031756, + "nauc_recall_at_5_max": 0.139357, + "nauc_recall_at_5_std": 0.430699, + "nauc_recall_at_5_diff1": -0.121277, + "nauc_recall_at_10_max": 0.139357, + "nauc_recall_at_10_std": 0.430699, + "nauc_recall_at_10_diff1": -0.121277, + "nauc_recall_at_20_max": 0.101581, + "nauc_recall_at_20_std": 0.411625, + "nauc_recall_at_20_diff1": -0.202706, + "nauc_recall_at_100_max": 0.08069, + "nauc_recall_at_100_std": 0.289591, + "nauc_recall_at_100_diff1": -0.1128, + "nauc_recall_at_1000_max": 0.077832, + "nauc_recall_at_1000_std": 0.23091, + "nauc_recall_at_1000_diff1": 0.000895, + "nauc_precision_at_1_max": 0.323888, + "nauc_precision_at_1_std": 0.096724, + "nauc_precision_at_1_diff1": -0.072193, + "nauc_precision_at_3_max": -0.029795, + "nauc_precision_at_3_std": -0.015887, + "nauc_precision_at_3_diff1": 0.040418, + "nauc_precision_at_5_max": 0.058625, + "nauc_precision_at_5_std": 0.238084, + "nauc_precision_at_5_diff1": -0.049741, + "nauc_precision_at_10_max": 0.058625, + "nauc_precision_at_10_std": 0.238084, + "nauc_precision_at_10_diff1": -0.049741, + "nauc_precision_at_20_max": 0.032462, + "nauc_precision_at_20_std": 0.255245, + "nauc_precision_at_20_diff1": -0.155249, + "nauc_precision_at_100_max": 0.109774, + "nauc_precision_at_100_std": 0.286943, + "nauc_precision_at_100_diff1": -0.079233, + "nauc_precision_at_1000_max": 0.155811, + "nauc_precision_at_1000_std": 0.349983, + "nauc_precision_at_1000_diff1": 0.025136, + "nauc_mrr_at_1_max": 0.323888, + "nauc_mrr_at_1_std": 0.096724, + "nauc_mrr_at_1_diff1": -0.072193, + "nauc_mrr_at_3_max": 0.147046, + "nauc_mrr_at_3_std": 0.040418, + "nauc_mrr_at_3_diff1": -0.015887, + "nauc_mrr_at_5_max": 0.167851, + "nauc_mrr_at_5_std": 0.15331, + "nauc_mrr_at_5_diff1": -0.051691, + "nauc_mrr_at_10_max": 0.167851, + "nauc_mrr_at_10_std": 0.15331, + "nauc_mrr_at_10_diff1": -0.051691, + "nauc_mrr_at_20_max": 0.159339, + "nauc_mrr_at_20_std": 0.159359, + "nauc_mrr_at_20_diff1": -0.070329, + "nauc_mrr_at_100_max": 0.164895, + "nauc_mrr_at_100_std": 0.176196, + "nauc_mrr_at_100_diff1": -0.070416, + "nauc_mrr_at_1000_max": 0.160962, + "nauc_mrr_at_1000_std": 0.177577, + "nauc_mrr_at_1000_diff1": -0.068965, + "main_score": 0.01042, + "hf_subset": "MedXpertQA-Exam", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.00847, + "ndcg_at_3": 0.00398, + "ndcg_at_5": 0.00473, + "ndcg_at_10": 0.00669, + "ndcg_at_20": 0.01343, + "ndcg_at_100": 0.02419, + "ndcg_at_1000": 0.04773, + "map_at_1": 0.00212, + "map_at_3": 0.00212, + "map_at_5": 0.00265, + "map_at_10": 0.00353, + "map_at_20": 0.00481, + "map_at_100": 0.0063, + "map_at_1000": 0.00689, + "recall_at_1": 0.00212, + "recall_at_3": 0.00212, + "recall_at_5": 0.00424, + "recall_at_10": 0.00757, + "recall_at_20": 0.0282, + "recall_at_100": 0.06995, + "recall_at_1000": 0.20768, + "precision_at_1": 0.00847, + "precision_at_3": 0.00282, + "precision_at_5": 0.00339, + "precision_at_10": 0.00339, + "precision_at_20": 0.00466, + "precision_at_100": 0.00237, + "precision_at_1000": 0.00075, + "mrr_at_1": 0.008475, + "mrr_at_3": 0.008475, + "mrr_at_5": 0.010593, + "mrr_at_10": 0.011804, + "mrr_at_20": 0.015327, + "mrr_at_100": 0.01707, + "mrr_at_1000": 0.018061, + "nauc_ndcg_at_1_max": -0.321102, + "nauc_ndcg_at_1_std": -0.207793, + "nauc_ndcg_at_1_diff1": 0.664794, + "nauc_ndcg_at_3_max": -0.321102, + "nauc_ndcg_at_3_std": -0.207793, + "nauc_ndcg_at_3_diff1": 0.664794, + "nauc_ndcg_at_5_max": -0.286992, + "nauc_ndcg_at_5_std": -0.207793, + "nauc_ndcg_at_5_diff1": 0.563887, + "nauc_ndcg_at_10_max": -0.296963, + "nauc_ndcg_at_10_std": -0.220948, + "nauc_ndcg_at_10_diff1": 0.507905, + "nauc_ndcg_at_20_max": -0.255079, + "nauc_ndcg_at_20_std": -0.04898, + "nauc_ndcg_at_20_diff1": 0.132866, + "nauc_ndcg_at_100_max": -0.20053, + "nauc_ndcg_at_100_std": -0.046344, + "nauc_ndcg_at_100_diff1": 0.007921, + "nauc_ndcg_at_1000_max": -0.065885, + "nauc_ndcg_at_1000_std": 0.050895, + "nauc_ndcg_at_1000_diff1": -0.018913, + "nauc_map_at_1_max": -0.321102, + "nauc_map_at_1_std": -0.207793, + "nauc_map_at_1_diff1": 0.664794, + "nauc_map_at_3_max": -0.321102, + "nauc_map_at_3_std": -0.207793, + "nauc_map_at_3_diff1": 0.664794, + "nauc_map_at_5_max": -0.29844, + "nauc_map_at_5_std": -0.207793, + "nauc_map_at_5_diff1": 0.597752, + "nauc_map_at_10_max": -0.304088, + "nauc_map_at_10_std": -0.213348, + "nauc_map_at_10_diff1": 0.578364, + "nauc_map_at_20_max": -0.290242, + "nauc_map_at_20_std": -0.125543, + "nauc_map_at_20_diff1": 0.360709, + "nauc_map_at_100_max": -0.258116, + "nauc_map_at_100_std": -0.110114, + "nauc_map_at_100_diff1": 0.259748, + "nauc_map_at_1000_max": -0.238769, + "nauc_map_at_1000_std": -0.085325, + "nauc_map_at_1000_diff1": 0.240126, + "nauc_recall_at_1_max": -0.321102, + "nauc_recall_at_1_std": -0.207793, + "nauc_recall_at_1_diff1": 0.664794, + "nauc_recall_at_3_max": -0.321102, + "nauc_recall_at_3_std": -0.207793, + "nauc_recall_at_3_diff1": 0.664794, + "nauc_recall_at_5_max": -0.264447, + "nauc_recall_at_5_std": -0.207793, + "nauc_recall_at_5_diff1": 0.497191, + "nauc_recall_at_10_max": -0.289375, + "nauc_recall_at_10_std": -0.225922, + "nauc_recall_at_10_diff1": 0.453139, + "nauc_recall_at_20_max": -0.259134, + "nauc_recall_at_20_std": -0.017748, + "nauc_recall_at_20_diff1": -0.052709, + "nauc_recall_at_100_max": -0.211538, + "nauc_recall_at_100_std": -0.070381, + "nauc_recall_at_100_diff1": -0.126103, + "nauc_recall_at_1000_max": -0.027869, + "nauc_recall_at_1000_std": 0.016341, + "nauc_recall_at_1000_diff1": -0.082281, + "nauc_precision_at_1_max": -0.321102, + "nauc_precision_at_1_std": -0.207793, + "nauc_precision_at_1_diff1": 0.664794, + "nauc_precision_at_3_max": -0.321102, + "nauc_precision_at_3_std": -0.207793, + "nauc_precision_at_3_diff1": 0.664794, + "nauc_precision_at_5_max": -0.264447, + "nauc_precision_at_5_std": -0.207793, + "nauc_precision_at_5_diff1": 0.497191, + "nauc_precision_at_10_max": -0.292774, + "nauc_precision_at_10_std": -0.23612, + "nauc_precision_at_10_diff1": 0.396934, + "nauc_precision_at_20_max": -0.191037, + "nauc_precision_at_20_std": 0.052486, + "nauc_precision_at_20_diff1": -0.010712, + "nauc_precision_at_100_max": -0.13718, + "nauc_precision_at_100_std": 0.038746, + "nauc_precision_at_100_diff1": -0.087835, + "nauc_precision_at_1000_max": 0.099042, + "nauc_precision_at_1000_std": 0.223177, + "nauc_precision_at_1000_diff1": -0.091972, + "nauc_mrr_at_1_max": -0.321102, + "nauc_mrr_at_1_std": -0.207793, + "nauc_mrr_at_1_diff1": 0.664794, + "nauc_mrr_at_3_max": -0.321102, + "nauc_mrr_at_3_std": -0.207793, + "nauc_mrr_at_3_diff1": 0.664794, + "nauc_mrr_at_5_max": -0.29844, + "nauc_mrr_at_5_std": -0.207793, + "nauc_mrr_at_5_diff1": 0.597752, + "nauc_mrr_at_10_max": -0.300764, + "nauc_mrr_at_10_std": -0.219414, + "nauc_mrr_at_10_diff1": 0.529118, + "nauc_mrr_at_20_max": -0.264382, + "nauc_mrr_at_20_std": -0.113041, + "nauc_mrr_at_20_diff1": 0.351643, + "nauc_mrr_at_100_max": -0.236002, + "nauc_mrr_at_100_std": -0.103816, + "nauc_mrr_at_100_diff1": 0.299161, + "nauc_mrr_at_1000_max": -0.226311, + "nauc_mrr_at_1000_std": -0.091842, + "nauc_mrr_at_1000_diff1": 0.288984, + "main_score": 0.00669, + "hf_subset": "MedQA-Diag", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.00667, + "ndcg_at_3": 0.01197, + "ndcg_at_5": 0.01285, + "ndcg_at_10": 0.01868, + "ndcg_at_20": 0.02283, + "ndcg_at_100": 0.03454, + "ndcg_at_1000": 0.05486, + "map_at_1": 0.00333, + "map_at_3": 0.00833, + "map_at_5": 0.0086, + "map_at_10": 0.01058, + "map_at_20": 0.01167, + "map_at_100": 0.01295, + "map_at_1000": 0.01358, + "recall_at_1": 0.00333, + "recall_at_3": 0.01556, + "recall_at_5": 0.01689, + "recall_at_10": 0.03356, + "recall_at_20": 0.04911, + "recall_at_100": 0.10344, + "recall_at_1000": 0.24578, + "precision_at_1": 0.00667, + "precision_at_3": 0.00889, + "precision_at_5": 0.00667, + "precision_at_10": 0.006, + "precision_at_20": 0.004, + "precision_at_100": 0.002, + "precision_at_1000": 0.00047, + "mrr_at_1": 0.006667, + "mrr_at_3": 0.015556, + "mrr_at_5": 0.016889, + "mrr_at_10": 0.020008, + "mrr_at_20": 0.021335, + "mrr_at_100": 0.023067, + "mrr_at_1000": 0.023973, + "nauc_ndcg_at_1_max": -0.499598, + "nauc_ndcg_at_1_std": -0.499598, + "nauc_ndcg_at_1_diff1": -0.574725, + "nauc_ndcg_at_3_max": -0.36184, + "nauc_ndcg_at_3_std": -0.215186, + "nauc_ndcg_at_3_diff1": -0.387384, + "nauc_ndcg_at_5_max": -0.358888, + "nauc_ndcg_at_5_std": -0.155475, + "nauc_ndcg_at_5_diff1": -0.38927, + "nauc_ndcg_at_10_max": -0.259724, + "nauc_ndcg_at_10_std": -0.023965, + "nauc_ndcg_at_10_diff1": -0.282468, + "nauc_ndcg_at_20_max": -0.127852, + "nauc_ndcg_at_20_std": 0.111519, + "nauc_ndcg_at_20_diff1": -0.27907, + "nauc_ndcg_at_100_max": -0.117196, + "nauc_ndcg_at_100_std": 0.037767, + "nauc_ndcg_at_100_diff1": -0.261511, + "nauc_ndcg_at_1000_max": -0.029728, + "nauc_ndcg_at_1000_std": 0.074848, + "nauc_ndcg_at_1000_diff1": -0.100008, + "nauc_map_at_1_max": -0.499598, + "nauc_map_at_1_std": -0.499598, + "nauc_map_at_1_diff1": -0.574725, + "nauc_map_at_3_max": -0.37587, + "nauc_map_at_3_std": -0.230516, + "nauc_map_at_3_diff1": -0.405957, + "nauc_map_at_5_max": -0.37409, + "nauc_map_at_5_std": -0.202843, + "nauc_map_at_5_diff1": -0.406239, + "nauc_map_at_10_max": -0.319152, + "nauc_map_at_10_std": -0.124344, + "nauc_map_at_10_diff1": -0.338393, + "nauc_map_at_20_max": -0.240465, + "nauc_map_at_20_std": -0.047285, + "nauc_map_at_20_diff1": -0.332245, + "nauc_map_at_100_max": -0.232176, + "nauc_map_at_100_std": -0.052581, + "nauc_map_at_100_diff1": -0.32527, + "nauc_map_at_1000_max": -0.216638, + "nauc_map_at_1000_std": -0.048575, + "nauc_map_at_1000_diff1": -0.304384, + "nauc_recall_at_1_max": -0.499598, + "nauc_recall_at_1_std": -0.499598, + "nauc_recall_at_1_diff1": -0.574725, + "nauc_recall_at_3_max": -0.377765, + "nauc_recall_at_3_std": -0.150006, + "nauc_recall_at_3_diff1": -0.357296, + "nauc_recall_at_5_max": -0.373085, + "nauc_recall_at_5_std": -0.085906, + "nauc_recall_at_5_diff1": -0.361858, + "nauc_recall_at_10_max": -0.218509, + "nauc_recall_at_10_std": 0.084033, + "nauc_recall_at_10_diff1": -0.208221, + "nauc_recall_at_20_max": -0.024648, + "nauc_recall_at_20_std": 0.282374, + "nauc_recall_at_20_diff1": -0.233568, + "nauc_recall_at_100_max": -0.047547, + "nauc_recall_at_100_std": 0.085225, + "nauc_recall_at_100_diff1": -0.229589, + "nauc_recall_at_1000_max": 0.067553, + "nauc_recall_at_1000_std": 0.158386, + "nauc_recall_at_1000_diff1": 0.041576, + "nauc_precision_at_1_max": -0.499598, + "nauc_precision_at_1_std": -0.499598, + "nauc_precision_at_1_diff1": -0.574725, + "nauc_precision_at_3_max": -0.323585, + "nauc_precision_at_3_std": -0.205259, + "nauc_precision_at_3_diff1": -0.354373, + "nauc_precision_at_5_max": -0.322565, + "nauc_precision_at_5_std": -0.031822, + "nauc_precision_at_5_diff1": -0.366515, + "nauc_precision_at_10_max": -0.167457, + "nauc_precision_at_10_std": 0.132516, + "nauc_precision_at_10_diff1": -0.224965, + "nauc_precision_at_20_max": 0.006484, + "nauc_precision_at_20_std": 0.293042, + "nauc_precision_at_20_diff1": -0.219301, + "nauc_precision_at_100_max": -0.019969, + "nauc_precision_at_100_std": 0.057866, + "nauc_precision_at_100_diff1": -0.211394, + "nauc_precision_at_1000_max": 0.091798, + "nauc_precision_at_1000_std": 0.075157, + "nauc_precision_at_1000_diff1": 0.048381, + "nauc_mrr_at_1_max": -0.499598, + "nauc_mrr_at_1_std": -0.499598, + "nauc_mrr_at_1_diff1": -0.574725, + "nauc_mrr_at_3_max": -0.343363, + "nauc_mrr_at_3_std": -0.277952, + "nauc_mrr_at_3_diff1": -0.404155, + "nauc_mrr_at_5_max": -0.341399, + "nauc_mrr_at_5_std": -0.203751, + "nauc_mrr_at_5_diff1": -0.405017, + "nauc_mrr_at_10_max": -0.286707, + "nauc_mrr_at_10_std": -0.126129, + "nauc_mrr_at_10_diff1": -0.347462, + "nauc_mrr_at_20_max": -0.231224, + "nauc_mrr_at_20_std": -0.071543, + "nauc_mrr_at_20_diff1": -0.338745, + "nauc_mrr_at_100_max": -0.231146, + "nauc_mrr_at_100_std": -0.081845, + "nauc_mrr_at_100_diff1": -0.326781, + "nauc_mrr_at_1000_max": -0.220969, + "nauc_mrr_at_1000_std": -0.080624, + "nauc_mrr_at_1000_diff1": -0.310809, + "main_score": 0.01868, + "hf_subset": "PMC-Treatment", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.04386, + "ndcg_at_3": 0.04349, + "ndcg_at_5": 0.04721, + "ndcg_at_10": 0.0505, + "ndcg_at_20": 0.06003, + "ndcg_at_100": 0.07881, + "ndcg_at_1000": 0.11513, + "map_at_1": 0.02339, + "map_at_3": 0.03423, + "map_at_5": 0.03599, + "map_at_10": 0.03714, + "map_at_20": 0.03941, + "map_at_100": 0.04183, + "map_at_1000": 0.04325, + "recall_at_1": 0.02339, + "recall_at_3": 0.04605, + "recall_at_5": 0.05482, + "recall_at_10": 0.06213, + "recall_at_20": 0.09357, + "recall_at_100": 0.17251, + "recall_at_1000": 0.40643, + "precision_at_1": 0.04386, + "precision_at_3": 0.02632, + "precision_at_5": 0.0193, + "precision_at_10": 0.0114, + "precision_at_20": 0.00877, + "precision_at_100": 0.00377, + "precision_at_1000": 0.00089, + "mrr_at_1": 0.04386, + "mrr_at_3": 0.059942, + "mrr_at_5": 0.06345, + "mrr_at_10": 0.066165, + "mrr_at_20": 0.07048, + "mrr_at_100": 0.073484, + "mrr_at_1000": 0.07489, + "nauc_ndcg_at_1_max": 0.340155, + "nauc_ndcg_at_1_std": -0.130455, + "nauc_ndcg_at_1_diff1": 0.255038, + "nauc_ndcg_at_3_max": 0.281964, + "nauc_ndcg_at_3_std": -0.183834, + "nauc_ndcg_at_3_diff1": 0.124796, + "nauc_ndcg_at_5_max": 0.249564, + "nauc_ndcg_at_5_std": -0.177564, + "nauc_ndcg_at_5_diff1": 0.162379, + "nauc_ndcg_at_10_max": 0.250287, + "nauc_ndcg_at_10_std": -0.13296, + "nauc_ndcg_at_10_diff1": 0.175002, + "nauc_ndcg_at_20_max": 0.205715, + "nauc_ndcg_at_20_std": -0.154506, + "nauc_ndcg_at_20_diff1": 0.162098, + "nauc_ndcg_at_100_max": 0.170109, + "nauc_ndcg_at_100_std": -0.064932, + "nauc_ndcg_at_100_diff1": 0.082506, + "nauc_ndcg_at_1000_max": 0.132429, + "nauc_ndcg_at_1000_std": -0.008887, + "nauc_ndcg_at_1000_diff1": 0.00596, + "nauc_map_at_1_max": 0.320926, + "nauc_map_at_1_std": -0.114088, + "nauc_map_at_1_diff1": 0.419259, + "nauc_map_at_3_max": 0.286529, + "nauc_map_at_3_std": -0.171872, + "nauc_map_at_3_diff1": 0.181553, + "nauc_map_at_5_max": 0.265904, + "nauc_map_at_5_std": -0.170151, + "nauc_map_at_5_diff1": 0.199426, + "nauc_map_at_10_max": 0.267837, + "nauc_map_at_10_std": -0.147572, + "nauc_map_at_10_diff1": 0.206032, + "nauc_map_at_20_max": 0.253814, + "nauc_map_at_20_std": -0.153629, + "nauc_map_at_20_diff1": 0.200001, + "nauc_map_at_100_max": 0.241627, + "nauc_map_at_100_std": -0.136918, + "nauc_map_at_100_diff1": 0.182075, + "nauc_map_at_1000_max": 0.23594, + "nauc_map_at_1000_std": -0.1304, + "nauc_map_at_1000_diff1": 0.173875, + "nauc_recall_at_1_max": 0.320926, + "nauc_recall_at_1_std": -0.114088, + "nauc_recall_at_1_diff1": 0.419259, + "nauc_recall_at_3_max": 0.276812, + "nauc_recall_at_3_std": -0.199058, + "nauc_recall_at_3_diff1": 0.050287, + "nauc_recall_at_5_max": 0.210672, + "nauc_recall_at_5_std": -0.189059, + "nauc_recall_at_5_diff1": 0.129953, + "nauc_recall_at_10_max": 0.214814, + "nauc_recall_at_10_std": -0.102431, + "nauc_recall_at_10_diff1": 0.155623, + "nauc_recall_at_20_max": 0.11819, + "nauc_recall_at_20_std": -0.157334, + "nauc_recall_at_20_diff1": 0.132243, + "nauc_recall_at_100_max": 0.077964, + "nauc_recall_at_100_std": 0.061594, + "nauc_recall_at_100_diff1": -0.022771, + "nauc_recall_at_1000_max": 0.01578, + "nauc_recall_at_1000_std": 0.201954, + "nauc_recall_at_1000_diff1": -0.16043, + "nauc_precision_at_1_max": 0.340155, + "nauc_precision_at_1_std": -0.130455, + "nauc_precision_at_1_diff1": 0.255038, + "nauc_precision_at_3_max": 0.286763, + "nauc_precision_at_3_std": -0.194216, + "nauc_precision_at_3_diff1": 0.031436, + "nauc_precision_at_5_max": 0.209795, + "nauc_precision_at_5_std": -0.183734, + "nauc_precision_at_5_diff1": 0.125393, + "nauc_precision_at_10_max": 0.200352, + "nauc_precision_at_10_std": -0.088629, + "nauc_precision_at_10_diff1": 0.148605, + "nauc_precision_at_20_max": 0.086844, + "nauc_precision_at_20_std": -0.158906, + "nauc_precision_at_20_diff1": 0.118373, + "nauc_precision_at_100_max": 0.033578, + "nauc_precision_at_100_std": 0.080821, + "nauc_precision_at_100_diff1": -0.08086, + "nauc_precision_at_1000_max": -0.027018, + "nauc_precision_at_1000_std": 0.098145, + "nauc_precision_at_1000_diff1": -0.230006, + "nauc_mrr_at_1_max": 0.340155, + "nauc_mrr_at_1_std": -0.130455, + "nauc_mrr_at_1_diff1": 0.255038, + "nauc_mrr_at_3_max": 0.297366, + "nauc_mrr_at_3_std": -0.173928, + "nauc_mrr_at_3_diff1": 0.121711, + "nauc_mrr_at_5_max": 0.27337, + "nauc_mrr_at_5_std": -0.171862, + "nauc_mrr_at_5_diff1": 0.145296, + "nauc_mrr_at_10_max": 0.271061, + "nauc_mrr_at_10_std": -0.146113, + "nauc_mrr_at_10_diff1": 0.152072, + "nauc_mrr_at_20_max": 0.25387, + "nauc_mrr_at_20_std": -0.151187, + "nauc_mrr_at_20_diff1": 0.145225, + "nauc_mrr_at_100_max": 0.24688, + "nauc_mrr_at_100_std": -0.143883, + "nauc_mrr_at_100_diff1": 0.131004, + "nauc_mrr_at_1000_max": 0.24323, + "nauc_mrr_at_1000_std": -0.143719, + "nauc_mrr_at_1000_diff1": 0.127933, + "main_score": 0.0505, + "hf_subset": "PMC-Clinical", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.07752, + "ndcg_at_3": 0.07341, + "ndcg_at_5": 0.07278, + "ndcg_at_10": 0.0901, + "ndcg_at_20": 0.10565, + "ndcg_at_100": 0.16663, + "ndcg_at_1000": 0.23558, + "map_at_1": 0.02171, + "map_at_3": 0.03755, + "map_at_5": 0.04242, + "map_at_10": 0.04922, + "map_at_20": 0.05322, + "map_at_100": 0.06369, + "map_at_1000": 0.06751, + "recall_at_1": 0.02171, + "recall_at_3": 0.05413, + "recall_at_5": 0.077, + "recall_at_10": 0.11279, + "recall_at_20": 0.15401, + "recall_at_100": 0.37287, + "recall_at_1000": 0.75982, + "precision_at_1": 0.07752, + "precision_at_3": 0.06977, + "precision_at_5": 0.05116, + "precision_at_10": 0.04031, + "precision_at_20": 0.02829, + "precision_at_100": 0.01434, + "precision_at_1000": 0.00275, + "mrr_at_1": 0.077519, + "mrr_at_3": 0.125323, + "mrr_at_5": 0.135788, + "mrr_at_10": 0.148111, + "mrr_at_20": 0.152797, + "mrr_at_100": 0.159779, + "mrr_at_1000": 0.160914, + "nauc_ndcg_at_1_max": 0.151471, + "nauc_ndcg_at_1_std": -0.229931, + "nauc_ndcg_at_1_diff1": 0.191078, + "nauc_ndcg_at_3_max": 0.180062, + "nauc_ndcg_at_3_std": -0.029156, + "nauc_ndcg_at_3_diff1": 0.129206, + "nauc_ndcg_at_5_max": 0.140703, + "nauc_ndcg_at_5_std": -0.050635, + "nauc_ndcg_at_5_diff1": 0.08263, + "nauc_ndcg_at_10_max": 0.143211, + "nauc_ndcg_at_10_std": -0.010213, + "nauc_ndcg_at_10_diff1": 0.05153, + "nauc_ndcg_at_20_max": 0.148723, + "nauc_ndcg_at_20_std": 0.057178, + "nauc_ndcg_at_20_diff1": 0.014044, + "nauc_ndcg_at_100_max": 0.225133, + "nauc_ndcg_at_100_std": 0.16203, + "nauc_ndcg_at_100_diff1": -0.027055, + "nauc_ndcg_at_1000_max": 0.256926, + "nauc_ndcg_at_1000_std": 0.182725, + "nauc_ndcg_at_1000_diff1": 0.020906, + "nauc_map_at_1_max": 0.206694, + "nauc_map_at_1_std": -0.276189, + "nauc_map_at_1_diff1": 0.204899, + "nauc_map_at_3_max": 0.189122, + "nauc_map_at_3_std": -0.101802, + "nauc_map_at_3_diff1": 0.118517, + "nauc_map_at_5_max": 0.140139, + "nauc_map_at_5_std": -0.114887, + "nauc_map_at_5_diff1": 0.093255, + "nauc_map_at_10_max": 0.139022, + "nauc_map_at_10_std": -0.082127, + "nauc_map_at_10_diff1": 0.076559, + "nauc_map_at_20_max": 0.145411, + "nauc_map_at_20_std": -0.051722, + "nauc_map_at_20_diff1": 0.065786, + "nauc_map_at_100_max": 0.162631, + "nauc_map_at_100_std": -0.007498, + "nauc_map_at_100_diff1": 0.044888, + "nauc_map_at_1000_max": 0.165497, + "nauc_map_at_1000_std": -0.004183, + "nauc_map_at_1000_diff1": 0.046666, + "nauc_recall_at_1_max": 0.206694, + "nauc_recall_at_1_std": -0.276189, + "nauc_recall_at_1_diff1": 0.204899, + "nauc_recall_at_3_max": 0.202687, + "nauc_recall_at_3_std": 0.0106, + "nauc_recall_at_3_diff1": 0.08484, + "nauc_recall_at_5_max": 0.046077, + "nauc_recall_at_5_std": -0.060028, + "nauc_recall_at_5_diff1": 0.021828, + "nauc_recall_at_10_max": 0.066731, + "nauc_recall_at_10_std": 0.015825, + "nauc_recall_at_10_diff1": -0.016374, + "nauc_recall_at_20_max": 0.081045, + "nauc_recall_at_20_std": 0.144286, + "nauc_recall_at_20_diff1": -0.089104, + "nauc_recall_at_100_max": 0.245222, + "nauc_recall_at_100_std": 0.27495, + "nauc_recall_at_100_diff1": -0.118156, + "nauc_recall_at_1000_max": 0.359414, + "nauc_recall_at_1000_std": 0.399481, + "nauc_recall_at_1000_diff1": 0.066274, + "nauc_precision_at_1_max": 0.151471, + "nauc_precision_at_1_std": -0.229931, + "nauc_precision_at_1_diff1": 0.191078, + "nauc_precision_at_3_max": 0.167014, + "nauc_precision_at_3_std": 0.038313, + "nauc_precision_at_3_diff1": 0.124796, + "nauc_precision_at_5_max": 0.130479, + "nauc_precision_at_5_std": 0.045175, + "nauc_precision_at_5_diff1": 0.075439, + "nauc_precision_at_10_max": 0.132987, + "nauc_precision_at_10_std": 0.119881, + "nauc_precision_at_10_diff1": 0.012937, + "nauc_precision_at_20_max": 0.129113, + "nauc_precision_at_20_std": 0.234261, + "nauc_precision_at_20_diff1": -0.058145, + "nauc_precision_at_100_max": 0.218642, + "nauc_precision_at_100_std": 0.350421, + "nauc_precision_at_100_diff1": -0.096879, + "nauc_precision_at_1000_max": 0.231897, + "nauc_precision_at_1000_std": 0.333623, + "nauc_precision_at_1000_diff1": -0.025798, + "nauc_mrr_at_1_max": 0.151471, + "nauc_mrr_at_1_std": -0.229931, + "nauc_mrr_at_1_diff1": 0.191078, + "nauc_mrr_at_3_max": 0.211358, + "nauc_mrr_at_3_std": -0.027712, + "nauc_mrr_at_3_diff1": 0.14291, + "nauc_mrr_at_5_max": 0.199157, + "nauc_mrr_at_5_std": -0.019165, + "nauc_mrr_at_5_diff1": 0.122683, + "nauc_mrr_at_10_max": 0.191466, + "nauc_mrr_at_10_std": -0.010998, + "nauc_mrr_at_10_diff1": 0.101568, + "nauc_mrr_at_20_max": 0.190938, + "nauc_mrr_at_20_std": 0.002005, + "nauc_mrr_at_20_diff1": 0.089711, + "nauc_mrr_at_100_max": 0.203694, + "nauc_mrr_at_100_std": 0.010104, + "nauc_mrr_at_100_diff1": 0.087498, + "nauc_mrr_at_1000_max": 0.203164, + "nauc_mrr_at_1000_std": 0.008418, + "nauc_mrr_at_1000_diff1": 0.090612, + "main_score": 0.0901, + "hf_subset": "IIYi-Clinical", + "languages": [ + "eng-Latn" + ] + } + ] + }, + "evaluation_time": 352.16485810279846, + "kg_co2_emissions": null +} \ No newline at end of file diff --git a/results/yibinlei__LENS-d4000/external/R2MEDRetrieval.json b/results/yibinlei__LENS-d4000/external/R2MEDRetrieval.json new file mode 100644 index 0000000000..5c2a899e1b --- /dev/null +++ b/results/yibinlei__LENS-d4000/external/R2MEDRetrieval.json @@ -0,0 +1,1187 @@ +{ + "dataset_revision": "1.0", + "task_name": "R2MEDRetrieval", + "mteb_version": "1.38.20", + "scores": { + "test": [ + { + "ndcg_at_1": 0.1068, + "ndcg_at_3": 0.06777, + "ndcg_at_5": 0.06658, + "ndcg_at_10": 0.07264, + "ndcg_at_20": 0.08415, + "ndcg_at_100": 0.12441, + "ndcg_at_1000": 0.17456, + "map_at_1": 0.02763, + "map_at_3": 0.03426, + "map_at_5": 0.03864, + "map_at_10": 0.04567, + "map_at_20": 0.04898, + "map_at_100": 0.0556, + "map_at_1000": 0.05812, + "recall_at_1": 0.02763, + "recall_at_3": 0.03952, + "recall_at_5": 0.04893, + "recall_at_10": 0.07597, + "recall_at_20": 0.1047, + "recall_at_100": 0.25677, + "recall_at_1000": 0.53732, + "precision_at_1": 0.1068, + "precision_at_3": 0.05502, + "precision_at_5": 0.0466, + "precision_at_10": 0.03398, + "precision_at_20": 0.02379, + "precision_at_100": 0.01019, + "precision_at_1000": 0.00206, + "mrr_at_1": 0.106796, + "mrr_at_3": 0.118123, + "mrr_at_5": 0.122006, + "mrr_at_10": 0.12609, + "mrr_at_20": 0.130158, + "mrr_at_100": 0.135751, + "mrr_at_1000": 0.136782, + "nauc_ndcg_at_1_max": -0.052281, + "nauc_ndcg_at_1_std": -0.133218, + "nauc_ndcg_at_1_diff1": 0.20461, + "nauc_ndcg_at_3_max": -0.066763, + "nauc_ndcg_at_3_std": -0.129649, + "nauc_ndcg_at_3_diff1": 0.15166, + "nauc_ndcg_at_5_max": -0.106513, + "nauc_ndcg_at_5_std": -0.164295, + "nauc_ndcg_at_5_diff1": 0.152603, + "nauc_ndcg_at_10_max": -0.158661, + "nauc_ndcg_at_10_std": -0.165949, + "nauc_ndcg_at_10_diff1": 0.081436, + "nauc_ndcg_at_20_max": -0.129569, + "nauc_ndcg_at_20_std": -0.17217, + "nauc_ndcg_at_20_diff1": 0.132054, + "nauc_ndcg_at_100_max": -0.032572, + "nauc_ndcg_at_100_std": -0.111738, + "nauc_ndcg_at_100_diff1": 0.122135, + "nauc_ndcg_at_1000_max": 0.00214, + "nauc_ndcg_at_1000_std": -0.047895, + "nauc_ndcg_at_1000_diff1": 0.086292, + "nauc_map_at_1_max": -0.148871, + "nauc_map_at_1_std": -0.157786, + "nauc_map_at_1_diff1": 0.078301, + "nauc_map_at_3_max": -0.154611, + "nauc_map_at_3_std": -0.164156, + "nauc_map_at_3_diff1": 0.094476, + "nauc_map_at_5_max": -0.147927, + "nauc_map_at_5_std": -0.1647, + "nauc_map_at_5_diff1": 0.127728, + "nauc_map_at_10_max": -0.173048, + "nauc_map_at_10_std": -0.188381, + "nauc_map_at_10_diff1": 0.10306, + "nauc_map_at_20_max": -0.160082, + "nauc_map_at_20_std": -0.188324, + "nauc_map_at_20_diff1": 0.131002, + "nauc_map_at_100_max": -0.125787, + "nauc_map_at_100_std": -0.172684, + "nauc_map_at_100_diff1": 0.137957, + "nauc_map_at_1000_max": -0.119268, + "nauc_map_at_1000_std": -0.167009, + "nauc_map_at_1000_diff1": 0.135247, + "nauc_recall_at_1_max": -0.148871, + "nauc_recall_at_1_std": -0.157786, + "nauc_recall_at_1_diff1": 0.078301, + "nauc_recall_at_3_max": -0.14839, + "nauc_recall_at_3_std": -0.135637, + "nauc_recall_at_3_diff1": 0.072396, + "nauc_recall_at_5_max": -0.161628, + "nauc_recall_at_5_std": -0.139036, + "nauc_recall_at_5_diff1": 0.108075, + "nauc_recall_at_10_max": -0.232793, + "nauc_recall_at_10_std": -0.191305, + "nauc_recall_at_10_diff1": 0.025772, + "nauc_recall_at_20_max": -0.138591, + "nauc_recall_at_20_std": -0.193956, + "nauc_recall_at_20_diff1": 0.150124, + "nauc_recall_at_100_max": 0.091038, + "nauc_recall_at_100_std": -0.029693, + "nauc_recall_at_100_diff1": 0.114708, + "nauc_recall_at_1000_max": 0.178789, + "nauc_recall_at_1000_std": 0.14309, + "nauc_recall_at_1000_diff1": 0.0181, + "nauc_precision_at_1_max": -0.052281, + "nauc_precision_at_1_std": -0.133218, + "nauc_precision_at_1_diff1": 0.20461, + "nauc_precision_at_3_max": -0.046243, + "nauc_precision_at_3_std": -0.105884, + "nauc_precision_at_3_diff1": 0.15116, + "nauc_precision_at_5_max": -0.078459, + "nauc_precision_at_5_std": -0.144129, + "nauc_precision_at_5_diff1": 0.194782, + "nauc_precision_at_10_max": -0.13223, + "nauc_precision_at_10_std": -0.181351, + "nauc_precision_at_10_diff1": 0.07651, + "nauc_precision_at_20_max": -0.097175, + "nauc_precision_at_20_std": -0.188539, + "nauc_precision_at_20_diff1": 0.175967, + "nauc_precision_at_100_max": 0.018928, + "nauc_precision_at_100_std": -0.079517, + "nauc_precision_at_100_diff1": 0.115856, + "nauc_precision_at_1000_max": 0.021037, + "nauc_precision_at_1000_std": 0.022427, + "nauc_precision_at_1000_diff1": -0.017602, + "nauc_mrr_at_1_max": -0.052281, + "nauc_mrr_at_1_std": -0.133218, + "nauc_mrr_at_1_diff1": 0.20461, + "nauc_mrr_at_3_max": -0.047921, + "nauc_mrr_at_3_std": -0.09881, + "nauc_mrr_at_3_diff1": 0.165479, + "nauc_mrr_at_5_max": -0.060149, + "nauc_mrr_at_5_std": -0.111813, + "nauc_mrr_at_5_diff1": 0.144911, + "nauc_mrr_at_10_max": -0.072144, + "nauc_mrr_at_10_std": -0.117545, + "nauc_mrr_at_10_diff1": 0.132001, + "nauc_mrr_at_20_max": -0.067506, + "nauc_mrr_at_20_std": -0.120672, + "nauc_mrr_at_20_diff1": 0.13685, + "nauc_mrr_at_100_max": -0.054223, + "nauc_mrr_at_100_std": -0.113049, + "nauc_mrr_at_100_diff1": 0.133577, + "nauc_mrr_at_1000_max": -0.054359, + "nauc_mrr_at_1000_std": -0.111048, + "nauc_mrr_at_1000_diff1": 0.133763, + "main_score": 0.07264, + "hf_subset": "Biology", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.19481, + "ndcg_at_3": 0.25164, + "ndcg_at_5": 0.26312, + "ndcg_at_10": 0.29616, + "ndcg_at_20": 0.33555, + "ndcg_at_100": 0.4017, + "ndcg_at_1000": 0.43753, + "map_at_1": 0.11224, + "map_at_3": 0.18236, + "map_at_5": 0.20399, + "map_at_10": 0.22593, + "map_at_20": 0.24072, + "map_at_100": 0.25449, + "map_at_1000": 0.2569, + "recall_at_1": 0.11224, + "recall_at_3": 0.24561, + "recall_at_5": 0.30472, + "recall_at_10": 0.39351, + "recall_at_20": 0.50407, + "recall_at_100": 0.77338, + "recall_at_1000": 0.97897, + "precision_at_1": 0.19481, + "precision_at_3": 0.18182, + "precision_at_5": 0.14026, + "precision_at_10": 0.1, + "precision_at_20": 0.06948, + "precision_at_100": 0.02195, + "precision_at_1000": 0.0029, + "mrr_at_1": 0.194805, + "mrr_at_3": 0.287879, + "mrr_at_5": 0.298918, + "mrr_at_10": 0.315543, + "mrr_at_20": 0.322773, + "mrr_at_100": 0.32715, + "mrr_at_1000": 0.327594, + "nauc_ndcg_at_1_max": -0.123489, + "nauc_ndcg_at_1_std": 0.015859, + "nauc_ndcg_at_1_diff1": 0.268458, + "nauc_ndcg_at_3_max": -0.065921, + "nauc_ndcg_at_3_std": -0.002329, + "nauc_ndcg_at_3_diff1": 0.273809, + "nauc_ndcg_at_5_max": -0.059544, + "nauc_ndcg_at_5_std": -0.055747, + "nauc_ndcg_at_5_diff1": 0.284879, + "nauc_ndcg_at_10_max": -0.028136, + "nauc_ndcg_at_10_std": -0.073, + "nauc_ndcg_at_10_diff1": 0.303726, + "nauc_ndcg_at_20_max": -0.017695, + "nauc_ndcg_at_20_std": -0.021698, + "nauc_ndcg_at_20_diff1": 0.253979, + "nauc_ndcg_at_100_max": -0.029021, + "nauc_ndcg_at_100_std": -0.027461, + "nauc_ndcg_at_100_diff1": 0.220997, + "nauc_ndcg_at_1000_max": -0.019842, + "nauc_ndcg_at_1000_std": -0.011465, + "nauc_ndcg_at_1000_diff1": 0.232673, + "nauc_map_at_1_max": -0.108608, + "nauc_map_at_1_std": 0.117084, + "nauc_map_at_1_diff1": 0.286231, + "nauc_map_at_3_max": -0.063309, + "nauc_map_at_3_std": 0.038944, + "nauc_map_at_3_diff1": 0.311899, + "nauc_map_at_5_max": -0.06163, + "nauc_map_at_5_std": -0.011259, + "nauc_map_at_5_diff1": 0.300195, + "nauc_map_at_10_max": -0.045221, + "nauc_map_at_10_std": -0.039442, + "nauc_map_at_10_diff1": 0.311421, + "nauc_map_at_20_max": -0.04256, + "nauc_map_at_20_std": -0.016164, + "nauc_map_at_20_diff1": 0.288049, + "nauc_map_at_100_max": -0.047116, + "nauc_map_at_100_std": -0.015526, + "nauc_map_at_100_diff1": 0.276668, + "nauc_map_at_1000_max": -0.046239, + "nauc_map_at_1000_std": -0.014213, + "nauc_map_at_1000_diff1": 0.276768, + "nauc_recall_at_1_max": -0.108608, + "nauc_recall_at_1_std": 0.117084, + "nauc_recall_at_1_diff1": 0.286231, + "nauc_recall_at_3_max": -0.014198, + "nauc_recall_at_3_std": 0.020513, + "nauc_recall_at_3_diff1": 0.309867, + "nauc_recall_at_5_max": -0.036299, + "nauc_recall_at_5_std": -0.090642, + "nauc_recall_at_5_diff1": 0.279162, + "nauc_recall_at_10_max": -0.00629, + "nauc_recall_at_10_std": -0.142467, + "nauc_recall_at_10_diff1": 0.309833, + "nauc_recall_at_20_max": 0.027746, + "nauc_recall_at_20_std": -0.02897, + "nauc_recall_at_20_diff1": 0.18959, + "nauc_recall_at_100_max": -0.080267, + "nauc_recall_at_100_std": -0.157566, + "nauc_recall_at_100_diff1": -0.013886, + "nauc_recall_at_1000_max": -0.537313, + "nauc_recall_at_1000_std": -0.764567, + "nauc_recall_at_1000_diff1": -1.058853, + "nauc_precision_at_1_max": -0.123489, + "nauc_precision_at_1_std": 0.015859, + "nauc_precision_at_1_diff1": 0.268458, + "nauc_precision_at_3_max": -0.032817, + "nauc_precision_at_3_std": -0.04372, + "nauc_precision_at_3_diff1": 0.178316, + "nauc_precision_at_5_max": -0.022921, + "nauc_precision_at_5_std": -0.135249, + "nauc_precision_at_5_diff1": 0.138022, + "nauc_precision_at_10_max": 0.025197, + "nauc_precision_at_10_std": -0.157043, + "nauc_precision_at_10_diff1": 0.142611, + "nauc_precision_at_20_max": 0.033016, + "nauc_precision_at_20_std": 0.003162, + "nauc_precision_at_20_diff1": -0.012221, + "nauc_precision_at_100_max": 0.061749, + "nauc_precision_at_100_std": 0.057302, + "nauc_precision_at_100_diff1": -0.090627, + "nauc_precision_at_1000_max": 0.113752, + "nauc_precision_at_1000_std": 0.132971, + "nauc_precision_at_1000_diff1": -0.056119, + "nauc_mrr_at_1_max": -0.123489, + "nauc_mrr_at_1_std": 0.015859, + "nauc_mrr_at_1_diff1": 0.268458, + "nauc_mrr_at_3_max": -0.067822, + "nauc_mrr_at_3_std": -0.033777, + "nauc_mrr_at_3_diff1": 0.254843, + "nauc_mrr_at_5_max": -0.069702, + "nauc_mrr_at_5_std": -0.054938, + "nauc_mrr_at_5_diff1": 0.261727, + "nauc_mrr_at_10_max": -0.066503, + "nauc_mrr_at_10_std": -0.055574, + "nauc_mrr_at_10_diff1": 0.25538, + "nauc_mrr_at_20_max": -0.055904, + "nauc_mrr_at_20_std": -0.046371, + "nauc_mrr_at_20_diff1": 0.252813, + "nauc_mrr_at_100_max": -0.060591, + "nauc_mrr_at_100_std": -0.048963, + "nauc_mrr_at_100_diff1": 0.251248, + "nauc_mrr_at_1000_max": -0.060851, + "nauc_mrr_at_1000_std": -0.048629, + "nauc_mrr_at_1000_diff1": 0.251723, + "main_score": 0.29616, + "hf_subset": "Bioinformatics", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.26136, + "ndcg_at_3": 0.28326, + "ndcg_at_5": 0.32165, + "ndcg_at_10": 0.35422, + "ndcg_at_20": 0.38941, + "ndcg_at_100": 0.44919, + "ndcg_at_1000": 0.46997, + "map_at_1": 0.13203, + "map_at_3": 0.21311, + "map_at_5": 0.24742, + "map_at_10": 0.26912, + "map_at_20": 0.28129, + "map_at_100": 0.29479, + "map_at_1000": 0.2964, + "recall_at_1": 0.13203, + "recall_at_3": 0.27263, + "recall_at_5": 0.38516, + "recall_at_10": 0.47535, + "recall_at_20": 0.57564, + "recall_at_100": 0.80944, + "recall_at_1000": 0.92081, + "precision_at_1": 0.26136, + "precision_at_3": 0.20076, + "precision_at_5": 0.16818, + "precision_at_10": 0.11023, + "precision_at_20": 0.07102, + "precision_at_100": 0.02125, + "precision_at_1000": 0.00253, + "mrr_at_1": 0.261364, + "mrr_at_3": 0.352273, + "mrr_at_5": 0.380682, + "mrr_at_10": 0.389439, + "mrr_at_20": 0.398215, + "mrr_at_100": 0.401574, + "mrr_at_1000": 0.40177, + "nauc_ndcg_at_1_max": 0.13394, + "nauc_ndcg_at_1_std": 0.143822, + "nauc_ndcg_at_1_diff1": 0.187813, + "nauc_ndcg_at_3_max": 0.238915, + "nauc_ndcg_at_3_std": 0.101716, + "nauc_ndcg_at_3_diff1": 0.293863, + "nauc_ndcg_at_5_max": 0.257226, + "nauc_ndcg_at_5_std": 0.033283, + "nauc_ndcg_at_5_diff1": 0.205761, + "nauc_ndcg_at_10_max": 0.240777, + "nauc_ndcg_at_10_std": 0.055518, + "nauc_ndcg_at_10_diff1": 0.15927, + "nauc_ndcg_at_20_max": 0.224031, + "nauc_ndcg_at_20_std": 0.060484, + "nauc_ndcg_at_20_diff1": 0.144576, + "nauc_ndcg_at_100_max": 0.239907, + "nauc_ndcg_at_100_std": 0.121733, + "nauc_ndcg_at_100_diff1": 0.194658, + "nauc_ndcg_at_1000_max": 0.239945, + "nauc_ndcg_at_1000_std": 0.122356, + "nauc_ndcg_at_1000_diff1": 0.198182, + "nauc_map_at_1_max": 0.144995, + "nauc_map_at_1_std": 0.000373, + "nauc_map_at_1_diff1": 0.290945, + "nauc_map_at_3_max": 0.211789, + "nauc_map_at_3_std": 0.037629, + "nauc_map_at_3_diff1": 0.312102, + "nauc_map_at_5_max": 0.223641, + "nauc_map_at_5_std": 0.017152, + "nauc_map_at_5_diff1": 0.245963, + "nauc_map_at_10_max": 0.219143, + "nauc_map_at_10_std": 0.039526, + "nauc_map_at_10_diff1": 0.210844, + "nauc_map_at_20_max": 0.216277, + "nauc_map_at_20_std": 0.042521, + "nauc_map_at_20_diff1": 0.205954, + "nauc_map_at_100_max": 0.218844, + "nauc_map_at_100_std": 0.054927, + "nauc_map_at_100_diff1": 0.214034, + "nauc_map_at_1000_max": 0.21876, + "nauc_map_at_1000_std": 0.055434, + "nauc_map_at_1000_diff1": 0.214627, + "nauc_recall_at_1_max": 0.144995, + "nauc_recall_at_1_std": 0.000373, + "nauc_recall_at_1_diff1": 0.290945, + "nauc_recall_at_3_max": 0.268218, + "nauc_recall_at_3_std": 0.021386, + "nauc_recall_at_3_diff1": 0.348359, + "nauc_recall_at_5_max": 0.282826, + "nauc_recall_at_5_std": -0.064821, + "nauc_recall_at_5_diff1": 0.160713, + "nauc_recall_at_10_max": 0.271588, + "nauc_recall_at_10_std": -0.000687, + "nauc_recall_at_10_diff1": 0.032007, + "nauc_recall_at_20_max": 0.197584, + "nauc_recall_at_20_std": -0.029046, + "nauc_recall_at_20_diff1": -0.033991, + "nauc_recall_at_100_max": 0.258837, + "nauc_recall_at_100_std": 0.223946, + "nauc_recall_at_100_diff1": 0.173764, + "nauc_recall_at_1000_max": 0.323215, + "nauc_recall_at_1000_std": 0.305748, + "nauc_recall_at_1000_diff1": 0.220908, + "nauc_precision_at_1_max": 0.13394, + "nauc_precision_at_1_std": 0.143822, + "nauc_precision_at_1_diff1": 0.187813, + "nauc_precision_at_3_max": 0.198675, + "nauc_precision_at_3_std": 0.190661, + "nauc_precision_at_3_diff1": 0.172576, + "nauc_precision_at_5_max": 0.213551, + "nauc_precision_at_5_std": 0.116248, + "nauc_precision_at_5_diff1": -0.015522, + "nauc_precision_at_10_max": 0.126778, + "nauc_precision_at_10_std": 0.137691, + "nauc_precision_at_10_diff1": -0.112767, + "nauc_precision_at_20_max": 0.101662, + "nauc_precision_at_20_std": 0.198407, + "nauc_precision_at_20_diff1": -0.142648, + "nauc_precision_at_100_max": 0.106339, + "nauc_precision_at_100_std": 0.33142, + "nauc_precision_at_100_diff1": -0.077962, + "nauc_precision_at_1000_max": 0.087513, + "nauc_precision_at_1000_std": 0.289268, + "nauc_precision_at_1000_diff1": -0.060975, + "nauc_mrr_at_1_max": 0.13394, + "nauc_mrr_at_1_std": 0.143822, + "nauc_mrr_at_1_diff1": 0.187813, + "nauc_mrr_at_3_max": 0.207365, + "nauc_mrr_at_3_std": 0.155192, + "nauc_mrr_at_3_diff1": 0.247721, + "nauc_mrr_at_5_max": 0.214979, + "nauc_mrr_at_5_std": 0.122731, + "nauc_mrr_at_5_diff1": 0.21197, + "nauc_mrr_at_10_max": 0.214621, + "nauc_mrr_at_10_std": 0.132439, + "nauc_mrr_at_10_diff1": 0.203047, + "nauc_mrr_at_20_max": 0.20884, + "nauc_mrr_at_20_std": 0.133635, + "nauc_mrr_at_20_diff1": 0.198284, + "nauc_mrr_at_100_max": 0.210915, + "nauc_mrr_at_100_std": 0.134459, + "nauc_mrr_at_100_diff1": 0.207907, + "nauc_mrr_at_1000_max": 0.210885, + "nauc_mrr_at_1000_std": 0.134261, + "nauc_mrr_at_1000_diff1": 0.207859, + "main_score": 0.35422, + "hf_subset": "Medical-Sciences", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.0, + "ndcg_at_3": 0.00484, + "ndcg_at_5": 0.00661, + "ndcg_at_10": 0.01093, + "ndcg_at_20": 0.01985, + "ndcg_at_100": 0.03419, + "ndcg_at_1000": 0.07508, + "map_at_1": 0.0, + "map_at_3": 0.00106, + "map_at_5": 0.00209, + "map_at_10": 0.00391, + "map_at_20": 0.00586, + "map_at_100": 0.00782, + "map_at_1000": 0.00929, + "recall_at_1": 0.0, + "recall_at_3": 0.00319, + "recall_at_5": 0.00835, + "recall_at_10": 0.02209, + "recall_at_20": 0.04993, + "recall_at_100": 0.1094, + "recall_at_1000": 0.37448, + "precision_at_1": 0.0, + "precision_at_3": 0.00687, + "precision_at_5": 0.00825, + "precision_at_10": 0.00619, + "precision_at_20": 0.0067, + "precision_at_100": 0.00289, + "precision_at_1000": 0.00094, + "mrr_at_1": 0.0, + "mrr_at_3": 0.006873, + "mrr_at_5": 0.010997, + "mrr_at_10": 0.0135, + "mrr_at_20": 0.017524, + "mrr_at_100": 0.019746, + "mrr_at_1000": 0.021126, + "nauc_ndcg_at_1_max": NaN, + "nauc_ndcg_at_1_std": NaN, + "nauc_ndcg_at_1_diff1": NaN, + "nauc_ndcg_at_3_max": -0.160187, + "nauc_ndcg_at_3_std": -0.054957, + "nauc_ndcg_at_3_diff1": 0.046667, + "nauc_ndcg_at_5_max": -0.02545, + "nauc_ndcg_at_5_std": -0.14431, + "nauc_ndcg_at_5_diff1": -0.148974, + "nauc_ndcg_at_10_max": 0.147288, + "nauc_ndcg_at_10_std": 0.165707, + "nauc_ndcg_at_10_diff1": 0.087197, + "nauc_ndcg_at_20_max": 0.000315, + "nauc_ndcg_at_20_std": 0.240275, + "nauc_ndcg_at_20_diff1": -0.093833, + "nauc_ndcg_at_100_max": -0.0143, + "nauc_ndcg_at_100_std": 0.201187, + "nauc_ndcg_at_100_diff1": -0.127783, + "nauc_ndcg_at_1000_max": -0.093059, + "nauc_ndcg_at_1000_std": 0.243745, + "nauc_ndcg_at_1000_diff1": -0.069763, + "nauc_map_at_1_max": NaN, + "nauc_map_at_1_std": NaN, + "nauc_map_at_1_diff1": NaN, + "nauc_map_at_3_max": -0.17995, + "nauc_map_at_3_std": -0.066624, + "nauc_map_at_3_diff1": -0.001329, + "nauc_map_at_5_max": -0.02944, + "nauc_map_at_5_std": -0.154244, + "nauc_map_at_5_diff1": -0.182124, + "nauc_map_at_10_max": 0.108522, + "nauc_map_at_10_std": 0.198383, + "nauc_map_at_10_diff1": 0.083351, + "nauc_map_at_20_max": 0.018076, + "nauc_map_at_20_std": 0.240044, + "nauc_map_at_20_diff1": -0.057913, + "nauc_map_at_100_max": 0.024028, + "nauc_map_at_100_std": 0.228321, + "nauc_map_at_100_diff1": -0.081739, + "nauc_map_at_1000_max": 0.01491, + "nauc_map_at_1000_std": 0.236456, + "nauc_map_at_1000_diff1": -0.073661, + "nauc_recall_at_1_max": NaN, + "nauc_recall_at_1_std": NaN, + "nauc_recall_at_1_diff1": NaN, + "nauc_recall_at_3_max": -0.17995, + "nauc_recall_at_3_std": -0.066624, + "nauc_recall_at_3_diff1": -0.001329, + "nauc_recall_at_5_max": 0.008925, + "nauc_recall_at_5_std": -0.176579, + "nauc_recall_at_5_diff1": -0.228209, + "nauc_recall_at_10_max": 0.204065, + "nauc_recall_at_10_std": 0.296627, + "nauc_recall_at_10_diff1": 0.169253, + "nauc_recall_at_20_max": -0.033572, + "nauc_recall_at_20_std": 0.349919, + "nauc_recall_at_20_diff1": -0.115038, + "nauc_recall_at_100_max": -0.07481, + "nauc_recall_at_100_std": 0.212943, + "nauc_recall_at_100_diff1": -0.158364, + "nauc_recall_at_1000_max": -0.165882, + "nauc_recall_at_1000_std": 0.27323, + "nauc_recall_at_1000_diff1": -0.055879, + "nauc_precision_at_1_max": NaN, + "nauc_precision_at_1_std": NaN, + "nauc_precision_at_1_diff1": NaN, + "nauc_precision_at_3_max": -0.160187, + "nauc_precision_at_3_std": -0.054957, + "nauc_precision_at_3_diff1": 0.046667, + "nauc_precision_at_5_max": -0.01717, + "nauc_precision_at_5_std": -0.149801, + "nauc_precision_at_5_diff1": -0.160996, + "nauc_precision_at_10_max": 0.171341, + "nauc_precision_at_10_std": 0.065883, + "nauc_precision_at_10_diff1": 0.058419, + "nauc_precision_at_20_max": 0.027653, + "nauc_precision_at_20_std": 0.163982, + "nauc_precision_at_20_diff1": -0.120536, + "nauc_precision_at_100_max": 0.011268, + "nauc_precision_at_100_std": 0.157589, + "nauc_precision_at_100_diff1": -0.142246, + "nauc_precision_at_1000_max": -0.101314, + "nauc_precision_at_1000_std": 0.196044, + "nauc_precision_at_1000_diff1": -0.04511, + "nauc_mrr_at_1_max": NaN, + "nauc_mrr_at_1_std": NaN, + "nauc_mrr_at_1_diff1": NaN, + "nauc_mrr_at_3_max": -0.160187, + "nauc_mrr_at_3_std": -0.054957, + "nauc_mrr_at_3_diff1": 0.046667, + "nauc_mrr_at_5_max": -0.052924, + "nauc_mrr_at_5_std": -0.12609, + "nauc_mrr_at_5_diff1": -0.10908, + "nauc_mrr_at_10_max": 0.043806, + "nauc_mrr_at_10_std": -0.004815, + "nauc_mrr_at_10_diff1": -0.002307, + "nauc_mrr_at_20_max": -0.005635, + "nauc_mrr_at_20_std": 0.061971, + "nauc_mrr_at_20_diff1": -0.05656, + "nauc_mrr_at_100_max": 0.008471, + "nauc_mrr_at_100_std": 0.087608, + "nauc_mrr_at_100_diff1": -0.059502, + "nauc_mrr_at_1000_max": 0.001291, + "nauc_mrr_at_1000_std": 0.086677, + "nauc_mrr_at_1000_diff1": -0.051222, + "main_score": 0.01093, + "hf_subset": "MedXpertQA-Exam", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.00847, + "ndcg_at_3": 0.00398, + "ndcg_at_5": 0.00441, + "ndcg_at_10": 0.00715, + "ndcg_at_20": 0.01163, + "ndcg_at_100": 0.03562, + "ndcg_at_1000": 0.08435, + "map_at_1": 0.00169, + "map_at_3": 0.00169, + "map_at_5": 0.00226, + "map_at_10": 0.00305, + "map_at_20": 0.00394, + "map_at_100": 0.00675, + "map_at_1000": 0.00854, + "recall_at_1": 0.00169, + "recall_at_3": 0.00169, + "recall_at_5": 0.00452, + "recall_at_10": 0.01003, + "recall_at_20": 0.02141, + "recall_at_100": 0.10858, + "recall_at_1000": 0.36759, + "precision_at_1": 0.00847, + "precision_at_3": 0.00282, + "precision_at_5": 0.00339, + "precision_at_10": 0.00424, + "precision_at_20": 0.00424, + "precision_at_100": 0.00458, + "precision_at_1000": 0.0016, + "mrr_at_1": 0.008475, + "mrr_at_3": 0.008475, + "mrr_at_5": 0.010169, + "mrr_at_10": 0.01217, + "mrr_at_20": 0.015558, + "mrr_at_100": 0.01978, + "mrr_at_1000": 0.021445, + "nauc_ndcg_at_1_max": -0.579509, + "nauc_ndcg_at_1_std": -0.503613, + "nauc_ndcg_at_1_diff1": -0.071437, + "nauc_ndcg_at_3_max": -0.579509, + "nauc_ndcg_at_3_std": -0.503613, + "nauc_ndcg_at_3_diff1": -0.071437, + "nauc_ndcg_at_5_max": -0.579509, + "nauc_ndcg_at_5_std": -0.09625, + "nauc_ndcg_at_5_diff1": -0.192276, + "nauc_ndcg_at_10_max": -0.469536, + "nauc_ndcg_at_10_std": -0.225658, + "nauc_ndcg_at_10_diff1": -0.188344, + "nauc_ndcg_at_20_max": -0.443232, + "nauc_ndcg_at_20_std": -0.209977, + "nauc_ndcg_at_20_diff1": -0.169386, + "nauc_ndcg_at_100_max": -0.263956, + "nauc_ndcg_at_100_std": -0.04867, + "nauc_ndcg_at_100_diff1": -0.032011, + "nauc_ndcg_at_1000_max": -0.216257, + "nauc_ndcg_at_1000_std": -0.013275, + "nauc_ndcg_at_1000_diff1": 0.019209, + "nauc_map_at_1_max": -0.579509, + "nauc_map_at_1_std": -0.503613, + "nauc_map_at_1_diff1": -0.071437, + "nauc_map_at_3_max": -0.579509, + "nauc_map_at_3_std": -0.503613, + "nauc_map_at_3_diff1": -0.071437, + "nauc_map_at_5_max": -0.579509, + "nauc_map_at_5_std": -0.211512, + "nauc_map_at_5_diff1": -0.158085, + "nauc_map_at_10_max": -0.523414, + "nauc_map_at_10_std": -0.271488, + "nauc_map_at_10_diff1": -0.162535, + "nauc_map_at_20_max": -0.496182, + "nauc_map_at_20_std": -0.252081, + "nauc_map_at_20_diff1": -0.166758, + "nauc_map_at_100_max": -0.41308, + "nauc_map_at_100_std": -0.177248, + "nauc_map_at_100_diff1": -0.090132, + "nauc_map_at_1000_max": -0.363397, + "nauc_map_at_1000_std": -0.140905, + "nauc_map_at_1000_diff1": -0.058963, + "nauc_recall_at_1_max": -0.579509, + "nauc_recall_at_1_std": -0.503613, + "nauc_recall_at_1_diff1": -0.071437, + "nauc_recall_at_3_max": -0.579509, + "nauc_recall_at_3_std": -0.503613, + "nauc_recall_at_3_diff1": -0.071437, + "nauc_recall_at_5_max": -0.579509, + "nauc_recall_at_5_std": 0.226641, + "nauc_recall_at_5_diff1": -0.288057, + "nauc_recall_at_10_max": -0.425859, + "nauc_recall_at_10_std": -0.135926, + "nauc_recall_at_10_diff1": -0.231444, + "nauc_recall_at_20_max": -0.414023, + "nauc_recall_at_20_std": -0.165464, + "nauc_recall_at_20_diff1": -0.182899, + "nauc_recall_at_100_max": -0.213061, + "nauc_recall_at_100_std": 0.014215, + "nauc_recall_at_100_diff1": 0.026431, + "nauc_recall_at_1000_max": -0.158911, + "nauc_recall_at_1000_std": 0.024782, + "nauc_recall_at_1000_diff1": 0.073035, + "nauc_precision_at_1_max": -0.579509, + "nauc_precision_at_1_std": -0.503613, + "nauc_precision_at_1_diff1": -0.071437, + "nauc_precision_at_3_max": -0.579509, + "nauc_precision_at_3_std": -0.503613, + "nauc_precision_at_3_diff1": -0.071437, + "nauc_precision_at_5_max": -0.579509, + "nauc_precision_at_5_std": 0.08059, + "nauc_precision_at_5_diff1": -0.244733, + "nauc_precision_at_10_max": -0.39769, + "nauc_precision_at_10_std": -0.23343, + "nauc_precision_at_10_diff1": -0.192957, + "nauc_precision_at_20_max": -0.398167, + "nauc_precision_at_20_std": -0.207609, + "nauc_precision_at_20_diff1": -0.151886, + "nauc_precision_at_100_max": -0.152042, + "nauc_precision_at_100_std": 0.020893, + "nauc_precision_at_100_diff1": -0.041374, + "nauc_precision_at_1000_max": -0.136825, + "nauc_precision_at_1000_std": 0.01886, + "nauc_precision_at_1000_diff1": 0.00025, + "nauc_mrr_at_1_max": -0.579509, + "nauc_mrr_at_1_std": -0.503613, + "nauc_mrr_at_1_diff1": -0.071437, + "nauc_mrr_at_3_max": -0.579509, + "nauc_mrr_at_3_std": -0.503613, + "nauc_mrr_at_3_diff1": -0.071437, + "nauc_mrr_at_5_max": -0.579509, + "nauc_mrr_at_5_std": -0.308879, + "nauc_mrr_at_5_diff1": -0.129203, + "nauc_mrr_at_10_max": -0.509173, + "nauc_mrr_at_10_std": -0.325009, + "nauc_mrr_at_10_diff1": -0.144079, + "nauc_mrr_at_20_max": -0.484928, + "nauc_mrr_at_20_std": -0.293606, + "nauc_mrr_at_20_diff1": -0.14465, + "nauc_mrr_at_100_max": -0.413831, + "nauc_mrr_at_100_std": -0.239181, + "nauc_mrr_at_100_diff1": -0.105028, + "nauc_mrr_at_1000_max": -0.418731, + "nauc_mrr_at_1000_std": -0.240105, + "nauc_mrr_at_1000_diff1": -0.106896, + "main_score": 0.00715, + "hf_subset": "MedQA-Diag", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.10667, + "ndcg_at_3": 0.10326, + "ndcg_at_5": 0.10804, + "ndcg_at_10": 0.12473, + "ndcg_at_20": 0.13754, + "ndcg_at_100": 0.16499, + "ndcg_at_1000": 0.21504, + "map_at_1": 0.06467, + "map_at_3": 0.08291, + "map_at_5": 0.08569, + "map_at_10": 0.09274, + "map_at_20": 0.09618, + "map_at_100": 0.10038, + "map_at_1000": 0.1022, + "recall_at_1": 0.06467, + "recall_at_3": 0.10689, + "recall_at_5": 0.11956, + "recall_at_10": 0.16533, + "recall_at_20": 0.20544, + "recall_at_100": 0.32244, + "recall_at_1000": 0.67333, + "precision_at_1": 0.10667, + "precision_at_3": 0.06, + "precision_at_5": 0.044, + "precision_at_10": 0.03, + "precision_at_20": 0.01967, + "precision_at_100": 0.00667, + "precision_at_1000": 0.00135, + "mrr_at_1": 0.106667, + "mrr_at_3": 0.134444, + "mrr_at_5": 0.143444, + "mrr_at_10": 0.150275, + "mrr_at_20": 0.155103, + "mrr_at_100": 0.159129, + "mrr_at_1000": 0.160362, + "nauc_ndcg_at_1_max": 0.153618, + "nauc_ndcg_at_1_std": 0.227129, + "nauc_ndcg_at_1_diff1": 0.364661, + "nauc_ndcg_at_3_max": 0.067473, + "nauc_ndcg_at_3_std": 0.123792, + "nauc_ndcg_at_3_diff1": 0.236965, + "nauc_ndcg_at_5_max": 0.07644, + "nauc_ndcg_at_5_std": 0.147355, + "nauc_ndcg_at_5_diff1": 0.2161, + "nauc_ndcg_at_10_max": 0.047948, + "nauc_ndcg_at_10_std": 0.164389, + "nauc_ndcg_at_10_diff1": 0.192959, + "nauc_ndcg_at_20_max": 0.053088, + "nauc_ndcg_at_20_std": 0.160068, + "nauc_ndcg_at_20_diff1": 0.183578, + "nauc_ndcg_at_100_max": 0.066059, + "nauc_ndcg_at_100_std": 0.145644, + "nauc_ndcg_at_100_diff1": 0.203041, + "nauc_ndcg_at_1000_max": 0.090132, + "nauc_ndcg_at_1000_std": 0.215228, + "nauc_ndcg_at_1000_diff1": 0.210297, + "nauc_map_at_1_max": 0.087337, + "nauc_map_at_1_std": 0.241758, + "nauc_map_at_1_diff1": 0.293466, + "nauc_map_at_3_max": 0.055556, + "nauc_map_at_3_std": 0.143983, + "nauc_map_at_3_diff1": 0.233836, + "nauc_map_at_5_max": 0.060101, + "nauc_map_at_5_std": 0.150854, + "nauc_map_at_5_diff1": 0.224977, + "nauc_map_at_10_max": 0.046332, + "nauc_map_at_10_std": 0.157373, + "nauc_map_at_10_diff1": 0.211316, + "nauc_map_at_20_max": 0.049727, + "nauc_map_at_20_std": 0.158902, + "nauc_map_at_20_diff1": 0.205997, + "nauc_map_at_100_max": 0.052105, + "nauc_map_at_100_std": 0.156467, + "nauc_map_at_100_diff1": 0.207919, + "nauc_map_at_1000_max": 0.054227, + "nauc_map_at_1000_std": 0.161459, + "nauc_map_at_1000_diff1": 0.208978, + "nauc_recall_at_1_max": 0.087337, + "nauc_recall_at_1_std": 0.241758, + "nauc_recall_at_1_diff1": 0.293466, + "nauc_recall_at_3_max": 0.031829, + "nauc_recall_at_3_std": 0.073159, + "nauc_recall_at_3_diff1": 0.188557, + "nauc_recall_at_5_max": 0.049026, + "nauc_recall_at_5_std": 0.105541, + "nauc_recall_at_5_diff1": 0.161507, + "nauc_recall_at_10_max": -0.012543, + "nauc_recall_at_10_std": 0.154208, + "nauc_recall_at_10_diff1": 0.116129, + "nauc_recall_at_20_max": -0.005985, + "nauc_recall_at_20_std": 0.128423, + "nauc_recall_at_20_diff1": 0.079917, + "nauc_recall_at_100_max": 0.019033, + "nauc_recall_at_100_std": 0.077965, + "nauc_recall_at_100_diff1": 0.125267, + "nauc_recall_at_1000_max": 0.088588, + "nauc_recall_at_1000_std": 0.382193, + "nauc_recall_at_1000_diff1": 0.071803, + "nauc_precision_at_1_max": 0.153618, + "nauc_precision_at_1_std": 0.227129, + "nauc_precision_at_1_diff1": 0.364661, + "nauc_precision_at_3_max": 0.073482, + "nauc_precision_at_3_std": 0.108345, + "nauc_precision_at_3_diff1": 0.19545, + "nauc_precision_at_5_max": 0.111195, + "nauc_precision_at_5_std": 0.151992, + "nauc_precision_at_5_diff1": 0.162684, + "nauc_precision_at_10_max": 0.038191, + "nauc_precision_at_10_std": 0.147005, + "nauc_precision_at_10_diff1": 0.10654, + "nauc_precision_at_20_max": 0.081896, + "nauc_precision_at_20_std": 0.144795, + "nauc_precision_at_20_diff1": 0.13808, + "nauc_precision_at_100_max": 0.151404, + "nauc_precision_at_100_std": 0.096817, + "nauc_precision_at_100_diff1": 0.237828, + "nauc_precision_at_1000_max": 0.197913, + "nauc_precision_at_1000_std": 0.208814, + "nauc_precision_at_1000_diff1": 0.2466, + "nauc_mrr_at_1_max": 0.153618, + "nauc_mrr_at_1_std": 0.227129, + "nauc_mrr_at_1_diff1": 0.364661, + "nauc_mrr_at_3_max": 0.116937, + "nauc_mrr_at_3_std": 0.162906, + "nauc_mrr_at_3_diff1": 0.287332, + "nauc_mrr_at_5_max": 0.127177, + "nauc_mrr_at_5_std": 0.172523, + "nauc_mrr_at_5_diff1": 0.273216, + "nauc_mrr_at_10_max": 0.11597, + "nauc_mrr_at_10_std": 0.179885, + "nauc_mrr_at_10_diff1": 0.263951, + "nauc_mrr_at_20_max": 0.114412, + "nauc_mrr_at_20_std": 0.17762, + "nauc_mrr_at_20_diff1": 0.262037, + "nauc_mrr_at_100_max": 0.11727, + "nauc_mrr_at_100_std": 0.175803, + "nauc_mrr_at_100_diff1": 0.264886, + "nauc_mrr_at_1000_max": 0.117204, + "nauc_mrr_at_1000_std": 0.177254, + "nauc_mrr_at_1000_diff1": 0.264394, + "main_score": 0.12473, + "hf_subset": "PMC-Treatment", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.09649, + "ndcg_at_3": 0.07868, + "ndcg_at_5": 0.09154, + "ndcg_at_10": 0.11324, + "ndcg_at_20": 0.13322, + "ndcg_at_100": 0.17748, + "ndcg_at_1000": 0.22101, + "map_at_1": 0.04459, + "map_at_3": 0.05677, + "map_at_5": 0.06489, + "map_at_10": 0.07271, + "map_at_20": 0.07895, + "map_at_100": 0.08539, + "map_at_1000": 0.08724, + "recall_at_1": 0.04459, + "recall_at_3": 0.07529, + "recall_at_5": 0.10746, + "recall_at_10": 0.1652, + "recall_at_20": 0.23026, + "recall_at_100": 0.4269, + "recall_at_1000": 0.71053, + "precision_at_1": 0.09649, + "precision_at_3": 0.05556, + "precision_at_5": 0.04386, + "precision_at_10": 0.03333, + "precision_at_20": 0.02325, + "precision_at_100": 0.00921, + "precision_at_1000": 0.00155, + "mrr_at_1": 0.096491, + "mrr_at_3": 0.124269, + "mrr_at_5": 0.134357, + "mrr_at_10": 0.146021, + "mrr_at_20": 0.151225, + "mrr_at_100": 0.156032, + "mrr_at_1000": 0.157053, + "nauc_ndcg_at_1_max": 0.133506, + "nauc_ndcg_at_1_std": -0.374533, + "nauc_ndcg_at_1_diff1": 0.536549, + "nauc_ndcg_at_3_max": 0.081161, + "nauc_ndcg_at_3_std": -0.228339, + "nauc_ndcg_at_3_diff1": 0.366566, + "nauc_ndcg_at_5_max": 0.033885, + "nauc_ndcg_at_5_std": -0.23344, + "nauc_ndcg_at_5_diff1": 0.326805, + "nauc_ndcg_at_10_max": 0.085069, + "nauc_ndcg_at_10_std": -0.212503, + "nauc_ndcg_at_10_diff1": 0.301821, + "nauc_ndcg_at_20_max": 0.066721, + "nauc_ndcg_at_20_std": -0.183033, + "nauc_ndcg_at_20_diff1": 0.255598, + "nauc_ndcg_at_100_max": 0.083202, + "nauc_ndcg_at_100_std": -0.191208, + "nauc_ndcg_at_100_diff1": 0.295003, + "nauc_ndcg_at_1000_max": 0.114372, + "nauc_ndcg_at_1000_std": -0.150048, + "nauc_ndcg_at_1000_diff1": 0.323015, + "nauc_map_at_1_max": 0.060916, + "nauc_map_at_1_std": -0.338751, + "nauc_map_at_1_diff1": 0.374876, + "nauc_map_at_3_max": 0.05305, + "nauc_map_at_3_std": -0.239079, + "nauc_map_at_3_diff1": 0.326885, + "nauc_map_at_5_max": 0.020904, + "nauc_map_at_5_std": -0.234162, + "nauc_map_at_5_diff1": 0.313691, + "nauc_map_at_10_max": 0.048381, + "nauc_map_at_10_std": -0.228203, + "nauc_map_at_10_diff1": 0.29895, + "nauc_map_at_20_max": 0.03924, + "nauc_map_at_20_std": -0.216775, + "nauc_map_at_20_diff1": 0.274676, + "nauc_map_at_100_max": 0.051673, + "nauc_map_at_100_std": -0.213518, + "nauc_map_at_100_diff1": 0.291644, + "nauc_map_at_1000_max": 0.052282, + "nauc_map_at_1000_std": -0.211157, + "nauc_map_at_1000_diff1": 0.294311, + "nauc_recall_at_1_max": 0.060916, + "nauc_recall_at_1_std": -0.338751, + "nauc_recall_at_1_diff1": 0.374876, + "nauc_recall_at_3_max": 0.05097, + "nauc_recall_at_3_std": -0.161926, + "nauc_recall_at_3_diff1": 0.245483, + "nauc_recall_at_5_max": -0.026064, + "nauc_recall_at_5_std": -0.190606, + "nauc_recall_at_5_diff1": 0.212956, + "nauc_recall_at_10_max": 0.085308, + "nauc_recall_at_10_std": -0.151878, + "nauc_recall_at_10_diff1": 0.14718, + "nauc_recall_at_20_max": 0.057092, + "nauc_recall_at_20_std": -0.082706, + "nauc_recall_at_20_diff1": 0.065297, + "nauc_recall_at_100_max": 0.061532, + "nauc_recall_at_100_std": -0.123024, + "nauc_recall_at_100_diff1": 0.149761, + "nauc_recall_at_1000_max": 0.209026, + "nauc_recall_at_1000_std": 0.116567, + "nauc_recall_at_1000_diff1": 0.195553, + "nauc_precision_at_1_max": 0.133506, + "nauc_precision_at_1_std": -0.374533, + "nauc_precision_at_1_diff1": 0.536549, + "nauc_precision_at_3_max": 0.119355, + "nauc_precision_at_3_std": -0.175161, + "nauc_precision_at_3_diff1": 0.370192, + "nauc_precision_at_5_max": 0.046252, + "nauc_precision_at_5_std": -0.189427, + "nauc_precision_at_5_diff1": 0.347385, + "nauc_precision_at_10_max": 0.123387, + "nauc_precision_at_10_std": -0.13771, + "nauc_precision_at_10_diff1": 0.345175, + "nauc_precision_at_20_max": 0.037229, + "nauc_precision_at_20_std": -0.098555, + "nauc_precision_at_20_diff1": 0.228334, + "nauc_precision_at_100_max": 0.09345, + "nauc_precision_at_100_std": -0.131913, + "nauc_precision_at_100_diff1": 0.314815, + "nauc_precision_at_1000_max": 0.16284, + "nauc_precision_at_1000_std": 0.003447, + "nauc_precision_at_1000_diff1": 0.305495, + "nauc_mrr_at_1_max": 0.133506, + "nauc_mrr_at_1_std": -0.374533, + "nauc_mrr_at_1_diff1": 0.536549, + "nauc_mrr_at_3_max": 0.120352, + "nauc_mrr_at_3_std": -0.262475, + "nauc_mrr_at_3_diff1": 0.46297, + "nauc_mrr_at_5_max": 0.101528, + "nauc_mrr_at_5_std": -0.276795, + "nauc_mrr_at_5_diff1": 0.444648, + "nauc_mrr_at_10_max": 0.120892, + "nauc_mrr_at_10_std": -0.262377, + "nauc_mrr_at_10_diff1": 0.439341, + "nauc_mrr_at_20_max": 0.11965, + "nauc_mrr_at_20_std": -0.25838, + "nauc_mrr_at_20_diff1": 0.436242, + "nauc_mrr_at_100_max": 0.118932, + "nauc_mrr_at_100_std": -0.260156, + "nauc_mrr_at_100_diff1": 0.436947, + "nauc_mrr_at_1000_max": 0.119678, + "nauc_mrr_at_1000_std": -0.259487, + "nauc_mrr_at_1000_diff1": 0.438407, + "main_score": 0.11324, + "hf_subset": "PMC-Clinical", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.10853, + "ndcg_at_3": 0.12094, + "ndcg_at_5": 0.12969, + "ndcg_at_10": 0.16225, + "ndcg_at_20": 0.19817, + "ndcg_at_100": 0.28062, + "ndcg_at_1000": 0.3405, + "map_at_1": 0.03734, + "map_at_3": 0.0686, + "map_at_5": 0.0798, + "map_at_10": 0.09333, + "map_at_20": 0.10576, + "map_at_100": 0.12256, + "map_at_1000": 0.12678, + "recall_at_1": 0.03734, + "recall_at_3": 0.10762, + "recall_at_5": 0.14444, + "recall_at_10": 0.21473, + "recall_at_20": 0.31266, + "recall_at_100": 0.6177, + "recall_at_1000": 0.93566, + "precision_at_1": 0.10853, + "precision_at_3": 0.10594, + "precision_at_5": 0.09147, + "precision_at_10": 0.07364, + "precision_at_20": 0.05388, + "precision_at_100": 0.02186, + "precision_at_1000": 0.00336, + "mrr_at_1": 0.108527, + "mrr_at_3": 0.187339, + "mrr_at_5": 0.206331, + "mrr_at_10": 0.226123, + "mrr_at_20": 0.233218, + "mrr_at_100": 0.239318, + "mrr_at_1000": 0.239973, + "nauc_ndcg_at_1_max": 0.227687, + "nauc_ndcg_at_1_std": 0.106528, + "nauc_ndcg_at_1_diff1": 0.295889, + "nauc_ndcg_at_3_max": 0.099658, + "nauc_ndcg_at_3_std": 0.099094, + "nauc_ndcg_at_3_diff1": 0.160169, + "nauc_ndcg_at_5_max": 0.079434, + "nauc_ndcg_at_5_std": 0.067964, + "nauc_ndcg_at_5_diff1": 0.182202, + "nauc_ndcg_at_10_max": 0.096765, + "nauc_ndcg_at_10_std": 0.122262, + "nauc_ndcg_at_10_diff1": 0.14054, + "nauc_ndcg_at_20_max": 0.088589, + "nauc_ndcg_at_20_std": 0.141379, + "nauc_ndcg_at_20_diff1": 0.141244, + "nauc_ndcg_at_100_max": 0.130579, + "nauc_ndcg_at_100_std": 0.231222, + "nauc_ndcg_at_100_diff1": 0.154779, + "nauc_ndcg_at_1000_max": 0.157421, + "nauc_ndcg_at_1000_std": 0.224598, + "nauc_ndcg_at_1000_diff1": 0.123575, + "nauc_map_at_1_max": 0.167743, + "nauc_map_at_1_std": 0.06568, + "nauc_map_at_1_diff1": 0.396183, + "nauc_map_at_3_max": 0.113558, + "nauc_map_at_3_std": 0.0473, + "nauc_map_at_3_diff1": 0.267823, + "nauc_map_at_5_max": 0.093254, + "nauc_map_at_5_std": 0.036457, + "nauc_map_at_5_diff1": 0.255813, + "nauc_map_at_10_max": 0.104542, + "nauc_map_at_10_std": 0.075967, + "nauc_map_at_10_diff1": 0.213249, + "nauc_map_at_20_max": 0.093615, + "nauc_map_at_20_std": 0.103536, + "nauc_map_at_20_diff1": 0.208048, + "nauc_map_at_100_max": 0.098041, + "nauc_map_at_100_std": 0.137964, + "nauc_map_at_100_diff1": 0.204961, + "nauc_map_at_1000_max": 0.104441, + "nauc_map_at_1000_std": 0.136553, + "nauc_map_at_1000_diff1": 0.204047, + "nauc_recall_at_1_max": 0.167743, + "nauc_recall_at_1_std": 0.06568, + "nauc_recall_at_1_diff1": 0.396183, + "nauc_recall_at_3_max": 0.052799, + "nauc_recall_at_3_std": 0.046521, + "nauc_recall_at_3_diff1": 0.15384, + "nauc_recall_at_5_max": 0.002271, + "nauc_recall_at_5_std": 0.020812, + "nauc_recall_at_5_diff1": 0.151312, + "nauc_recall_at_10_max": 0.033232, + "nauc_recall_at_10_std": 0.112371, + "nauc_recall_at_10_diff1": 0.071086, + "nauc_recall_at_20_max": 0.008006, + "nauc_recall_at_20_std": 0.110476, + "nauc_recall_at_20_diff1": 0.052251, + "nauc_recall_at_100_max": 0.108937, + "nauc_recall_at_100_std": 0.289033, + "nauc_recall_at_100_diff1": 0.118019, + "nauc_recall_at_1000_max": 0.345127, + "nauc_recall_at_1000_std": 0.590988, + "nauc_recall_at_1000_diff1": -0.239375, + "nauc_precision_at_1_max": 0.227687, + "nauc_precision_at_1_std": 0.106528, + "nauc_precision_at_1_diff1": 0.295889, + "nauc_precision_at_3_max": 0.09311, + "nauc_precision_at_3_std": 0.153949, + "nauc_precision_at_3_diff1": 0.040506, + "nauc_precision_at_5_max": 0.015551, + "nauc_precision_at_5_std": 0.108205, + "nauc_precision_at_5_diff1": 0.013768, + "nauc_precision_at_10_max": 0.0336, + "nauc_precision_at_10_std": 0.212035, + "nauc_precision_at_10_diff1": -0.054651, + "nauc_precision_at_20_max": 0.036676, + "nauc_precision_at_20_std": 0.257435, + "nauc_precision_at_20_diff1": -0.008095, + "nauc_precision_at_100_max": 0.065135, + "nauc_precision_at_100_std": 0.384816, + "nauc_precision_at_100_diff1": -0.032773, + "nauc_precision_at_1000_max": 0.058734, + "nauc_precision_at_1000_std": 0.240088, + "nauc_precision_at_1000_diff1": -0.161494, + "nauc_mrr_at_1_max": 0.227687, + "nauc_mrr_at_1_std": 0.106528, + "nauc_mrr_at_1_diff1": 0.295889, + "nauc_mrr_at_3_max": 0.171556, + "nauc_mrr_at_3_std": 0.140424, + "nauc_mrr_at_3_diff1": 0.154062, + "nauc_mrr_at_5_max": 0.144887, + "nauc_mrr_at_5_std": 0.134866, + "nauc_mrr_at_5_diff1": 0.148326, + "nauc_mrr_at_10_max": 0.160608, + "nauc_mrr_at_10_std": 0.140417, + "nauc_mrr_at_10_diff1": 0.152796, + "nauc_mrr_at_20_max": 0.167315, + "nauc_mrr_at_20_std": 0.133783, + "nauc_mrr_at_20_diff1": 0.155373, + "nauc_mrr_at_100_max": 0.175894, + "nauc_mrr_at_100_std": 0.13609, + "nauc_mrr_at_100_diff1": 0.158541, + "nauc_mrr_at_1000_max": 0.175272, + "nauc_mrr_at_1000_std": 0.136139, + "nauc_mrr_at_1000_diff1": 0.158081, + "main_score": 0.16225, + "hf_subset": "IIYi-Clinical", + "languages": [ + "eng-Latn" + ] + } + ] + }, + "evaluation_time": 18799.076119422913, + "kg_co2_emissions": null +} \ No newline at end of file diff --git a/results/yibinlei__LENS-d8000/external/R2MEDRetrieval.json b/results/yibinlei__LENS-d8000/external/R2MEDRetrieval.json new file mode 100644 index 0000000000..947d2b0543 --- /dev/null +++ b/results/yibinlei__LENS-d8000/external/R2MEDRetrieval.json @@ -0,0 +1,1187 @@ +{ + "dataset_revision": "1.0", + "task_name": "R2MEDRetrieval", + "mteb_version": "1.38.20", + "scores": { + "test": [ + { + "ndcg_at_1": 0.08738, + "ndcg_at_3": 0.0626, + "ndcg_at_5": 0.06618, + "ndcg_at_10": 0.07822, + "ndcg_at_20": 0.09337, + "ndcg_at_100": 0.13685, + "ndcg_at_1000": 0.20008, + "map_at_1": 0.01873, + "map_at_3": 0.0303, + "map_at_5": 0.03688, + "map_at_10": 0.04544, + "map_at_20": 0.04974, + "map_at_100": 0.05763, + "map_at_1000": 0.06052, + "recall_at_1": 0.01873, + "recall_at_3": 0.04114, + "recall_at_5": 0.05657, + "recall_at_10": 0.09385, + "recall_at_20": 0.13578, + "recall_at_100": 0.29738, + "recall_at_1000": 0.66738, + "precision_at_1": 0.08738, + "precision_at_3": 0.05502, + "precision_at_5": 0.05049, + "precision_at_10": 0.04175, + "precision_at_20": 0.02816, + "precision_at_100": 0.01194, + "precision_at_1000": 0.00243, + "mrr_at_1": 0.087379, + "mrr_at_3": 0.10356, + "mrr_at_5": 0.111812, + "mrr_at_10": 0.121182, + "mrr_at_20": 0.127763, + "mrr_at_100": 0.132042, + "mrr_at_1000": 0.133499, + "nauc_ndcg_at_1_max": -0.028906, + "nauc_ndcg_at_1_std": -0.109087, + "nauc_ndcg_at_1_diff1": 0.510312, + "nauc_ndcg_at_3_max": -0.004987, + "nauc_ndcg_at_3_std": -0.138694, + "nauc_ndcg_at_3_diff1": 0.32002, + "nauc_ndcg_at_5_max": -0.064694, + "nauc_ndcg_at_5_std": -0.175125, + "nauc_ndcg_at_5_diff1": 0.258182, + "nauc_ndcg_at_10_max": -0.035342, + "nauc_ndcg_at_10_std": -0.132674, + "nauc_ndcg_at_10_diff1": 0.216678, + "nauc_ndcg_at_20_max": -0.001145, + "nauc_ndcg_at_20_std": -0.137955, + "nauc_ndcg_at_20_diff1": 0.226189, + "nauc_ndcg_at_100_max": 0.041547, + "nauc_ndcg_at_100_std": -0.128741, + "nauc_ndcg_at_100_diff1": 0.170752, + "nauc_ndcg_at_1000_max": 0.096242, + "nauc_ndcg_at_1000_std": -0.031548, + "nauc_ndcg_at_1000_diff1": 0.167223, + "nauc_map_at_1_max": -0.065381, + "nauc_map_at_1_std": -0.032058, + "nauc_map_at_1_diff1": 0.444611, + "nauc_map_at_3_max": -0.105619, + "nauc_map_at_3_std": -0.110616, + "nauc_map_at_3_diff1": 0.218557, + "nauc_map_at_5_max": -0.125488, + "nauc_map_at_5_std": -0.151111, + "nauc_map_at_5_diff1": 0.204688, + "nauc_map_at_10_max": -0.082057, + "nauc_map_at_10_std": -0.165276, + "nauc_map_at_10_diff1": 0.220012, + "nauc_map_at_20_max": -0.06121, + "nauc_map_at_20_std": -0.166259, + "nauc_map_at_20_diff1": 0.23172, + "nauc_map_at_100_max": -0.039066, + "nauc_map_at_100_std": -0.165631, + "nauc_map_at_100_diff1": 0.21399, + "nauc_map_at_1000_max": -0.030665, + "nauc_map_at_1000_std": -0.153268, + "nauc_map_at_1000_diff1": 0.213119, + "nauc_recall_at_1_max": -0.065381, + "nauc_recall_at_1_std": -0.032058, + "nauc_recall_at_1_diff1": 0.444611, + "nauc_recall_at_3_max": -0.109224, + "nauc_recall_at_3_std": -0.134982, + "nauc_recall_at_3_diff1": 0.094577, + "nauc_recall_at_5_max": -0.150579, + "nauc_recall_at_5_std": -0.1843, + "nauc_recall_at_5_diff1": 0.091356, + "nauc_recall_at_10_max": -0.018529, + "nauc_recall_at_10_std": -0.125291, + "nauc_recall_at_10_diff1": 0.116238, + "nauc_recall_at_20_max": 0.049033, + "nauc_recall_at_20_std": -0.12739, + "nauc_recall_at_20_diff1": 0.150266, + "nauc_recall_at_100_max": 0.120378, + "nauc_recall_at_100_std": -0.082621, + "nauc_recall_at_100_diff1": 0.064374, + "nauc_recall_at_1000_max": 0.321899, + "nauc_recall_at_1000_std": 0.241571, + "nauc_recall_at_1000_diff1": 0.0691, + "nauc_precision_at_1_max": -0.028906, + "nauc_precision_at_1_std": -0.109087, + "nauc_precision_at_1_diff1": 0.510312, + "nauc_precision_at_3_max": 0.026877, + "nauc_precision_at_3_std": -0.158556, + "nauc_precision_at_3_diff1": 0.272986, + "nauc_precision_at_5_max": -0.033321, + "nauc_precision_at_5_std": -0.203804, + "nauc_precision_at_5_diff1": 0.253213, + "nauc_precision_at_10_max": 0.026921, + "nauc_precision_at_10_std": -0.183806, + "nauc_precision_at_10_diff1": 0.234963, + "nauc_precision_at_20_max": 0.056032, + "nauc_precision_at_20_std": -0.174581, + "nauc_precision_at_20_diff1": 0.226131, + "nauc_precision_at_100_max": 0.09608, + "nauc_precision_at_100_std": -0.161459, + "nauc_precision_at_100_diff1": 0.142033, + "nauc_precision_at_1000_max": 0.109423, + "nauc_precision_at_1000_std": -0.013175, + "nauc_precision_at_1000_diff1": 0.061966, + "nauc_mrr_at_1_max": -0.028906, + "nauc_mrr_at_1_std": -0.109087, + "nauc_mrr_at_1_diff1": 0.510312, + "nauc_mrr_at_3_max": 0.019585, + "nauc_mrr_at_3_std": -0.072829, + "nauc_mrr_at_3_diff1": 0.399302, + "nauc_mrr_at_5_max": -0.003827, + "nauc_mrr_at_5_std": -0.091713, + "nauc_mrr_at_5_diff1": 0.35771, + "nauc_mrr_at_10_max": -0.002084, + "nauc_mrr_at_10_std": -0.084527, + "nauc_mrr_at_10_diff1": 0.333103, + "nauc_mrr_at_20_max": 0.009212, + "nauc_mrr_at_20_std": -0.088898, + "nauc_mrr_at_20_diff1": 0.326007, + "nauc_mrr_at_100_max": 0.008395, + "nauc_mrr_at_100_std": -0.089418, + "nauc_mrr_at_100_diff1": 0.318396, + "nauc_mrr_at_1000_max": 0.009912, + "nauc_mrr_at_1000_std": -0.086125, + "nauc_mrr_at_1000_diff1": 0.319377, + "main_score": 0.07822, + "hf_subset": "Biology", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.23377, + "ndcg_at_3": 0.23708, + "ndcg_at_5": 0.25206, + "ndcg_at_10": 0.29558, + "ndcg_at_20": 0.33444, + "ndcg_at_100": 0.39248, + "ndcg_at_1000": 0.43202, + "map_at_1": 0.11322, + "map_at_3": 0.16194, + "map_at_5": 0.19028, + "map_at_10": 0.21549, + "map_at_20": 0.22864, + "map_at_100": 0.24225, + "map_at_1000": 0.24514, + "recall_at_1": 0.11322, + "recall_at_3": 0.20015, + "recall_at_5": 0.27398, + "recall_at_10": 0.39997, + "recall_at_20": 0.513, + "recall_at_100": 0.74006, + "recall_at_1000": 0.96274, + "precision_at_1": 0.23377, + "precision_at_3": 0.17749, + "precision_at_5": 0.14545, + "precision_at_10": 0.10519, + "precision_at_20": 0.07013, + "precision_at_100": 0.02143, + "precision_at_1000": 0.00287, + "mrr_at_1": 0.233766, + "mrr_at_3": 0.298701, + "mrr_at_5": 0.317532, + "mrr_at_10": 0.339059, + "mrr_at_20": 0.346353, + "mrr_at_100": 0.350084, + "mrr_at_1000": 0.350542, + "nauc_ndcg_at_1_max": -0.164581, + "nauc_ndcg_at_1_std": -0.011811, + "nauc_ndcg_at_1_diff1": -0.011984, + "nauc_ndcg_at_3_max": -0.155899, + "nauc_ndcg_at_3_std": -0.016481, + "nauc_ndcg_at_3_diff1": -0.086737, + "nauc_ndcg_at_5_max": -0.089827, + "nauc_ndcg_at_5_std": -0.040904, + "nauc_ndcg_at_5_diff1": 0.014833, + "nauc_ndcg_at_10_max": -0.091914, + "nauc_ndcg_at_10_std": -0.055757, + "nauc_ndcg_at_10_diff1": 0.0015, + "nauc_ndcg_at_20_max": -0.078313, + "nauc_ndcg_at_20_std": -0.036352, + "nauc_ndcg_at_20_diff1": 0.012461, + "nauc_ndcg_at_100_max": -0.066226, + "nauc_ndcg_at_100_std": 0.019505, + "nauc_ndcg_at_100_diff1": -0.047321, + "nauc_ndcg_at_1000_max": -0.07, + "nauc_ndcg_at_1000_std": 0.026028, + "nauc_ndcg_at_1000_diff1": -0.040146, + "nauc_map_at_1_max": -0.191782, + "nauc_map_at_1_std": 0.060461, + "nauc_map_at_1_diff1": 0.044494, + "nauc_map_at_3_max": -0.135385, + "nauc_map_at_3_std": 0.009367, + "nauc_map_at_3_diff1": -0.040607, + "nauc_map_at_5_max": -0.076652, + "nauc_map_at_5_std": -0.016913, + "nauc_map_at_5_diff1": 0.009582, + "nauc_map_at_10_max": -0.0835, + "nauc_map_at_10_std": -0.031694, + "nauc_map_at_10_diff1": -0.004517, + "nauc_map_at_20_max": -0.082861, + "nauc_map_at_20_std": -0.023434, + "nauc_map_at_20_diff1": -0.003072, + "nauc_map_at_100_max": -0.080878, + "nauc_map_at_100_std": -0.00997, + "nauc_map_at_100_diff1": -0.017182, + "nauc_map_at_1000_max": -0.079776, + "nauc_map_at_1000_std": -0.007911, + "nauc_map_at_1000_diff1": -0.01665, + "nauc_recall_at_1_max": -0.191782, + "nauc_recall_at_1_std": 0.060461, + "nauc_recall_at_1_diff1": 0.044494, + "nauc_recall_at_3_max": -0.139537, + "nauc_recall_at_3_std": -0.002273, + "nauc_recall_at_3_diff1": -0.092517, + "nauc_recall_at_5_max": -0.023413, + "nauc_recall_at_5_std": -0.067855, + "nauc_recall_at_5_diff1": 0.073789, + "nauc_recall_at_10_max": -0.064641, + "nauc_recall_at_10_std": -0.128272, + "nauc_recall_at_10_diff1": 0.05232, + "nauc_recall_at_20_max": -0.029525, + "nauc_recall_at_20_std": -0.103229, + "nauc_recall_at_20_diff1": 0.10193, + "nauc_recall_at_100_max": 0.00728, + "nauc_recall_at_100_std": 0.063452, + "nauc_recall_at_100_diff1": -0.12744, + "nauc_recall_at_1000_max": -0.476584, + "nauc_recall_at_1000_std": -0.117721, + "nauc_recall_at_1000_diff1": -0.552574, + "nauc_precision_at_1_max": -0.164581, + "nauc_precision_at_1_std": -0.011811, + "nauc_precision_at_1_diff1": -0.011984, + "nauc_precision_at_3_max": -0.099545, + "nauc_precision_at_3_std": -0.062363, + "nauc_precision_at_3_diff1": -0.159808, + "nauc_precision_at_5_max": 0.024703, + "nauc_precision_at_5_std": -0.072464, + "nauc_precision_at_5_diff1": -0.033734, + "nauc_precision_at_10_max": 0.015962, + "nauc_precision_at_10_std": -0.044004, + "nauc_precision_at_10_diff1": -0.067121, + "nauc_precision_at_20_max": 0.048117, + "nauc_precision_at_20_std": 0.047503, + "nauc_precision_at_20_diff1": -0.077363, + "nauc_precision_at_100_max": 0.070949, + "nauc_precision_at_100_std": 0.184604, + "nauc_precision_at_100_diff1": -0.175184, + "nauc_precision_at_1000_max": 0.12571, + "nauc_precision_at_1000_std": 0.239512, + "nauc_precision_at_1000_diff1": -0.121139, + "nauc_mrr_at_1_max": -0.164581, + "nauc_mrr_at_1_std": -0.011811, + "nauc_mrr_at_1_diff1": -0.011984, + "nauc_mrr_at_3_max": -0.162947, + "nauc_mrr_at_3_std": -0.000861, + "nauc_mrr_at_3_diff1": -0.070269, + "nauc_mrr_at_5_max": -0.138377, + "nauc_mrr_at_5_std": -0.008587, + "nauc_mrr_at_5_diff1": -0.026214, + "nauc_mrr_at_10_max": -0.143061, + "nauc_mrr_at_10_std": -0.004725, + "nauc_mrr_at_10_diff1": -0.03248, + "nauc_mrr_at_20_max": -0.136378, + "nauc_mrr_at_20_std": -0.007924, + "nauc_mrr_at_20_diff1": -0.027607, + "nauc_mrr_at_100_max": -0.135218, + "nauc_mrr_at_100_std": -0.005279, + "nauc_mrr_at_100_diff1": -0.031428, + "nauc_mrr_at_1000_max": -0.135996, + "nauc_mrr_at_1000_std": -0.005511, + "nauc_mrr_at_1000_diff1": -0.03122, + "main_score": 0.29558, + "hf_subset": "Bioinformatics", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.26136, + "ndcg_at_3": 0.26294, + "ndcg_at_5": 0.28641, + "ndcg_at_10": 0.31872, + "ndcg_at_20": 0.35669, + "ndcg_at_100": 0.42585, + "ndcg_at_1000": 0.44375, + "map_at_1": 0.1133, + "map_at_3": 0.18744, + "map_at_5": 0.21335, + "map_at_10": 0.2344, + "map_at_20": 0.25009, + "map_at_100": 0.26377, + "map_at_1000": 0.26489, + "recall_at_1": 0.1133, + "recall_at_3": 0.2679, + "recall_at_5": 0.34142, + "recall_at_10": 0.43064, + "recall_at_20": 0.53858, + "recall_at_100": 0.81594, + "recall_at_1000": 0.91503, + "precision_at_1": 0.26136, + "precision_at_3": 0.18182, + "precision_at_5": 0.14545, + "precision_at_10": 0.09773, + "precision_at_20": 0.06477, + "precision_at_100": 0.02159, + "precision_at_1000": 0.00253, + "mrr_at_1": 0.261364, + "mrr_at_3": 0.337121, + "mrr_at_5": 0.35928, + "mrr_at_10": 0.372028, + "mrr_at_20": 0.377461, + "mrr_at_100": 0.382693, + "mrr_at_1000": 0.382841, + "nauc_ndcg_at_1_max": 0.224994, + "nauc_ndcg_at_1_std": 0.198546, + "nauc_ndcg_at_1_diff1": 0.154549, + "nauc_ndcg_at_3_max": 0.333444, + "nauc_ndcg_at_3_std": 0.028641, + "nauc_ndcg_at_3_diff1": 0.294232, + "nauc_ndcg_at_5_max": 0.30574, + "nauc_ndcg_at_5_std": -0.032818, + "nauc_ndcg_at_5_diff1": 0.225636, + "nauc_ndcg_at_10_max": 0.332297, + "nauc_ndcg_at_10_std": -0.028049, + "nauc_ndcg_at_10_diff1": 0.209371, + "nauc_ndcg_at_20_max": 0.33321, + "nauc_ndcg_at_20_std": 0.021963, + "nauc_ndcg_at_20_diff1": 0.136458, + "nauc_ndcg_at_100_max": 0.333391, + "nauc_ndcg_at_100_std": 0.075326, + "nauc_ndcg_at_100_diff1": 0.190409, + "nauc_ndcg_at_1000_max": 0.338433, + "nauc_ndcg_at_1000_std": 0.087057, + "nauc_ndcg_at_1000_diff1": 0.188925, + "nauc_map_at_1_max": 0.282752, + "nauc_map_at_1_std": 0.046464, + "nauc_map_at_1_diff1": 0.392596, + "nauc_map_at_3_max": 0.349133, + "nauc_map_at_3_std": -0.018006, + "nauc_map_at_3_diff1": 0.367539, + "nauc_map_at_5_max": 0.315584, + "nauc_map_at_5_std": -0.05102, + "nauc_map_at_5_diff1": 0.301857, + "nauc_map_at_10_max": 0.331158, + "nauc_map_at_10_std": -0.040253, + "nauc_map_at_10_diff1": 0.280657, + "nauc_map_at_20_max": 0.331116, + "nauc_map_at_20_std": -0.013122, + "nauc_map_at_20_diff1": 0.249865, + "nauc_map_at_100_max": 0.332362, + "nauc_map_at_100_std": -0.004216, + "nauc_map_at_100_diff1": 0.259046, + "nauc_map_at_1000_max": 0.332333, + "nauc_map_at_1000_std": -0.003706, + "nauc_map_at_1000_diff1": 0.259651, + "nauc_recall_at_1_max": 0.282752, + "nauc_recall_at_1_std": 0.046464, + "nauc_recall_at_1_diff1": 0.392596, + "nauc_recall_at_3_max": 0.351287, + "nauc_recall_at_3_std": -0.081428, + "nauc_recall_at_3_diff1": 0.30481, + "nauc_recall_at_5_max": 0.275015, + "nauc_recall_at_5_std": -0.142866, + "nauc_recall_at_5_diff1": 0.172218, + "nauc_recall_at_10_max": 0.324205, + "nauc_recall_at_10_std": -0.141481, + "nauc_recall_at_10_diff1": 0.134872, + "nauc_recall_at_20_max": 0.324706, + "nauc_recall_at_20_std": -0.03775, + "nauc_recall_at_20_diff1": -0.040493, + "nauc_recall_at_100_max": 0.388339, + "nauc_recall_at_100_std": 0.15608, + "nauc_recall_at_100_diff1": 0.166591, + "nauc_recall_at_1000_max": 0.601535, + "nauc_recall_at_1000_std": 0.385227, + "nauc_recall_at_1000_diff1": 0.138563, + "nauc_precision_at_1_max": 0.224994, + "nauc_precision_at_1_std": 0.198546, + "nauc_precision_at_1_diff1": 0.154549, + "nauc_precision_at_3_max": 0.252589, + "nauc_precision_at_3_std": 0.10178, + "nauc_precision_at_3_diff1": 0.190104, + "nauc_precision_at_5_max": 0.230542, + "nauc_precision_at_5_std": 0.024537, + "nauc_precision_at_5_diff1": 0.028528, + "nauc_precision_at_10_max": 0.254495, + "nauc_precision_at_10_std": 0.016159, + "nauc_precision_at_10_diff1": -0.052783, + "nauc_precision_at_20_max": 0.20422, + "nauc_precision_at_20_std": 0.120991, + "nauc_precision_at_20_diff1": -0.213734, + "nauc_precision_at_100_max": 0.066566, + "nauc_precision_at_100_std": 0.247802, + "nauc_precision_at_100_diff1": -0.135204, + "nauc_precision_at_1000_max": 0.029748, + "nauc_precision_at_1000_std": 0.240755, + "nauc_precision_at_1000_diff1": -0.149592, + "nauc_mrr_at_1_max": 0.224994, + "nauc_mrr_at_1_std": 0.198546, + "nauc_mrr_at_1_diff1": 0.154549, + "nauc_mrr_at_3_max": 0.252607, + "nauc_mrr_at_3_std": 0.156881, + "nauc_mrr_at_3_diff1": 0.173429, + "nauc_mrr_at_5_max": 0.251625, + "nauc_mrr_at_5_std": 0.144951, + "nauc_mrr_at_5_diff1": 0.133178, + "nauc_mrr_at_10_max": 0.256384, + "nauc_mrr_at_10_std": 0.135747, + "nauc_mrr_at_10_diff1": 0.127845, + "nauc_mrr_at_20_max": 0.259676, + "nauc_mrr_at_20_std": 0.145182, + "nauc_mrr_at_20_diff1": 0.116812, + "nauc_mrr_at_100_max": 0.259219, + "nauc_mrr_at_100_std": 0.148593, + "nauc_mrr_at_100_diff1": 0.127028, + "nauc_mrr_at_1000_max": 0.259575, + "nauc_mrr_at_1000_std": 0.149208, + "nauc_mrr_at_1000_diff1": 0.127137, + "main_score": 0.31872, + "hf_subset": "Medical-Sciences", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.01031, + "ndcg_at_3": 0.02441, + "ndcg_at_5": 0.03246, + "ndcg_at_10": 0.03627, + "ndcg_at_20": 0.04463, + "ndcg_at_100": 0.07442, + "ndcg_at_1000": 0.12558, + "map_at_1": 0.00172, + "map_at_3": 0.01006, + "map_at_5": 0.01727, + "map_at_10": 0.01855, + "map_at_20": 0.02085, + "map_at_100": 0.02515, + "map_at_1000": 0.02695, + "recall_at_1": 0.00172, + "recall_at_3": 0.02106, + "recall_at_5": 0.0446, + "recall_at_10": 0.05663, + "recall_at_20": 0.08326, + "recall_at_100": 0.21175, + "recall_at_1000": 0.53483, + "precision_at_1": 0.01031, + "precision_at_3": 0.02749, + "precision_at_5": 0.02887, + "precision_at_10": 0.01753, + "precision_at_20": 0.01186, + "precision_at_100": 0.00557, + "precision_at_1000": 0.00142, + "mrr_at_1": 0.010309, + "mrr_at_3": 0.036082, + "mrr_at_5": 0.042784, + "mrr_at_10": 0.046105, + "mrr_at_20": 0.048693, + "mrr_at_100": 0.053162, + "mrr_at_1000": 0.054586, + "nauc_ndcg_at_1_max": 0.670612, + "nauc_ndcg_at_1_std": -0.320219, + "nauc_ndcg_at_1_diff1": 0.096724, + "nauc_ndcg_at_3_max": 0.024838, + "nauc_ndcg_at_3_std": 0.021736, + "nauc_ndcg_at_3_diff1": 0.100801, + "nauc_ndcg_at_5_max": 0.021427, + "nauc_ndcg_at_5_std": 0.099781, + "nauc_ndcg_at_5_diff1": 0.044264, + "nauc_ndcg_at_10_max": 0.072396, + "nauc_ndcg_at_10_std": 0.133667, + "nauc_ndcg_at_10_diff1": 0.028622, + "nauc_ndcg_at_20_max": 0.024179, + "nauc_ndcg_at_20_std": 0.066247, + "nauc_ndcg_at_20_diff1": -0.004927, + "nauc_ndcg_at_100_max": 0.128065, + "nauc_ndcg_at_100_std": 0.138287, + "nauc_ndcg_at_100_diff1": -0.028647, + "nauc_ndcg_at_1000_max": 0.173198, + "nauc_ndcg_at_1000_std": 0.180468, + "nauc_ndcg_at_1000_diff1": 0.011598, + "nauc_map_at_1_max": 0.670612, + "nauc_map_at_1_std": -0.320219, + "nauc_map_at_1_diff1": 0.096724, + "nauc_map_at_3_max": 0.015317, + "nauc_map_at_3_std": 0.086035, + "nauc_map_at_3_diff1": 0.119226, + "nauc_map_at_5_max": 0.001244, + "nauc_map_at_5_std": 0.105785, + "nauc_map_at_5_diff1": 0.042276, + "nauc_map_at_10_max": 0.034084, + "nauc_map_at_10_std": 0.121163, + "nauc_map_at_10_diff1": 0.028908, + "nauc_map_at_20_max": 0.014785, + "nauc_map_at_20_std": 0.085807, + "nauc_map_at_20_diff1": 0.021128, + "nauc_map_at_100_max": 0.058799, + "nauc_map_at_100_std": 0.120053, + "nauc_map_at_100_diff1": -0.002572, + "nauc_map_at_1000_max": 0.063497, + "nauc_map_at_1000_std": 0.122656, + "nauc_map_at_1000_diff1": -0.000841, + "nauc_recall_at_1_max": 0.670612, + "nauc_recall_at_1_std": -0.320219, + "nauc_recall_at_1_diff1": 0.096724, + "nauc_recall_at_3_max": -0.064313, + "nauc_recall_at_3_std": 0.168008, + "nauc_recall_at_3_diff1": 0.09384, + "nauc_recall_at_5_max": -0.039405, + "nauc_recall_at_5_std": 0.176043, + "nauc_recall_at_5_diff1": -0.005742, + "nauc_recall_at_10_max": 0.065443, + "nauc_recall_at_10_std": 0.205686, + "nauc_recall_at_10_diff1": -0.042373, + "nauc_recall_at_20_max": -0.023698, + "nauc_recall_at_20_std": 0.057669, + "nauc_recall_at_20_diff1": -0.096646, + "nauc_recall_at_100_max": 0.169877, + "nauc_recall_at_100_std": 0.169989, + "nauc_recall_at_100_diff1": -0.105927, + "nauc_recall_at_1000_max": 0.292025, + "nauc_recall_at_1000_std": 0.276491, + "nauc_recall_at_1000_diff1": -0.02094, + "nauc_precision_at_1_max": 0.670612, + "nauc_precision_at_1_std": -0.320219, + "nauc_precision_at_1_diff1": 0.096724, + "nauc_precision_at_3_max": -0.053273, + "nauc_precision_at_3_std": 0.029557, + "nauc_precision_at_3_diff1": 0.094707, + "nauc_precision_at_5_max": 0.044597, + "nauc_precision_at_5_std": 0.085779, + "nauc_precision_at_5_diff1": 0.075247, + "nauc_precision_at_10_max": 0.117167, + "nauc_precision_at_10_std": 0.102926, + "nauc_precision_at_10_diff1": 0.06872, + "nauc_precision_at_20_max": 0.053937, + "nauc_precision_at_20_std": 0.031133, + "nauc_precision_at_20_diff1": 0.029162, + "nauc_precision_at_100_max": 0.161211, + "nauc_precision_at_100_std": 0.135849, + "nauc_precision_at_100_diff1": 0.06119, + "nauc_precision_at_1000_max": 0.136849, + "nauc_precision_at_1000_std": 0.137734, + "nauc_precision_at_1000_diff1": 0.176218, + "nauc_mrr_at_1_max": 0.670612, + "nauc_mrr_at_1_std": -0.320219, + "nauc_mrr_at_1_diff1": 0.096724, + "nauc_mrr_at_3_max": 0.10257, + "nauc_mrr_at_3_std": -0.048314, + "nauc_mrr_at_3_diff1": 0.122516, + "nauc_mrr_at_5_max": 0.094139, + "nauc_mrr_at_5_std": 0.013008, + "nauc_mrr_at_5_diff1": 0.098572, + "nauc_mrr_at_10_max": 0.121517, + "nauc_mrr_at_10_std": 0.023496, + "nauc_mrr_at_10_diff1": 0.095948, + "nauc_mrr_at_20_max": 0.104448, + "nauc_mrr_at_20_std": 0.009803, + "nauc_mrr_at_20_diff1": 0.074924, + "nauc_mrr_at_100_max": 0.116719, + "nauc_mrr_at_100_std": 0.018634, + "nauc_mrr_at_100_diff1": 0.069024, + "nauc_mrr_at_1000_max": 0.117822, + "nauc_mrr_at_1000_std": 0.020033, + "nauc_mrr_at_1000_diff1": 0.068015, + "main_score": 0.03627, + "hf_subset": "MedXpertQA-Exam", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.00847, + "ndcg_at_3": 0.00658, + "ndcg_at_5": 0.0069, + "ndcg_at_10": 0.01527, + "ndcg_at_20": 0.02315, + "ndcg_at_100": 0.05865, + "ndcg_at_1000": 0.11847, + "map_at_1": 0.00169, + "map_at_3": 0.00311, + "map_at_5": 0.00364, + "map_at_10": 0.00615, + "map_at_20": 0.00846, + "map_at_100": 0.0132, + "map_at_1000": 0.01589, + "recall_at_1": 0.00169, + "recall_at_3": 0.00593, + "recall_at_5": 0.00805, + "recall_at_10": 0.02516, + "recall_at_20": 0.04537, + "recall_at_100": 0.17717, + "recall_at_1000": 0.49386, + "precision_at_1": 0.00847, + "precision_at_3": 0.00565, + "precision_at_5": 0.00508, + "precision_at_10": 0.00932, + "precision_at_20": 0.0089, + "precision_at_100": 0.00695, + "precision_at_1000": 0.00211, + "mrr_at_1": 0.008475, + "mrr_at_3": 0.011299, + "mrr_at_5": 0.013418, + "mrr_at_10": 0.020891, + "mrr_at_20": 0.023378, + "mrr_at_100": 0.02939, + "mrr_at_1000": 0.030879, + "nauc_ndcg_at_1_max": -0.579509, + "nauc_ndcg_at_1_std": -0.503613, + "nauc_ndcg_at_1_diff1": 0.329587, + "nauc_ndcg_at_3_max": -0.549519, + "nauc_ndcg_at_3_std": -0.332842, + "nauc_ndcg_at_3_diff1": 0.329587, + "nauc_ndcg_at_5_max": -0.55092, + "nauc_ndcg_at_5_std": -0.168694, + "nauc_ndcg_at_5_diff1": 0.141786, + "nauc_ndcg_at_10_max": -0.433911, + "nauc_ndcg_at_10_std": 0.018371, + "nauc_ndcg_at_10_diff1": -0.082701, + "nauc_ndcg_at_20_max": -0.394089, + "nauc_ndcg_at_20_std": 0.025652, + "nauc_ndcg_at_20_diff1": -0.098581, + "nauc_ndcg_at_100_max": -0.214615, + "nauc_ndcg_at_100_std": 0.006553, + "nauc_ndcg_at_100_diff1": -0.056999, + "nauc_ndcg_at_1000_max": -0.219389, + "nauc_ndcg_at_1000_std": 0.08107, + "nauc_ndcg_at_1000_diff1": -0.097475, + "nauc_map_at_1_max": -0.579509, + "nauc_map_at_1_std": -0.503613, + "nauc_map_at_1_diff1": 0.329587, + "nauc_map_at_3_max": -0.545011, + "nauc_map_at_3_std": -0.30717, + "nauc_map_at_3_diff1": 0.329587, + "nauc_map_at_5_max": -0.550035, + "nauc_map_at_5_std": -0.214438, + "nauc_map_at_5_diff1": 0.197195, + "nauc_map_at_10_max": -0.475952, + "nauc_map_at_10_std": -0.078402, + "nauc_map_at_10_diff1": 0.026632, + "nauc_map_at_20_max": -0.446017, + "nauc_map_at_20_std": -0.037748, + "nauc_map_at_20_diff1": -0.007899, + "nauc_map_at_100_max": -0.35998, + "nauc_map_at_100_std": -0.019962, + "nauc_map_at_100_diff1": -0.026831, + "nauc_map_at_1000_max": -0.348528, + "nauc_map_at_1000_std": 0.005266, + "nauc_map_at_1000_diff1": -0.038181, + "nauc_recall_at_1_max": -0.579509, + "nauc_recall_at_1_std": -0.503613, + "nauc_recall_at_1_diff1": 0.329587, + "nauc_recall_at_3_max": -0.525298, + "nauc_recall_at_3_std": -0.194916, + "nauc_recall_at_3_diff1": 0.329587, + "nauc_recall_at_5_max": -0.539564, + "nauc_recall_at_5_std": -0.056889, + "nauc_recall_at_5_diff1": 0.090352, + "nauc_recall_at_10_max": -0.402122, + "nauc_recall_at_10_std": 0.119549, + "nauc_recall_at_10_diff1": -0.176891, + "nauc_recall_at_20_max": -0.369915, + "nauc_recall_at_20_std": 0.089583, + "nauc_recall_at_20_diff1": -0.15366, + "nauc_recall_at_100_max": -0.093654, + "nauc_recall_at_100_std": 0.023584, + "nauc_recall_at_100_diff1": -0.033432, + "nauc_recall_at_1000_max": -0.125643, + "nauc_recall_at_1000_std": 0.14168, + "nauc_recall_at_1000_diff1": -0.126862, + "nauc_precision_at_1_max": -0.579509, + "nauc_precision_at_1_std": -0.503613, + "nauc_precision_at_1_diff1": 0.329587, + "nauc_precision_at_3_max": -0.541561, + "nauc_precision_at_3_std": -0.287525, + "nauc_precision_at_3_diff1": 0.329587, + "nauc_precision_at_5_max": -0.554211, + "nauc_precision_at_5_std": -0.081821, + "nauc_precision_at_5_diff1": 0.026555, + "nauc_precision_at_10_max": -0.391305, + "nauc_precision_at_10_std": 0.061553, + "nauc_precision_at_10_diff1": -0.149892, + "nauc_precision_at_20_max": -0.342924, + "nauc_precision_at_20_std": 0.061172, + "nauc_precision_at_20_diff1": -0.155369, + "nauc_precision_at_100_max": -0.173591, + "nauc_precision_at_100_std": 0.007633, + "nauc_precision_at_100_diff1": -0.073665, + "nauc_precision_at_1000_max": -0.137834, + "nauc_precision_at_1000_std": 0.049844, + "nauc_precision_at_1000_diff1": -0.050694, + "nauc_mrr_at_1_max": -0.579509, + "nauc_mrr_at_1_std": -0.503613, + "nauc_mrr_at_1_diff1": 0.329587, + "nauc_mrr_at_3_max": -0.560535, + "nauc_mrr_at_3_std": -0.395569, + "nauc_mrr_at_3_diff1": 0.329587, + "nauc_mrr_at_5_max": -0.563531, + "nauc_mrr_at_5_std": -0.281071, + "nauc_mrr_at_5_diff1": 0.186046, + "nauc_mrr_at_10_max": -0.467842, + "nauc_mrr_at_10_std": -0.091953, + "nauc_mrr_at_10_diff1": 0.006262, + "nauc_mrr_at_20_max": -0.437781, + "nauc_mrr_at_20_std": -0.106137, + "nauc_mrr_at_20_diff1": -0.016946, + "nauc_mrr_at_100_max": -0.38484, + "nauc_mrr_at_100_std": -0.107462, + "nauc_mrr_at_100_diff1": -0.015278, + "nauc_mrr_at_1000_max": -0.386709, + "nauc_mrr_at_1000_std": -0.099747, + "nauc_mrr_at_1000_diff1": -0.017878, + "main_score": 0.01527, + "hf_subset": "MedQA-Diag", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.09333, + "ndcg_at_3": 0.1016, + "ndcg_at_5": 0.11483, + "ndcg_at_10": 0.13459, + "ndcg_at_20": 0.15706, + "ndcg_at_100": 0.19279, + "ndcg_at_1000": 0.23622, + "map_at_1": 0.05633, + "map_at_3": 0.07902, + "map_at_5": 0.08751, + "map_at_10": 0.09537, + "map_at_20": 0.10241, + "map_at_100": 0.10715, + "map_at_1000": 0.10882, + "recall_at_1": 0.05633, + "recall_at_3": 0.10567, + "recall_at_5": 0.13778, + "recall_at_10": 0.19056, + "recall_at_20": 0.26544, + "recall_at_100": 0.42844, + "recall_at_1000": 0.72656, + "precision_at_1": 0.09333, + "precision_at_3": 0.06222, + "precision_at_5": 0.05067, + "precision_at_10": 0.03467, + "precision_at_20": 0.024, + "precision_at_100": 0.00833, + "precision_at_1000": 0.00147, + "mrr_at_1": 0.093333, + "mrr_at_3": 0.135556, + "mrr_at_5": 0.147556, + "mrr_at_10": 0.158275, + "mrr_at_20": 0.164847, + "mrr_at_100": 0.169446, + "mrr_at_1000": 0.170227, + "nauc_ndcg_at_1_max": 0.244394, + "nauc_ndcg_at_1_std": 0.02572, + "nauc_ndcg_at_1_diff1": 0.447813, + "nauc_ndcg_at_3_max": 0.189404, + "nauc_ndcg_at_3_std": 0.087126, + "nauc_ndcg_at_3_diff1": 0.323655, + "nauc_ndcg_at_5_max": 0.1656, + "nauc_ndcg_at_5_std": 0.083482, + "nauc_ndcg_at_5_diff1": 0.353843, + "nauc_ndcg_at_10_max": 0.111264, + "nauc_ndcg_at_10_std": 0.110187, + "nauc_ndcg_at_10_diff1": 0.264664, + "nauc_ndcg_at_20_max": 0.096333, + "nauc_ndcg_at_20_std": 0.086457, + "nauc_ndcg_at_20_diff1": 0.265222, + "nauc_ndcg_at_100_max": 0.133665, + "nauc_ndcg_at_100_std": 0.111239, + "nauc_ndcg_at_100_diff1": 0.251627, + "nauc_ndcg_at_1000_max": 0.144493, + "nauc_ndcg_at_1000_std": 0.146201, + "nauc_ndcg_at_1000_diff1": 0.244329, + "nauc_map_at_1_max": 0.260284, + "nauc_map_at_1_std": 0.059267, + "nauc_map_at_1_diff1": 0.496668, + "nauc_map_at_3_max": 0.203309, + "nauc_map_at_3_std": 0.083633, + "nauc_map_at_3_diff1": 0.37777, + "nauc_map_at_5_max": 0.185882, + "nauc_map_at_5_std": 0.080705, + "nauc_map_at_5_diff1": 0.384832, + "nauc_map_at_10_max": 0.159972, + "nauc_map_at_10_std": 0.095435, + "nauc_map_at_10_diff1": 0.336165, + "nauc_map_at_20_max": 0.15178, + "nauc_map_at_20_std": 0.087181, + "nauc_map_at_20_diff1": 0.335954, + "nauc_map_at_100_max": 0.159309, + "nauc_map_at_100_std": 0.093234, + "nauc_map_at_100_diff1": 0.333674, + "nauc_map_at_1000_max": 0.159669, + "nauc_map_at_1000_std": 0.096173, + "nauc_map_at_1000_diff1": 0.332806, + "nauc_recall_at_1_max": 0.260284, + "nauc_recall_at_1_std": 0.059267, + "nauc_recall_at_1_diff1": 0.496668, + "nauc_recall_at_3_max": 0.168274, + "nauc_recall_at_3_std": 0.102486, + "nauc_recall_at_3_diff1": 0.268727, + "nauc_recall_at_5_max": 0.131858, + "nauc_recall_at_5_std": 0.076871, + "nauc_recall_at_5_diff1": 0.31634, + "nauc_recall_at_10_max": 0.019302, + "nauc_recall_at_10_std": 0.122157, + "nauc_recall_at_10_diff1": 0.127537, + "nauc_recall_at_20_max": -0.002568, + "nauc_recall_at_20_std": 0.063237, + "nauc_recall_at_20_diff1": 0.128458, + "nauc_recall_at_100_max": 0.061968, + "nauc_recall_at_100_std": 0.113961, + "nauc_recall_at_100_diff1": 0.068782, + "nauc_recall_at_1000_max": 0.087887, + "nauc_recall_at_1000_std": 0.302797, + "nauc_recall_at_1000_diff1": -0.03695, + "nauc_precision_at_1_max": 0.244394, + "nauc_precision_at_1_std": 0.02572, + "nauc_precision_at_1_diff1": 0.447813, + "nauc_precision_at_3_max": 0.147074, + "nauc_precision_at_3_std": 0.123443, + "nauc_precision_at_3_diff1": 0.197395, + "nauc_precision_at_5_max": 0.099623, + "nauc_precision_at_5_std": 0.10584, + "nauc_precision_at_5_diff1": 0.250441, + "nauc_precision_at_10_max": -0.004472, + "nauc_precision_at_10_std": 0.148255, + "nauc_precision_at_10_diff1": 0.070561, + "nauc_precision_at_20_max": -0.025824, + "nauc_precision_at_20_std": 0.078243, + "nauc_precision_at_20_diff1": 0.097632, + "nauc_precision_at_100_max": 0.152614, + "nauc_precision_at_100_std": 0.13565, + "nauc_precision_at_100_diff1": 0.065929, + "nauc_precision_at_1000_max": 0.143749, + "nauc_precision_at_1000_std": 0.121549, + "nauc_precision_at_1000_diff1": -0.015013, + "nauc_mrr_at_1_max": 0.244394, + "nauc_mrr_at_1_std": 0.02572, + "nauc_mrr_at_1_diff1": 0.447813, + "nauc_mrr_at_3_max": 0.183086, + "nauc_mrr_at_3_std": 0.085381, + "nauc_mrr_at_3_diff1": 0.315467, + "nauc_mrr_at_5_max": 0.176026, + "nauc_mrr_at_5_std": 0.075509, + "nauc_mrr_at_5_diff1": 0.337882, + "nauc_mrr_at_10_max": 0.151152, + "nauc_mrr_at_10_std": 0.087324, + "nauc_mrr_at_10_diff1": 0.303768, + "nauc_mrr_at_20_max": 0.146856, + "nauc_mrr_at_20_std": 0.079014, + "nauc_mrr_at_20_diff1": 0.302874, + "nauc_mrr_at_100_max": 0.153339, + "nauc_mrr_at_100_std": 0.081556, + "nauc_mrr_at_100_diff1": 0.302803, + "nauc_mrr_at_1000_max": 0.152976, + "nauc_mrr_at_1000_std": 0.081943, + "nauc_mrr_at_1000_diff1": 0.302696, + "main_score": 0.13459, + "hf_subset": "PMC-Treatment", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.08772, + "ndcg_at_3": 0.07853, + "ndcg_at_5": 0.09052, + "ndcg_at_10": 0.10414, + "ndcg_at_20": 0.12171, + "ndcg_at_100": 0.16823, + "ndcg_at_1000": 0.21773, + "map_at_1": 0.03728, + "map_at_3": 0.05385, + "map_at_5": 0.06346, + "map_at_10": 0.07017, + "map_at_20": 0.07565, + "map_at_100": 0.08228, + "map_at_1000": 0.08416, + "recall_at_1": 0.03728, + "recall_at_3": 0.07675, + "recall_at_5": 0.10526, + "recall_at_10": 0.13962, + "recall_at_20": 0.19591, + "recall_at_100": 0.40351, + "recall_at_1000": 0.73173, + "precision_at_1": 0.08772, + "precision_at_3": 0.0614, + "precision_at_5": 0.04912, + "precision_at_10": 0.03158, + "precision_at_20": 0.02149, + "precision_at_100": 0.00877, + "precision_at_1000": 0.00159, + "mrr_at_1": 0.087719, + "mrr_at_3": 0.122807, + "mrr_at_5": 0.13114, + "mrr_at_10": 0.136901, + "mrr_at_20": 0.141711, + "mrr_at_100": 0.148203, + "mrr_at_1000": 0.149484, + "nauc_ndcg_at_1_max": 0.419287, + "nauc_ndcg_at_1_std": -0.32647, + "nauc_ndcg_at_1_diff1": 0.599334, + "nauc_ndcg_at_3_max": 0.232227, + "nauc_ndcg_at_3_std": -0.243894, + "nauc_ndcg_at_3_diff1": 0.494751, + "nauc_ndcg_at_5_max": 0.22067, + "nauc_ndcg_at_5_std": -0.18068, + "nauc_ndcg_at_5_diff1": 0.407154, + "nauc_ndcg_at_10_max": 0.158566, + "nauc_ndcg_at_10_std": -0.19672, + "nauc_ndcg_at_10_diff1": 0.390254, + "nauc_ndcg_at_20_max": 0.163249, + "nauc_ndcg_at_20_std": -0.182107, + "nauc_ndcg_at_20_diff1": 0.356995, + "nauc_ndcg_at_100_max": 0.180118, + "nauc_ndcg_at_100_std": -0.162876, + "nauc_ndcg_at_100_diff1": 0.305533, + "nauc_ndcg_at_1000_max": 0.212272, + "nauc_ndcg_at_1000_std": -0.126078, + "nauc_ndcg_at_1000_diff1": 0.31912, + "nauc_map_at_1_max": 0.455113, + "nauc_map_at_1_std": -0.252201, + "nauc_map_at_1_diff1": 0.650527, + "nauc_map_at_3_max": 0.289557, + "nauc_map_at_3_std": -0.228031, + "nauc_map_at_3_diff1": 0.538091, + "nauc_map_at_5_max": 0.268698, + "nauc_map_at_5_std": -0.209255, + "nauc_map_at_5_diff1": 0.468999, + "nauc_map_at_10_max": 0.225681, + "nauc_map_at_10_std": -0.219722, + "nauc_map_at_10_diff1": 0.460346, + "nauc_map_at_20_max": 0.224895, + "nauc_map_at_20_std": -0.215452, + "nauc_map_at_20_diff1": 0.443783, + "nauc_map_at_100_max": 0.228036, + "nauc_map_at_100_std": -0.203815, + "nauc_map_at_100_diff1": 0.428569, + "nauc_map_at_1000_max": 0.228652, + "nauc_map_at_1000_std": -0.202526, + "nauc_map_at_1000_diff1": 0.429305, + "nauc_recall_at_1_max": 0.455113, + "nauc_recall_at_1_std": -0.252201, + "nauc_recall_at_1_diff1": 0.650527, + "nauc_recall_at_3_max": 0.138419, + "nauc_recall_at_3_std": -0.21071, + "nauc_recall_at_3_diff1": 0.398982, + "nauc_recall_at_5_max": 0.120583, + "nauc_recall_at_5_std": -0.135852, + "nauc_recall_at_5_diff1": 0.255623, + "nauc_recall_at_10_max": 0.006253, + "nauc_recall_at_10_std": -0.169975, + "nauc_recall_at_10_diff1": 0.232628, + "nauc_recall_at_20_max": 0.04123, + "nauc_recall_at_20_std": -0.132914, + "nauc_recall_at_20_diff1": 0.165324, + "nauc_recall_at_100_max": 0.114294, + "nauc_recall_at_100_std": -0.096367, + "nauc_recall_at_100_diff1": 0.060951, + "nauc_recall_at_1000_max": 0.224338, + "nauc_recall_at_1000_std": 0.176194, + "nauc_recall_at_1000_diff1": 0.00211, + "nauc_precision_at_1_max": 0.419287, + "nauc_precision_at_1_std": -0.32647, + "nauc_precision_at_1_diff1": 0.599334, + "nauc_precision_at_3_max": 0.118331, + "nauc_precision_at_3_std": -0.245634, + "nauc_precision_at_3_diff1": 0.440571, + "nauc_precision_at_5_max": 0.159207, + "nauc_precision_at_5_std": -0.135794, + "nauc_precision_at_5_diff1": 0.358131, + "nauc_precision_at_10_max": 0.061913, + "nauc_precision_at_10_std": -0.179003, + "nauc_precision_at_10_diff1": 0.348857, + "nauc_precision_at_20_max": 0.077574, + "nauc_precision_at_20_std": -0.128627, + "nauc_precision_at_20_diff1": 0.277529, + "nauc_precision_at_100_max": 0.084483, + "nauc_precision_at_100_std": -0.089875, + "nauc_precision_at_100_diff1": 0.190482, + "nauc_precision_at_1000_max": 0.118087, + "nauc_precision_at_1000_std": 0.015986, + "nauc_precision_at_1000_diff1": 0.120997, + "nauc_mrr_at_1_max": 0.419287, + "nauc_mrr_at_1_std": -0.32647, + "nauc_mrr_at_1_diff1": 0.599334, + "nauc_mrr_at_3_max": 0.252199, + "nauc_mrr_at_3_std": -0.255686, + "nauc_mrr_at_3_diff1": 0.494797, + "nauc_mrr_at_5_max": 0.254891, + "nauc_mrr_at_5_std": -0.203262, + "nauc_mrr_at_5_diff1": 0.454149, + "nauc_mrr_at_10_max": 0.237241, + "nauc_mrr_at_10_std": -0.205817, + "nauc_mrr_at_10_diff1": 0.444151, + "nauc_mrr_at_20_max": 0.236202, + "nauc_mrr_at_20_std": -0.201453, + "nauc_mrr_at_20_diff1": 0.4367, + "nauc_mrr_at_100_max": 0.237305, + "nauc_mrr_at_100_std": -0.203084, + "nauc_mrr_at_100_diff1": 0.428566, + "nauc_mrr_at_1000_max": 0.238715, + "nauc_mrr_at_1000_std": -0.202243, + "nauc_mrr_at_1000_diff1": 0.429092, + "main_score": 0.10414, + "hf_subset": "PMC-Clinical", + "languages": [ + "eng-Latn" + ] + }, + { + "ndcg_at_1": 0.16279, + "ndcg_at_3": 0.13329, + "ndcg_at_5": 0.13815, + "ndcg_at_10": 0.18588, + "ndcg_at_20": 0.215, + "ndcg_at_100": 0.30591, + "ndcg_at_1000": 0.36053, + "map_at_1": 0.05879, + "map_at_3": 0.08056, + "map_at_5": 0.08913, + "map_at_10": 0.11029, + "map_at_20": 0.12161, + "map_at_100": 0.14052, + "map_at_1000": 0.14426, + "recall_at_1": 0.05879, + "recall_at_3": 0.1022, + "recall_at_5": 0.13618, + "recall_at_10": 0.24561, + "recall_at_20": 0.32235, + "recall_at_100": 0.65375, + "recall_at_1000": 0.94599, + "precision_at_1": 0.16279, + "precision_at_3": 0.10853, + "precision_at_5": 0.08837, + "precision_at_10": 0.07829, + "precision_at_20": 0.0531, + "precision_at_100": 0.02333, + "precision_at_1000": 0.0034, + "mrr_at_1": 0.162791, + "mrr_at_3": 0.217054, + "mrr_at_5": 0.24031, + "mrr_at_10": 0.263557, + "mrr_at_20": 0.267609, + "mrr_at_100": 0.274217, + "mrr_at_1000": 0.274818, + "nauc_ndcg_at_1_max": 0.220414, + "nauc_ndcg_at_1_std": 0.061108, + "nauc_ndcg_at_1_diff1": 0.210853, + "nauc_ndcg_at_3_max": 0.141332, + "nauc_ndcg_at_3_std": 0.069507, + "nauc_ndcg_at_3_diff1": 0.138673, + "nauc_ndcg_at_5_max": 0.161851, + "nauc_ndcg_at_5_std": 0.035488, + "nauc_ndcg_at_5_diff1": 0.147766, + "nauc_ndcg_at_10_max": 0.115367, + "nauc_ndcg_at_10_std": 0.002427, + "nauc_ndcg_at_10_diff1": 0.121944, + "nauc_ndcg_at_20_max": 0.164864, + "nauc_ndcg_at_20_std": 0.030284, + "nauc_ndcg_at_20_diff1": 0.126922, + "nauc_ndcg_at_100_max": 0.19635, + "nauc_ndcg_at_100_std": 0.151046, + "nauc_ndcg_at_100_diff1": 0.074165, + "nauc_ndcg_at_1000_max": 0.193482, + "nauc_ndcg_at_1000_std": 0.146592, + "nauc_ndcg_at_1000_diff1": 0.051245, + "nauc_map_at_1_max": 0.062408, + "nauc_map_at_1_std": -0.010915, + "nauc_map_at_1_diff1": 0.170614, + "nauc_map_at_3_max": 0.084729, + "nauc_map_at_3_std": 0.013917, + "nauc_map_at_3_diff1": 0.146988, + "nauc_map_at_5_max": 0.098083, + "nauc_map_at_5_std": 0.001162, + "nauc_map_at_5_diff1": 0.153398, + "nauc_map_at_10_max": 0.08408, + "nauc_map_at_10_std": -0.006798, + "nauc_map_at_10_diff1": 0.145419, + "nauc_map_at_20_max": 0.11224, + "nauc_map_at_20_std": 0.006906, + "nauc_map_at_20_diff1": 0.14996, + "nauc_map_at_100_max": 0.119415, + "nauc_map_at_100_std": 0.05355, + "nauc_map_at_100_diff1": 0.132102, + "nauc_map_at_1000_max": 0.120727, + "nauc_map_at_1000_std": 0.053164, + "nauc_map_at_1000_diff1": 0.12826, + "nauc_recall_at_1_max": 0.062408, + "nauc_recall_at_1_std": -0.010915, + "nauc_recall_at_1_diff1": 0.170614, + "nauc_recall_at_3_max": 0.102143, + "nauc_recall_at_3_std": 0.060093, + "nauc_recall_at_3_diff1": 0.107512, + "nauc_recall_at_5_max": 0.137827, + "nauc_recall_at_5_std": 0.010905, + "nauc_recall_at_5_diff1": 0.131185, + "nauc_recall_at_10_max": 0.018741, + "nauc_recall_at_10_std": -0.06693, + "nauc_recall_at_10_diff1": 0.067878, + "nauc_recall_at_20_max": 0.132183, + "nauc_recall_at_20_std": -0.023735, + "nauc_recall_at_20_diff1": 0.095048, + "nauc_recall_at_100_max": 0.185728, + "nauc_recall_at_100_std": 0.22717, + "nauc_recall_at_100_diff1": -0.012872, + "nauc_recall_at_1000_max": 0.319655, + "nauc_recall_at_1000_std": 0.613667, + "nauc_recall_at_1000_diff1": -0.431753, + "nauc_precision_at_1_max": 0.220414, + "nauc_precision_at_1_std": 0.061108, + "nauc_precision_at_1_diff1": 0.210853, + "nauc_precision_at_3_max": 0.196911, + "nauc_precision_at_3_std": 0.147861, + "nauc_precision_at_3_diff1": 0.096739, + "nauc_precision_at_5_max": 0.244421, + "nauc_precision_at_5_std": 0.121208, + "nauc_precision_at_5_diff1": 0.121846, + "nauc_precision_at_10_max": 0.134613, + "nauc_precision_at_10_std": 0.052998, + "nauc_precision_at_10_diff1": 0.069027, + "nauc_precision_at_20_max": 0.182376, + "nauc_precision_at_20_std": 0.119649, + "nauc_precision_at_20_diff1": 0.046151, + "nauc_precision_at_100_max": 0.176745, + "nauc_precision_at_100_std": 0.319744, + "nauc_precision_at_100_diff1": -0.093572, + "nauc_precision_at_1000_max": 0.097096, + "nauc_precision_at_1000_std": 0.249671, + "nauc_precision_at_1000_diff1": -0.199269, + "nauc_mrr_at_1_max": 0.220414, + "nauc_mrr_at_1_std": 0.061108, + "nauc_mrr_at_1_diff1": 0.210853, + "nauc_mrr_at_3_max": 0.210498, + "nauc_mrr_at_3_std": 0.082801, + "nauc_mrr_at_3_diff1": 0.132928, + "nauc_mrr_at_5_max": 0.22779, + "nauc_mrr_at_5_std": 0.071208, + "nauc_mrr_at_5_diff1": 0.144442, + "nauc_mrr_at_10_max": 0.210349, + "nauc_mrr_at_10_std": 0.053335, + "nauc_mrr_at_10_diff1": 0.136736, + "nauc_mrr_at_20_max": 0.213686, + "nauc_mrr_at_20_std": 0.059326, + "nauc_mrr_at_20_diff1": 0.132488, + "nauc_mrr_at_100_max": 0.217666, + "nauc_mrr_at_100_std": 0.064686, + "nauc_mrr_at_100_diff1": 0.129602, + "nauc_mrr_at_1000_max": 0.217222, + "nauc_mrr_at_1000_std": 0.064491, + "nauc_mrr_at_1000_diff1": 0.130503, + "main_score": 0.18588, + "hf_subset": "IIYi-Clinical", + "languages": [ + "eng-Latn" + ] + } + ] + }, + "evaluation_time": 18790.98300766945, + "kg_co2_emissions": null +} \ No newline at end of file