boards_data/ru/data_overall/default.jsonl

{"index":5,"Rank":1,"Model":"<a target=\"_blank\" style=\"text-decoration: underline\" href=\"https:\/\/huggingface.co\/ai-forever\/ru-en-RoSBERTa\">ru-en-RoSBERTa<\/a>","Model Size (Million Parameters)":404,"Memory Usage (GB, fp32)":1.5,"Embedding Dimensions":1024,"Max Tokens":514,"Average (16 datasets)":64.14,"Classification Average (7 datasets)":60.84,"Clustering Average (3 datasets)":56.06,"PairClassification Average (1 datasets)":60.79,"Reranking Average (1 datasets)":70.87,"Retrieval Average (2 datasets)":72.82,"STS Average (2 datasets)":77.42}
{"index":0,"Rank":2,"Model":"<a target=\"_blank\" style=\"text-decoration: underline\" href=\"https:\/\/huggingface.co\/BAAI\/bge-m3\">bge-m3<\/a>","Model Size (Million Parameters)":567,"Memory Usage (GB, fp32)":2.11,"Embedding Dimensions":1024,"Max Tokens":8192,"Average (16 datasets)":"","Classification Average (7 datasets)":57.43,"Clustering Average (3 datasets)":52.38,"PairClassification Average (1 datasets)":"","Reranking Average (1 datasets)":74.03,"Retrieval Average (2 datasets)":77.1,"STS Average (2 datasets)":""}
{"index":1,"Rank":3,"Model":"<a target=\"_blank\" style=\"text-decoration: underline\" href=\"https:\/\/huggingface.co\/DeepPavlov\/distilrubert-small-cased-conversational\">distilrubert-small-cased-conversational<\/a>","Model Size (Million Parameters)":106,"Memory Usage (GB, fp32)":0.39,"Embedding Dimensions":768,"Max Tokens":512,"Average (16 datasets)":"","Classification Average (7 datasets)":52.16,"Clustering Average (3 datasets)":38.41,"PairClassification Average (1 datasets)":"","Reranking Average (1 datasets)":42.58,"Retrieval Average (2 datasets)":7.37,"STS Average (2 datasets)":""}
{"index":2,"Rank":4,"Model":"<a target=\"_blank\" style=\"text-decoration: underline\" href=\"https:\/\/huggingface.co\/DeepPavlov\/rubert-base-cased\">rubert-base-cased<\/a>","Model Size (Million Parameters)":180,"Memory Usage (GB, fp32)":0.67,"Embedding Dimensions":768,"Max Tokens":512,"Average (16 datasets)":"","Classification Average (7 datasets)":50.66,"Clustering Average (3 datasets)":27.91,"PairClassification Average (1 datasets)":"","Reranking Average (1 datasets)":41.65,"Retrieval Average (2 datasets)":7.55,"STS Average (2 datasets)":""}
{"index":3,"Rank":5,"Model":"<a target=\"_blank\" style=\"text-decoration: underline\" href=\"https:\/\/huggingface.co\/DeepPavlov\/rubert-base-cased-sentence\">rubert-base-cased-sentence<\/a>","Model Size (Million Parameters)":180,"Memory Usage (GB, fp32)":0.67,"Embedding Dimensions":768,"Max Tokens":512,"Average (16 datasets)":"","Classification Average (7 datasets)":51.49,"Clustering Average (3 datasets)":43.13,"PairClassification Average (1 datasets)":"","Reranking Average (1 datasets)":39.89,"Retrieval Average (2 datasets)":9.68,"STS Average (2 datasets)":""}
{"index":4,"Rank":6,"Model":"<a target=\"_blank\" style=\"text-decoration: underline\" href=\"https:\/\/huggingface.co\/GritLM\/GritLM-7B\">GritLM-7B<\/a>","Model Size (Million Parameters)":7240,"Memory Usage (GB, fp32)":26.97,"Embedding Dimensions":"","Max Tokens":4096,"Average (16 datasets)":"","Classification Average (7 datasets)":64.72,"Clustering Average (3 datasets)":61.91,"PairClassification Average (1 datasets)":"","Reranking Average (1 datasets)":72.43,"Retrieval Average (2 datasets)":"","STS Average (2 datasets)":""}
{"index":6,"Rank":7,"Model":"<a target=\"_blank\" style=\"text-decoration: underline\" href=\"https:\/\/huggingface.co\/ai-forever\/sbert_large_mt_nlu_ru\">sbert_large_mt_nlu_ru<\/a>","Model Size (Million Parameters)":427,"Memory Usage (GB, fp32)":1.59,"Embedding Dimensions":1024,"Max Tokens":514,"Average (16 datasets)":"","Classification Average (7 datasets)":55.44,"Clustering Average (3 datasets)":51.29,"PairClassification Average (1 datasets)":"","Reranking Average (1 datasets)":56.14,"Retrieval Average (2 datasets)":25.6,"STS Average (2 datasets)":""}
{"index":7,"Rank":8,"Model":"<a target=\"_blank\" style=\"text-decoration: underline\" href=\"https:\/\/huggingface.co\/ai-forever\/sbert_large_nlu_ru\">sbert_large_nlu_ru<\/a>","Model Size (Million Parameters)":427,"Memory Usage (GB, fp32)":1.59,"Embedding Dimensions":1024,"Max Tokens":512,"Average (16 datasets)":"","Classification Average (7 datasets)":55.21,"Clustering Average (3 datasets)":50.43,"PairClassification Average (1 datasets)":"","Reranking Average (1 datasets)":46.81,"Retrieval Average (2 datasets)":11.78,"STS Average (2 datasets)":""}
{"index":8,"Rank":9,"Model":"<a target=\"_blank\" style=\"text-decoration: underline\" href=\"https:\/\/huggingface.co\/cointegrated\/LaBSE-en-ru\">LaBSE-en-ru<\/a>","Model Size (Million Parameters)":129,"Memory Usage (GB, fp32)":0.48,"Embedding Dimensions":768,"Max Tokens":512,"Average (16 datasets)":"","Classification Average (7 datasets)":52.73,"Clustering Average (3 datasets)":46.84,"PairClassification Average (1 datasets)":"","Reranking Average (1 datasets)":54.83,"Retrieval Average (2 datasets)":31.88,"STS Average (2 datasets)":""}
{"index":9,"Rank":10,"Model":"<a target=\"_blank\" style=\"text-decoration: underline\" href=\"https:\/\/huggingface.co\/cointegrated\/rubert-tiny\">rubert-tiny<\/a>","Model Size (Million Parameters)":12,"Memory Usage (GB, fp32)":0.04,"Embedding Dimensions":512,"Max Tokens":514,"Average (16 datasets)":"","Classification Average (7 datasets)":42.68,"Clustering Average (3 datasets)":30.76,"PairClassification Average (1 datasets)":"","Reranking Average (1 datasets)":35.44,"Retrieval Average (2 datasets)":2.02,"STS Average (2 datasets)":""}
{"index":10,"Rank":11,"Model":"<a target=\"_blank\" style=\"text-decoration: underline\" href=\"https:\/\/huggingface.co\/cointegrated\/rubert-tiny2\">rubert-tiny2<\/a>","Model Size (Million Parameters)":29,"Memory Usage (GB, fp32)":0.11,"Embedding Dimensions":2048,"Max Tokens":514,"Average (16 datasets)":"","Classification Average (7 datasets)":51.37,"Clustering Average (3 datasets)":39.11,"PairClassification Average (1 datasets)":"","Reranking Average (1 datasets)":46.09,"Retrieval Average (2 datasets)":12.4,"STS Average (2 datasets)":""}
{"index":11,"Rank":12,"Model":"<a target=\"_blank\" style=\"text-decoration: underline\" href=\"https:\/\/huggingface.co\/deepvk\/USER-base\">USER-base<\/a>","Model Size (Million Parameters)":124,"Memory Usage (GB, fp32)":0.46,"Embedding Dimensions":768,"Max Tokens":512,"Average (16 datasets)":"","Classification Average (7 datasets)":57.86,"Clustering Average (3 datasets)":53.42,"PairClassification Average (1 datasets)":"","Reranking Average (1 datasets)":64.42,"Retrieval Average (2 datasets)":67.34,"STS Average (2 datasets)":""}
{"index":12,"Rank":13,"Model":"<a target=\"_blank\" style=\"text-decoration: underline\" href=\"https:\/\/huggingface.co\/deepvk\/USER-bge-m3\">USER-bge-m3<\/a>","Model Size (Million Parameters)":359,"Memory Usage (GB, fp32)":1.34,"Embedding Dimensions":1024,"Max Tokens":8192,"Average (16 datasets)":"","Classification Average (7 datasets)":59.36,"Clustering Average (3 datasets)":53.61,"PairClassification Average (1 datasets)":"","Reranking Average (1 datasets)":73.08,"Retrieval Average (2 datasets)":76.78,"STS Average (2 datasets)":""}
{"index":13,"Rank":14,"Model":"<a target=\"_blank\" style=\"text-decoration: underline\" href=\"https:\/\/huggingface.co\/deepvk\/deberta-v1-base\">deberta-v1-base<\/a>","Model Size (Million Parameters)":124,"Memory Usage (GB, fp32)":0.46,"Embedding Dimensions":768,"Max Tokens":512,"Average (16 datasets)":"","Classification Average (7 datasets)":54.23,"Clustering Average (3 datasets)":42.92,"PairClassification Average (1 datasets)":"","Reranking Average (1 datasets)":34.01,"Retrieval Average (2 datasets)":7.5,"STS Average (2 datasets)":""}
{"index":14,"Rank":15,"Model":"<a target=\"_blank\" style=\"text-decoration: underline\" href=\"https:\/\/huggingface.co\/intfloat\/e5-mistral-7b-instruct\">e5-mistral-7b-instruct<\/a>","Model Size (Million Parameters)":7111,"Memory Usage (GB, fp32)":26.49,"Embedding Dimensions":4096,"Max Tokens":32768,"Average (16 datasets)":"","Classification Average (7 datasets)":67.31,"Clustering Average (3 datasets)":64.24,"PairClassification Average (1 datasets)":"","Reranking Average (1 datasets)":76.32,"Retrieval Average (2 datasets)":77.46,"STS Average (2 datasets)":""}
{"index":15,"Rank":16,"Model":"<a target=\"_blank\" style=\"text-decoration: underline\" href=\"https:\/\/huggingface.co\/intfloat\/multilingual-e5-base\">multilingual-e5-base<\/a>","Model Size (Million Parameters)":278,"Memory Usage (GB, fp32)":1.04,"Embedding Dimensions":768,"Max Tokens":514,"Average (16 datasets)":"","Classification Average (7 datasets)":56.19,"Clustering Average (3 datasets)":50.27,"PairClassification Average (1 datasets)":"","Reranking Average (1 datasets)":72.01,"Retrieval Average (2 datasets)":69.91,"STS Average (2 datasets)":""}
{"index":16,"Rank":17,"Model":"<a target=\"_blank\" style=\"text-decoration: underline\" href=\"https:\/\/huggingface.co\/intfloat\/multilingual-e5-large\">multilingual-e5-large<\/a>","Model Size (Million Parameters)":560,"Memory Usage (GB, fp32)":2.09,"Embedding Dimensions":1024,"Max Tokens":514,"Average (16 datasets)":"","Classification Average (7 datasets)":58.92,"Clustering Average (3 datasets)":52.23,"PairClassification Average (1 datasets)":"","Reranking Average (1 datasets)":75.6,"Retrieval Average (2 datasets)":77.4,"STS Average (2 datasets)":""}
{"index":17,"Rank":18,"Model":"<a target=\"_blank\" style=\"text-decoration: underline\" href=\"https:\/\/huggingface.co\/intfloat\/multilingual-e5-small\">multilingual-e5-small<\/a>","Model Size (Million Parameters)":118,"Memory Usage (GB, fp32)":0.44,"Embedding Dimensions":384,"Max Tokens":512,"Average (16 datasets)":"","Classification Average (7 datasets)":55.09,"Clustering Average (3 datasets)":51.35,"PairClassification Average (1 datasets)":"","Reranking Average (1 datasets)":69.98,"Retrieval Average (2 datasets)":69.26,"STS Average (2 datasets)":""}
{"index":18,"Rank":19,"Model":"<a target=\"_blank\" style=\"text-decoration: underline\" href=\"https:\/\/huggingface.co\/sentence-transformers\/LaBSE\">LaBSE<\/a>","Model Size (Million Parameters)":471,"Memory Usage (GB, fp32)":1.75,"Embedding Dimensions":768,"Max Tokens":512,"Average (16 datasets)":"","Classification Average (7 datasets)":52.35,"Clustering Average (3 datasets)":47.74,"PairClassification Average (1 datasets)":"","Reranking Average (1 datasets)":55.13,"Retrieval Average (2 datasets)":36.38,"STS Average (2 datasets)":""}
{"index":19,"Rank":20,"Model":"<a target=\"_blank\" style=\"text-decoration: underline\" href=\"https:\/\/huggingface.co\/sentence-transformers\/all-MiniLM-L12-v2\">all-MiniLM-L12-v2<\/a>","Model Size (Million Parameters)":33,"Memory Usage (GB, fp32)":0.12,"Embedding Dimensions":384,"Max Tokens":512,"Average (16 datasets)":"","Classification Average (7 datasets)":28.33,"Clustering Average (3 datasets)":13.78,"PairClassification Average (1 datasets)":"","Reranking Average (1 datasets)":38.51,"Retrieval Average (2 datasets)":"","STS Average (2 datasets)":""}
{"index":20,"Rank":21,"Model":"<a target=\"_blank\" style=\"text-decoration: underline\" href=\"https:\/\/huggingface.co\/sentence-transformers\/all-MiniLM-L6-v2\">all-MiniLM-L6-v2<\/a>","Model Size (Million Parameters)":23,"Memory Usage (GB, fp32)":0.09,"Embedding Dimensions":384,"Max Tokens":512,"Average (16 datasets)":"","Classification Average (7 datasets)":28.67,"Clustering Average (3 datasets)":13.3,"PairClassification Average (1 datasets)":"","Reranking Average (1 datasets)":27.05,"Retrieval Average (2 datasets)":1.66,"STS Average (2 datasets)":""}
{"index":21,"Rank":22,"Model":"<a target=\"_blank\" style=\"text-decoration: underline\" href=\"https:\/\/huggingface.co\/sentence-transformers\/all-mpnet-base-v2\">all-mpnet-base-v2<\/a>","Model Size (Million Parameters)":110,"Memory Usage (GB, fp32)":0.41,"Embedding Dimensions":768,"Max Tokens":514,"Average (16 datasets)":"","Classification Average (7 datasets)":29.53,"Clustering Average (3 datasets)":15.83,"PairClassification Average (1 datasets)":"","Reranking Average (1 datasets)":30.96,"Retrieval Average (2 datasets)":"","STS Average (2 datasets)":""}
{"index":22,"Rank":23,"Model":"<a target=\"_blank\" style=\"text-decoration: underline\" href=\"https:\/\/huggingface.co\/sentence-transformers\/paraphrase-multilingual-MiniLM-L12-v2\">paraphrase-multilingual-MiniLM-L12-v2<\/a>","Model Size (Million Parameters)":118,"Memory Usage (GB, fp32)":0.44,"Embedding Dimensions":384,"Max Tokens":512,"Average (16 datasets)":"","Classification Average (7 datasets)":51.38,"Clustering Average (3 datasets)":47.76,"PairClassification Average (1 datasets)":"","Reranking Average (1 datasets)":52.8,"Retrieval Average (2 datasets)":37.26,"STS Average (2 datasets)":""}
{"index":23,"Rank":24,"Model":"<a target=\"_blank\" style=\"text-decoration: underline\" href=\"https:\/\/huggingface.co\/sentence-transformers\/paraphrase-multilingual-mpnet-base-v2\">paraphrase-multilingual-mpnet-base-v2<\/a>","Model Size (Million Parameters)":278,"Memory Usage (GB, fp32)":1.04,"Embedding Dimensions":768,"Max Tokens":514,"Average (16 datasets)":"","Classification Average (7 datasets)":54.11,"Clustering Average (3 datasets)":49.18,"PairClassification Average (1 datasets)":"","Reranking Average (1 datasets)":58.77,"Retrieval Average (2 datasets)":44.4,"STS Average (2 datasets)":""}
{"index":24,"Rank":25,"Model":"<a target=\"_blank\" style=\"text-decoration: underline\" href=\"https:\/\/huggingface.co\/sergeyzh\/LaBSE-ru-turbo\">LaBSE-ru-turbo<\/a>","Model Size (Million Parameters)":128,"Memory Usage (GB, fp32)":0.48,"Embedding Dimensions":768,"Max Tokens":512,"Average (16 datasets)":"","Classification Average (7 datasets)":56.55,"Clustering Average (3 datasets)":53.22,"PairClassification Average (1 datasets)":"","Reranking Average (1 datasets)":68.65,"Retrieval Average (2 datasets)":67.54,"STS Average (2 datasets)":""}
{"index":25,"Rank":26,"Model":"<a target=\"_blank\" style=\"text-decoration: underline\" href=\"https:\/\/huggingface.co\/sergeyzh\/rubert-tiny-turbo\">rubert-tiny-turbo<\/a>","Model Size (Million Parameters)":29,"Memory Usage (GB, fp32)":0.11,"Embedding Dimensions":312,"Max Tokens":2048,"Average (16 datasets)":"","Classification Average (7 datasets)":53.46,"Clustering Average (3 datasets)":49.57,"PairClassification Average (1 datasets)":"","Reranking Average (1 datasets)":62.15,"Retrieval Average (2 datasets)":51.5,"STS Average (2 datasets)":""}