fix table calculation

[Samoed]

Applying fix from embeddings-benchmark/mteb#3674

[Samoed]

Example table from #317 with validate_and_filter. BelebeleRetrieval scores are the same now

---

Model Results Comparison

Reference models: intfloat/multilingual-e5-large, google/gemini-embedding-001
New models evaluated: Alibaba-NLP/gte-multilingual-base, BAAI/bge-m3, Snowflake/snowflake-arctic-embed-l-v2.0, Snowflake/snowflake-arctic-embed-m-v2.0, ibm-granite/granite-embedding-107m-multilingual, ibm-granite/granite-embedding-278m-multilingual, intfloat/multilingual-e5-base, intfloat/multilingual-e5-large, intfloat/multilingual-e5-small, minishlab/potion-multilingual-128M, sentence-transformers/LaBSE, sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2, sentence-transformers/paraphrase-multilingual-mpnet-base-v2, sentence-transformers/static-similarity-mrl-multilingual-v1
Tasks: ArguAna-NL, ArguAna-NL.v2, BelebeleRetrieval, CovidDisinformationNLMultiLabelClassification, DutchBookReviewSentimentClassification, DutchBookReviewSentimentClassification.v2, DutchColaClassification, DutchGovernmentBiasClassification, DutchNewsArticlesClassification, DutchNewsArticlesClusteringP2P, DutchNewsArticlesClusteringS2S, DutchNewsArticlesRetrieval, DutchSarcasticHeadlinesClassification, IconclassClassification, IconclassClusteringS2S, LegalQANLRetrieval, MassiveIntentClassification, MassiveScenarioClassification, MultiEURLEXMultilabelClassification, MultiHateClassification, NFCorpus-NL, NFCorpus-NL.v2, OpenTenderClassification, OpenTenderClusteringP2P, OpenTenderClusteringS2S, OpenTenderRetrieval, SCIDOCS-NL, SCIDOCS-NL.v2, SIB200Classification, SIB200ClusteringS2S, SICK-NL-STS, SICKNLPairClassification, STSBenchmarkMultilingualSTS, SciFact-NL, SciFact-NL.v2, VABBClusteringP2P, VABBClusteringS2S, VABBMultiLabelClassification, VABBRetrieval, VaccinChatNLClassification, WebFAQRetrieval, WikipediaRerankingMultilingual, WikipediaRetrievalMultilingual, XLWICNLPairClassification, bBSARDNLRetrieval

Results for Alibaba-NLP/gte-multilingual-base

task_name	Alibaba-NLP/gte-multilingual-base	Alibaba-NLP/gte-multilingual-base	Alibaba-NLP/gte-multilingual-base	google/gemini-embedding-001	intfloat/multilingual-e5-large	Max result	Model with max result	In Training Data
Revisions	7fc06782350c1a83f88b15dd4b38ef853d3b8503	ca1791e0bcc104f6db161f27de1340241b13c5a4	external
ArguAna-NL.v2	nan	0.5283	nan	nan	0.4894			False
BelebeleRetrieval	0.8920	0.8920	nan	0.9649	0.9525	0.9858	Qwen/Qwen3-Embedding-8B	False
CovidDisinformationNLMultiLabelClassification	nan	0.4972	nan	nan	0.4970			False
DutchBookReviewSentimentClassification	nan	0.7695	nan	nan	0.7770	0.8821	intfloat/multilingual-e5-large-instruct	False
DutchBookReviewSentimentClassification.v2	nan	0.7459	nan	nan	0.6256			False
DutchColaClassification	nan	0.5550	nan	nan	0.5676			False
DutchGovernmentBiasClassification	nan	0.6193	nan	nan	0.6193			False
DutchNewsArticlesClassification	nan	0.5300	nan	nan	0.5781			False
DutchNewsArticlesClusteringP2P	nan	0.3507	nan	nan	0.4045			False
DutchNewsArticlesClusteringS2S	nan	0.2790	nan	nan	0.2601			False
DutchNewsArticlesRetrieval	nan	0.8088	nan	nan	0.7459			False
DutchSarcasticHeadlinesClassification	nan	0.6578	nan	nan	0.7281			False
IconclassClassification	nan	0.5390	nan	nan	0.5134			False
IconclassClusteringS2S	nan	0.2595	nan	nan	0.2220			False
LegalQANLRetrieval	nan	0.6490	nan	nan	0.7748			False
MassiveIntentClassification	0.6193	0.6193	0.6636	0.8567	0.7045	0.8567	google/gemini-embedding-001	False
MassiveScenarioClassification	nan	0.6985	0.7196	0.8976	0.7483	0.8976	google/gemini-embedding-001	False
MultiEURLEXMultilabelClassification	0.0094	0.0072	nan	0.0594	0.0567	0.0733	google/text-multilingual-embedding-002	False
MultiHateClassification	0.5824	0.5824	nan	0.7417	0.6261	0.8710	tencent/KaLM-Embedding-Gemma3-12B-2511	False
NFCorpus-NL.v2	nan	0.2947	nan	nan	0.2982			False
OpenTenderClassification	nan	0.4336	nan	nan	0.4193			False
OpenTenderClusteringP2P	nan	0.3364	nan	nan	0.2301			False
OpenTenderClusteringS2S	nan	0.2761	nan	nan	0.1617			False
OpenTenderRetrieval	nan	0.4219	nan	nan	0.3778			False
SCIDOCS-NL.v2	nan	0.1584	nan	nan	0.1309			False
SIB200Classification	nan	0.6725	nan	nan	0.7491	0.8496	intfloat/e5-mistral-7b-instruct	False
SIB200ClusteringS2S	0.2489	0.2411	nan	0.4663	0.4166	0.6539	nvidia/llama-embed-nemotron-8b	False
SICK-NL-STS	nan	0.7582	nan	nan	0.7692			False
SICKNLPairClassification	nan	0.9294	nan	nan	0.9332			False
STSBenchmarkMultilingualSTS	0.8302	0.8302	nan	nan	0.8413	0.9552	Gameselo/STS-multilingual-mpnet-base-v2	False
SciFact-NL.v2	nan	0.6433	nan	nan	0.6840			False
VABBClusteringP2P	nan	0.4095	nan	nan	0.3437			False
VABBClusteringS2S	nan	0.3520	nan	nan	0.3071			False
VABBMultiLabelClassification	nan	0.5212	nan	nan	0.5233			False
VABBRetrieval	nan	0.7367	nan	nan	0.7036			False
VaccinChatNLClassification	nan	0.4881	nan	nan	0.5063			False
WikipediaRerankingMultilingual	0.8234	0.8237	nan	0.9267	0.9031	0.9267	google/gemini-embedding-001	False
WikipediaRetrievalMultilingual	0.8398	0.8400	nan	0.9448	0.9182	0.9448	google/gemini-embedding-001	False
XLWICNLPairClassification	nan	0.6274	nan	nan	0.6732			False
bBSARDNLRetrieval	nan	0.2009	nan	nan	0.2384			False
Average	0.6057	0.5396	0.6916	0.7323	0.5505	0.8088	nan	-