add qihoo360/Zhinao-ChineseModernBert-Embedding

[gitabtion]

Checklist

• My model has a model sheet, report, or similar
• [] My model has a reference implementation in mteb/models/model_implementations/, 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 qihoo360/Zhinao-ChineseModernBert-Embedding mteb#4266
• The results submitted are 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 trained 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: qihoo360/Zhinao-ChineseModernBert-Embedding
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 qihoo360/Zhinao-ChineseModernBert-Embedding

task_name	google/gemini-embedding-001	qihoo360/Zhinao-ChineseModernBert-Embedding	intfloat/multilingual-e5-large	Max result	Model with max result	In Training Data
AFQMC	nan	0.5264	0.3301	0.7225	Alibaba-NLP/gte-Qwen2-7B-instruct	False
ATEC	nan	0.5275	0.398	0.6262	Alibaba-NLP/gte-Qwen2-7B-instruct	False
BQ	nan	0.6354	0.4644	0.8125	Alibaba-NLP/gte-Qwen2-7B-instruct	False
CLSClusteringP2P	nan	0.4816	nan	0.8225	Bytedance/Seed1.6-embedding	False
CLSClusteringS2S	nan	0.4992	nan	0.7627	tencent/Youtu-Embedding	False
CMedQAv1-reranking	nan	0.8566	0.6765	0.9434	Kingsoft-LLM/QZhou-Embedding	False
CMedQAv2-reranking	nan	0.8685	0.6672	0.9444	IEITYuan/Yuan-embedding-2.0-zh	False
CmedqaRetrieval	nan	0.4088	0.2866	0.5743	IEITYuan/Yuan-embedding-2.0-zh	False
Cmnli	nan	0.8736	nan	0.9579	Kingsoft-LLM/QZhou-Embedding-Zh	False
CovidRetrieval	0.7913	0.8416	0.7561	0.9606	TencentBAC/Conan-embedding-v2	False
DuRetrieval	nan	0.8659	0.853	0.9423	Bytedance/Seed1.6-embedding	False
EcomRetrieval	nan	0.5986	0.5467	0.7881	Kingsoft-LLM/QZhou-Embedding-Zh	False
IFlyTek	nan	0.4592	0.4186	0.5973	tencent/Youtu-Embedding	False
JDReview	nan	0.8415	0.8054	0.9214	Kingsoft-LLM/QZhou-Embedding-Zh	False
LCQMC	nan	0.7805	0.7595	0.8354	Kingsoft-LLM/QZhou-Embedding-Zh	False
MMarcoReranking	nan	0.315	0.2912	0.4689	TencentBAC/Conan-embedding-v2	False
MMarcoRetrieval	nan	0.7732	0.792	0.9033	Bytedance/Seed1.6-embedding	False
MedicalRetrieval	nan	0.5653	0.5144	0.7627	IEITYuan/Yuan-embedding-2.0-zh	False
MultilingualSentiment	nan	0.7945	0.709	0.8536	Kingsoft-LLM/QZhou-Embedding	False
Ocnli	nan	0.8462	nan	0.9518	Kingsoft-LLM/QZhou-Embedding-Zh	False
OnlineShopping	nan	0.9361	0.9045	0.9716	TencentBAC/Conan-embedding-v2	False
PAWSX	nan	0.4823	0.1463	0.7331	Kingsoft-LLM/QZhou-Embedding-Zh	False
QBQTC	nan	0.527	nan	0.6156	Kingsoft-LLM/QZhou-Embedding-Zh	False
STSB	0.8465	0.7412	0.8108	0.9140	Gameselo/STS-multilingual-mpnet-base-v2	False
T2Reranking	0.6795	0.6815	0.6632	0.7315	tencent/Youtu-Embedding	False
T2Retrieval	nan	0.7785	0.7607	0.8926	ByteDance-Seed/Seed1.5-Embedding	False
TNews	nan	0.4911	0.488	0.6090	Kingsoft-LLM/QZhou-Embedding	False
ThuNewsClusteringP2P	nan	0.8441	nan	0.8976	Kingsoft-LLM/QZhou-Embedding-Zh	False
ThuNewsClusteringS2S	nan	0.797	nan	0.8955	tencent/Youtu-Embedding	False
VideoRetrieval	nan	0.7133	0.5828	0.8311	IEITYuan/Yuan-embedding-2.0-zh	False
Waimai	nan	0.8801	0.863	0.9231	Kingsoft-LLM/QZhou-Embedding	False
Average	0.7725	0.6849	0.6037	0.8118	nan	-

---

---

Note: Content truncated due to GitHub API limits. See the full report in the workflow artifacts.

[gitabtion]

@KennethEnevoldsen Hi, this model is already added to mteb model implementation.