add results for CoDi-Embedding-V1

[spring-quan]

Checklist

• My model has a model sheet, report or similar
• My model has a reference implementation in mteb/models/ this can be as an API. Instruction on how to add a model can be found here
  • No, but there is an existing PR model: Add CoDi-Embedding-V1
• The results submitted is obtained using the reference implementation
• My model is available, either as a publicly accessible API or publicly on e.g., Huggingface
• I solemnly swear that for all results submitted I have not on the evaluation dataset including training splits. If I have I have disclosed it clearly.

[github-actions]

Model Results Comparison

Reference models: intfloat/multilingual-e5-large, google/gemini-embedding-001
New models evaluated: Youtu-RAG/CoDi-Embedding-V1
Tasks: AFQMC, ATEC, BQ, CLSClusteringP2P, CLSClusteringS2S, CMedQAv1-reranking, CMedQAv2-reranking, CmedqaRetrieval, Cmnli, CovidRetrieval, DuRetrieval, EcomRetrieval, IFlyTek, JDReview, LCQMC, MMarcoReranking, MMarcoRetrieval, MedicalRetrieval, MultilingualSentiment, Ocnli, OnlineShopping, PAWSX, QBQTC, STSB, T2Reranking, T2Retrieval, TNews, ThuNewsClusteringP2P, ThuNewsClusteringS2S, VideoRetrieval, Waimai

Results for Youtu-RAG/CoDi-Embedding-V1

task_name	Youtu-RAG/CoDi-Embedding-V1	google/gemini-embedding-001	intfloat/multilingual-e5-large	Max result
AFQMC	0.7153	nan	0.3301	0.7225
ATEC	0.6225	nan	0.398	0.6464
BQ	0.7263	nan	0.4644	0.8125
CLSClusteringP2P	0.7906	nan	nan	0.8225
CLSClusteringS2S	0.7710	nan	nan	0.7387
CMedQAv1-reranking	0.8822	nan	0.6765	0.9156
CMedQAv2-reranking	0.8713	nan	0.6672	0.9248
CmedqaRetrieval	0.5475	nan	0.2866	0.5658
Cmnli	0.8952	nan	nan	0.9306
CovidRetrieval	0.9323	0.7913	0.7561	0.9606
DuRetrieval	0.8969	nan	0.853	0.9423
EcomRetrieval	0.7138	nan	0.5467	0.7764
IFlyTek	0.5303	nan	0.4186	0.5770
JDReview	0.9109	nan	0.8054	0.9169
LCQMC	0.7967	nan	0.7595	0.8070
MMarcoReranking	0.2874	nan	0.2912	0.4689
MMarcoRetrieval	0.8566	nan	0.792	0.9033
MedicalRetrieval	0.7032	nan	0.5144	0.7562
MultilingualSentiment	0.8094	nan	0.709	0.8263
Ocnli	0.8868	nan	nan	0.9215
OnlineShopping	0.9487	nan	0.9045	0.9716
PAWSX	0.5986	nan	0.1463	0.6644
QBQTC	0.5905	nan	nan	0.7145
STSB	0.8404	0.8465	0.8108	0.9140
T2Reranking	0.6759	0.6795	0.6632	0.7283
T2Retrieval	0.8768	nan	0.7607	0.8926
TNews	0.5852	nan	0.488	0.5922
ThuNewsClusteringP2P	0.8805	nan	nan	0.8879
ThuNewsClusteringS2S	0.9024	nan	nan	0.8790
VideoRetrieval	0.7796	nan	0.5828	0.8384
Waimai	0.9047	nan	0.863	0.9174
Average	0.7655	0.7725	0.6037	0.8044

---

[KennethEnevoldsen]

@spring-quan a few of the values seems surprisingly high given the training data, any chance there might have been leakage (or that you have missed a few of these datasets in the training data annotations?) - can I please ask you to double check these

Also seems like the reference link in the model meta refer to the wrong model (feel free to make a PR to fix it)

[spring-quan]

I will check the training data next and close this PR for now.