Financial PhraseBank
Models classify the financial sentiment of a news sentence as positive, negative, or neutral.
MTEB reports accuracy on its FinancialPhrasebankClassification task.
- Made by
- Pekka Malo and colleagues
- Released
- July 2013
- Kind
- Finance
- Level
- University
- Scored
- Checked automatically
- Answers
- Prediction
- Tasks
- All public
- Measures
- Capability
- Subject
- Economics and business
- Language
- English
- Interaction
- Single turn
- Items from
- Real work and use
- Refresh
- One fixed set
- Run by
- Anyone
- In views
- Law and finance
- Last model added
- October 2026
- Scores refreshed
- November 20th, 2026
ai-sage/Giga-Embeddings-instruct-3B-0826 tops the leaderboard with 100% Qwen3-Embedding-8B leads with 95.2% among models released by October 2026
Best score per entry from MTEB’s leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. The best model we track is Qwen3-Embedding-8B, at 95.2%. This view shows only models we track, each at its best.
The newest model with a score here came out in October 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6.1 Terra
- and 16 more
- 100.0 ai-sage/Giga-Embeddings-instruct-3B-0826
- 99.9 ai-sage/Giga-Embeddings-instruct-10B-A1.8B-0826
- 95.2 microsoft/harrier-oss-v1-0.6b
- 95.2
Qwen3-Embedding-8B
- 94.4 nvidia/llama-embed-nemotron-8b
- 94.1 tencent/KaLM-Embedding-Gemma3-12B-2511
- 94.0 codefuse-ai/F2LLM-v2-14B
- 93.9
Qwen3-Embedding-4B
- 93.8 codefuse-ai/F2LLM-v2-8B
- 93.4 microsoft/harrier-oss-v1-27b
- 93.0 codefuse-ai/F2LLM-v2-4B
- 91.7 BidirLM/BidirLM-Omni-2.5B-Embedding
- 91.2 ICT-TIME-and-Querit/BOOM_4B_v1
- 91.1 ICT-TIME-and-Querit/ICT-TIME-and-Querit-embedding-v1
- 90.6
Qwen3-Embedding-0.6B
- 90.1 Bytedance/Seed1.6-embedding-1215
- 88.6 google/gemini-embedding-001
- 87.7 BidirLM/BidirLM-1.7B-Embedding
- 86.5 BidirLM/BidirLM-1B-Embedding
- 86.5 google/embeddinggemma-300m
- 86.2 Linq-AI-Research/Linq-Embed-Mistral
- 85.6 BidirLM/BidirLM-270M-Embedding
- 85.4 codefuse-ai/F2LLM-v2-1.7B
- 85.4 BidirLM/BidirLM-0.6B-Embedding
- 85.1 codefuse-ai/F2LLM-v2-0.6B
- 84.9 Octen/Octen-Embedding-8B
- 84.5
Gemini Embedding 2
- 84.4 intfloat/multilingual-e5-large-instruct
- 84.4 GritLM/GritLM-7B
- 84.3 google/text-multilingual-embedding-002
- 84.2 nomic-ai/nomic-embed-text-v1.5
- 84.0 nomic-ai/nomic-embed-text-v1
- 83.9 intfloat/multilingual-e5-large
- 83.9 Cohere/Cohere-embed-multilingual-v3.0
- 83.5 deepvk/USER-bge-m3
- 83.5 nomic-ai/nomic-embed-text-v1-ablated
- 83.3 NovaSearch/jasper_en_vision_language_v1
- 83.1 intfloat/e5-large-v2
- 83.0 sentence-transformers/all-mpnet-base-v2
- 82.9 intfloat/e5-base-v2
- 82.9 HIT-TMG/KaLM-embedding-multilingual-mini-v1
- 82.8 Lajavaness/bilingual-embedding-large
- 82.8 thenlper/gte-large
- 82.7 mongodb/voyage-large-2-instruct
- 82.6 McGill-NLP/LLM2Vec-Mistral-7B-Instruct-v2-mntp-supervised
- 82.3 manu/bge-m3-custom-fr
- 82.2 openai/text-embedding-3-large
- 82.2
EmbeddingGemma 2
- 82.2 abhinand/MedEmbed-small-v0.1
- 82.1 intfloat/multilingual-e5-base
- 81.9 nomic-ai/nomic-embed-text-v1-unsupervised
- 81.9 thenlper/gte-base
- 81.9 BAAI/bge-m3
- 81.9 thenlper/gte-small
- 81.7 GritLM/GritLM-8x7B
- 81.7 Cohere/Cohere-embed-english-v3.0
- 81.6 mongodb/voyage-3
- 81.6 avsolatorio/GIST-Embedding-v0
- 81.6 OrdalieTech/Solon-embeddings-large-0.1
- 81.5 avsolatorio/GIST-small-Embedding-v0
- 81.0 intfloat/e5-large
- 80.9 avsolatorio/GIST-large-Embedding-v0
- 80.8 intfloat/e5-small-v2
- 80.8 sergeyzh/LaBSE-ru-turbo
- 80.7 nomic-ai/nomic-embed-text-v2-moe
- 80.7 mongodb/voyage-3.5
- 80.6 Alibaba-NLP/gte-Qwen2-1.5B-instruct
- 80.6 infgrad/stella-base-en-v2
- 80.5 BAAI/bge-base-en-v1.5
- 80.3 microsoft/harrier-oss-v1-270m
- 80.3 BAAI/bge-large-en-v1.5
- 80.3 sdadas/mmlw-e5-base
- 80.2 HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1
- 80.2 NovaSearch/stella_en_1.5B_v5
- 80.1 intfloat/e5-small
- 80.1 Alibaba-NLP/gte-multilingual-base
- 80.0 BAAI/bge-small-en-v1.5
- 80.0 sdadas/mmlw-roberta-base
- 80.0 sdadas/mmlw-roberta-large
- 79.9 Lajavaness/bilingual-embedding-base
- 79.9 mongodb/voyage-3-lite
- 79.9 sdadas/mmlw-e5-large
- 79.8 Omartificial-Intelligence-Space/Arabic-labse-Matryoshka
- 79.7 mongodb/voyage-multilingual-2
- 79.7 avsolatorio/NoInstruct-small-Embedding-v0
- 79.6 mixedbread-ai/mxbai-embed-large-v1
- 79.5 jinaai/jina-embeddings-v3
- 79.4 omarelshehy/arabic-english-sts-matryoshka
- 79.2 intfloat/e5-mistral-7b-instruct
- 79.1 intfloat/e5-base
- 78.8 dwzhu/e5-base-4k
- 78.5 WhereIsAI/UAE-Large-V1
- 78.5 Cohere/Cohere-embed-english-light-v3.0
- 78.4 zeroentropy/zembed-1
- 78.3 nvidia/NV-Embed-v2
- 78.2 sdadas/mmlw-e5-small
- 78.2 intfloat/multilingual-e5-small
- 78.1 deepfile/embedder-100p
- 77.8 openai/text-embedding-3-small
- 77.8 Alibaba-NLP/gte-Qwen1.5-7B-instruct
- 77.7 hotchpotch/bekko-embedding-v1-a25m
- 77.5 sentence-transformers/all-MiniLM-L12-v2
- 77.4 sentence-transformers/paraphrase-multilingual-mpnet-base-v2
- 77.4 Lajavaness/bilingual-embedding-small
- 77.1 ai-forever/ru-en-RoSBERTa
- 77.1 Cohere/Cohere-embed-multilingual-light-v3.0
- 76.6 Omartificial-Intelligence-Space/Arabic-all-nli-triplet-Matryoshka
- 76.4 avsolatorio/GIST-all-MiniLM-L6-v2
- 76.4 aari1995/German_Semantic_STS_V2
- 76.2 Mihaiii/Ivysaur
- 76.2 nvidia/NV-Embed-v1
- 75.8 Salesforce/SFR-Embedding-2_R
- 75.7 NovaSearch/stella_en_400M_v5
- 75.6 Salesforce/SFR-Embedding-Mistral
- 75.4 Alibaba-NLP/gte-Qwen2-7B-instruct
- 74.5 brahmairesearch/slx-v0.1
- 74.5 sentence-transformers/all-MiniLM-L6-v2
- 74.3 codefuse-ai/F2LLM-v2-160M
- 74.0 sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
- 73.0 Mihaiii/Venusaur
- 73.0 Snowflake/snowflake-arctic-embed-m-v2.0
- 72.7 Mihaiii/Wartortle
- 72.7 Mihaiii/Squirtle
- 72.5 manu/sentence_croissant_alpha_v0.4
- 72.2 codefuse-ai/F2LLM-v2-330M
- 72.1 Omartificial-Intelligence-Space/Arabic-MiniLM-L12-v2-all-nli-triplet
- 72.0 Snowflake/snowflake-arctic-embed-m-v1.5
- 72.0 Snowflake/snowflake-arctic-embed-l-v2.0
- 71.9 sentence-transformers/LaBSE
- 71.6 cointegrated/LaBSE-en-ru
- 71.6 Mihaiii/gte-micro-v4
- 71.5 Snowflake/snowflake-arctic-embed-s
- 71.4 ibm-granite/granite-embedding-278m-multilingual
- 71.1 Mihaiii/Bulbasaur
- 71.0 manu/sentence_croissant_alpha_v0.3
- 71.0 Mihaiii/gte-micro
- 70.9 ibm-granite/granite-embedding-107m-multilingual
- 70.9 shibing624/text2vec-base-multilingual
- 70.7 hotchpotch/bekko-embedding-v1-a8m
- 70.5 codefuse-ai/F2LLM-v2-80M
- 69.8 manu/sentence_croissant_alpha_v0.2
- 69.7 ibm-granite/granite-embedding-311m-multilingual-r2
- 69.6 ibm-granite/granite-embedding-125m-english
- 69.4 McGill-NLP/LLM2Vec-Mistral-7B-Instruct-v2-mntp-unsup-simcse
- 69.2 Snowflake/snowflake-arctic-embed-m-long
- 69.0 Snowflake/snowflake-arctic-embed-l
- 68.9 hotchpotch/bekko-static-embedding-v1
- 68.7 Gameselo/STS-multilingual-mpnet-base-v2
- 68.4 Haon-Chen/speed-embedding-7b-instruct
- 68.4 izhx/udever-bloom-7b1
- 68.0 sergeyzh/rubert-tiny-turbo
- 67.8 Snowflake/snowflake-arctic-embed-xs
- 67.6 ibm-granite/granite-embedding-97m-multilingual-r2
- 67.1 Snowflake/snowflake-arctic-embed-m
- 67.0 bigscience/sgpt-bloom-7b1-msmarco
- 66.6 ibm-granite/granite-embedding-30m-english
- 66.1 cnmoro/static-nomic-384-pten-v2-st
- 66.1 izhx/udever-bloom-3b
- 64.8 izhx/udever-bloom-1b1
- 64.7 minishlab/potion-base-8M
- 63.4 jinaai/jina-embeddings-v5-omni-small
- 63.4 jinaai/jina-embeddings-v5-text-small
- 62.9 deepvk/USER-base
- 62.6 cointegrated/rubert-tiny2
- 62.4 minishlab/potion-multilingual-128M
- 61.9 minishlab/potion-base-4M
- 61.9 jinaai/jina-embedding-b-en-v1
- 61.7 consciousAI/cai-lunaris-text-embeddings
- 60.6 cointegrated/rubert-tiny
- 59.0 minishlab/potion-base-2M
- 58.4 jinaai/jina-embedding-s-en-v1
- 58.4 izhx/udever-bloom-560m
- 57.1 ai-forever/sbert_large_nlu_ru
- 56.4 minishlab/M2V_base_output
- 56.3 minishlab/M2V_base_glove_subword
- 56.2 Jaume/gemma-2b-embeddings
- 55.9 silma-ai/silma-embeddding-matryoshka-v0.1
- 55.3 DeepPavlov/distilrubert-small-cased-conversational
- 54.8 ai-forever/sbert_large_mt_nlu_ru
- 54.8 jinaai/jina-embeddings-v2-small-en
- 53.9 minishlab/M2V_base_glove
- 53.5 DeepPavlov/rubert-base-cased
- 52.8 Omartificial-Intelligence-Space/Marbert-all-nli-triplet-Matryoshka
- 52.7 Omartificial-Intelligence-Space/Arabic-mpnet-base-all-nli-triplet
- 52.2 sentence-transformers/static-similarity-mrl-multilingual-v1
- 50.3 deepvk/deberta-v1-base
- 48.8 DeepPavlov/rubert-base-cased-sentence
- 48.6 jinaai/jina-embeddings-v5-omni-nano
- 48.6 jinaai/jina-embeddings-v5-text-nano
- 46.0 Omartificial-Intelligence-Space/Arabert-all-nli-triplet-Matryoshka
- 44.3 malenia1/ternary-weight-embedding
- 44.0 Hum-Works/lodestone-base-4096-v1
- 37.5 jinaai/jina-embeddings-v2-base-en
- 1 ai-sage/Giga-Embeddings-instruct-3B-0826 100%
- 2 ai-sage/Giga-Embeddings-instruct-10B-A1.8B-0826 99.9%
- 3 microsoft/harrier-oss-v1-0.6b 95.2%
- 4
Qwen3-Embedding-8B 95.2%
- 5 nvidia/llama-embed-nemotron-8b 94.4%
- 6 tencent/KaLM-Embedding-Gemma3-12B-2511 94.1%
- 7 codefuse-ai/F2LLM-v2-14B 94%
- 8
Qwen3-Embedding-4B 93.9%
- 9 codefuse-ai/F2LLM-v2-8B 93.8%
- 10 microsoft/harrier-oss-v1-27b 93.4%
- 11 codefuse-ai/F2LLM-v2-4B 93%
- 12 BidirLM/BidirLM-Omni-2.5B-Embedding 91.7%
- 13 ICT-TIME-and-Querit/BOOM_4B_v1 91.2%
- 14 ICT-TIME-and-Querit/ICT-TIME-and-Querit-embedding-v1 91.1%
- 15
Qwen3-Embedding-0.6B 90.6%
- 16 Bytedance/Seed1.6-embedding-1215 90.1%
- 17 google/gemini-embedding-001 88.6%
- 18 BidirLM/BidirLM-1.7B-Embedding 87.7%
- 19 BidirLM/BidirLM-1B-Embedding 86.5%
- 20 google/embeddinggemma-300m 86.5%
- 21 Linq-AI-Research/Linq-Embed-Mistral 86.2%
- 22 BidirLM/BidirLM-270M-Embedding 85.6%
- 23 codefuse-ai/F2LLM-v2-1.7B 85.4%
- 24 BidirLM/BidirLM-0.6B-Embedding 85.4%
- 25 codefuse-ai/F2LLM-v2-0.6B 85.1%
- 26 Octen/Octen-Embedding-8B 84.9%
- 27
Gemini Embedding 2 84.5%
- 28 intfloat/multilingual-e5-large-instruct 84.4%
- 29 GritLM/GritLM-7B 84.4%
- 30 google/text-multilingual-embedding-002 84.3%
- 31 nomic-ai/nomic-embed-text-v1.5 84.2%
- 32 nomic-ai/nomic-embed-text-v1 84%
- 33 intfloat/multilingual-e5-large 83.9%
- 34 Cohere/Cohere-embed-multilingual-v3.0 83.9%
- 35 deepvk/USER-bge-m3 83.5%
- 36 nomic-ai/nomic-embed-text-v1-ablated 83.5%
- 37 NovaSearch/jasper_en_vision_language_v1 83.3%
- 38 intfloat/e5-large-v2 83.1%
- 39 sentence-transformers/all-mpnet-base-v2 83%
- 40 intfloat/e5-base-v2 82.9%
- 41 HIT-TMG/KaLM-embedding-multilingual-mini-v1 82.9%
- 42 Lajavaness/bilingual-embedding-large 82.8%
- 43 thenlper/gte-large 82.8%
- 44 mongodb/voyage-large-2-instruct 82.7%
- 45 McGill-NLP/LLM2Vec-Mistral-7B-Instruct-v2-mntp-supervised 82.6%
- 46 manu/bge-m3-custom-fr 82.3%
- 47 openai/text-embedding-3-large 82.2%
- 48
EmbeddingGemma 2 82.2%
- 49 abhinand/MedEmbed-small-v0.1 82.2%
- 50 intfloat/multilingual-e5-base 82.1%
- 51 nomic-ai/nomic-embed-text-v1-unsupervised 81.9%
- 52 thenlper/gte-base 81.9%
- 53 BAAI/bge-m3 81.9%
- 54 thenlper/gte-small 81.9%
- 55 GritLM/GritLM-8x7B 81.7%
- 56 Cohere/Cohere-embed-english-v3.0 81.7%
- 57 mongodb/voyage-3 81.6%
- 58 avsolatorio/GIST-Embedding-v0 81.6%
- 59 OrdalieTech/Solon-embeddings-large-0.1 81.6%
- 60 avsolatorio/GIST-small-Embedding-v0 81.5%
- 61 intfloat/e5-large 81%
- 62 avsolatorio/GIST-large-Embedding-v0 80.9%
- 63 intfloat/e5-small-v2 80.8%
- 64 sergeyzh/LaBSE-ru-turbo 80.8%
- 65 nomic-ai/nomic-embed-text-v2-moe 80.7%
- 66 mongodb/voyage-3.5 80.7%
- 67 Alibaba-NLP/gte-Qwen2-1.5B-instruct 80.6%
- 68 infgrad/stella-base-en-v2 80.6%
- 69 BAAI/bge-base-en-v1.5 80.5%
- 70 microsoft/harrier-oss-v1-270m 80.3%
- 71 BAAI/bge-large-en-v1.5 80.3%
- 72 sdadas/mmlw-e5-base 80.3%
- 73 HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1 80.2%
- 74 NovaSearch/stella_en_1.5B_v5 80.2%
- 75 intfloat/e5-small 80.1%
- 76 Alibaba-NLP/gte-multilingual-base 80.1%
- 77 BAAI/bge-small-en-v1.5 80%
- 78 sdadas/mmlw-roberta-base 80%
- 79 sdadas/mmlw-roberta-large 80%
- 80 Lajavaness/bilingual-embedding-base 79.9%
- 81 mongodb/voyage-3-lite 79.9%
- 82 sdadas/mmlw-e5-large 79.9%
- 83 Omartificial-Intelligence-Space/Arabic-labse-Matryoshka 79.8%
- 84 mongodb/voyage-multilingual-2 79.7%
- 85 avsolatorio/NoInstruct-small-Embedding-v0 79.7%
- 86 mixedbread-ai/mxbai-embed-large-v1 79.6%
- 87 jinaai/jina-embeddings-v3 79.5%
- 88 omarelshehy/arabic-english-sts-matryoshka 79.4%
- 89 intfloat/e5-mistral-7b-instruct 79.2%
- 90 intfloat/e5-base 79.1%
- 91 dwzhu/e5-base-4k 78.8%
- 92 WhereIsAI/UAE-Large-V1 78.5%
- 93 Cohere/Cohere-embed-english-light-v3.0 78.5%
- 94 zeroentropy/zembed-1 78.4%
- 95 nvidia/NV-Embed-v2 78.3%
- 96 sdadas/mmlw-e5-small 78.2%
- 97 intfloat/multilingual-e5-small 78.2%
- 98 deepfile/embedder-100p 78.1%
- 99 openai/text-embedding-3-small 77.8%
- 100 Alibaba-NLP/gte-Qwen1.5-7B-instruct 77.8%
- 101 hotchpotch/bekko-embedding-v1-a25m 77.7%
- 102 sentence-transformers/all-MiniLM-L12-v2 77.5%
- 103 sentence-transformers/paraphrase-multilingual-mpnet-base-v2 77.4%
- 104 Lajavaness/bilingual-embedding-small 77.4%
- 105 ai-forever/ru-en-RoSBERTa 77.1%
- 106 Cohere/Cohere-embed-multilingual-light-v3.0 77.1%
- 107 Omartificial-Intelligence-Space/Arabic-all-nli-triplet-Matryoshka 76.6%
- 108 avsolatorio/GIST-all-MiniLM-L6-v2 76.4%
- 109 aari1995/German_Semantic_STS_V2 76.4%
- 110 Mihaiii/Ivysaur 76.2%
- 111 nvidia/NV-Embed-v1 76.2%
- 112 Salesforce/SFR-Embedding-2_R 75.8%
- 113 NovaSearch/stella_en_400M_v5 75.7%
- 114 Salesforce/SFR-Embedding-Mistral 75.6%
- 115 Alibaba-NLP/gte-Qwen2-7B-instruct 75.4%
- 116 brahmairesearch/slx-v0.1 74.5%
- 117 sentence-transformers/all-MiniLM-L6-v2 74.5%
- 118 codefuse-ai/F2LLM-v2-160M 74.3%
- 119 sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 74%
- 120 Mihaiii/Venusaur 73%
- 121 Snowflake/snowflake-arctic-embed-m-v2.0 73%
- 122 Mihaiii/Wartortle 72.7%
- 123 Mihaiii/Squirtle 72.7%
- 124 manu/sentence_croissant_alpha_v0.4 72.5%
- 125 codefuse-ai/F2LLM-v2-330M 72.2%
- 126 Omartificial-Intelligence-Space/Arabic-MiniLM-L12-v2-all-nli-triplet 72.1%
- 127 Snowflake/snowflake-arctic-embed-m-v1.5 72%
- 128 Snowflake/snowflake-arctic-embed-l-v2.0 72%
- 129 sentence-transformers/LaBSE 71.9%
- 130 cointegrated/LaBSE-en-ru 71.6%
- 131 Mihaiii/gte-micro-v4 71.6%
- 132 Snowflake/snowflake-arctic-embed-s 71.5%
- 133 ibm-granite/granite-embedding-278m-multilingual 71.4%
- 134 Mihaiii/Bulbasaur 71.1%
- 135 manu/sentence_croissant_alpha_v0.3 71%
- 136 Mihaiii/gte-micro 71%
- 137 ibm-granite/granite-embedding-107m-multilingual 70.9%
- 138 shibing624/text2vec-base-multilingual 70.9%
- 139 hotchpotch/bekko-embedding-v1-a8m 70.7%
- 140 codefuse-ai/F2LLM-v2-80M 70.5%
- 141 manu/sentence_croissant_alpha_v0.2 69.8%
- 142 ibm-granite/granite-embedding-311m-multilingual-r2 69.7%
- 143 ibm-granite/granite-embedding-125m-english 69.6%
- 144 McGill-NLP/LLM2Vec-Mistral-7B-Instruct-v2-mntp-unsup-simcse 69.4%
- 145 Snowflake/snowflake-arctic-embed-m-long 69.2%
- 146 Snowflake/snowflake-arctic-embed-l 69%
- 147 hotchpotch/bekko-static-embedding-v1 68.9%
- 148 Gameselo/STS-multilingual-mpnet-base-v2 68.7%
- 149 Haon-Chen/speed-embedding-7b-instruct 68.4%
- 150 izhx/udever-bloom-7b1 68.4%
- 151 sergeyzh/rubert-tiny-turbo 68%
- 152 Snowflake/snowflake-arctic-embed-xs 67.8%
- 153 ibm-granite/granite-embedding-97m-multilingual-r2 67.6%
- 154 Snowflake/snowflake-arctic-embed-m 67.1%
- 155 bigscience/sgpt-bloom-7b1-msmarco 67%
- 156 ibm-granite/granite-embedding-30m-english 66.6%
- 157 cnmoro/static-nomic-384-pten-v2-st 66.1%
- 158 izhx/udever-bloom-3b 66.1%
- 159 izhx/udever-bloom-1b1 64.8%
- 160 minishlab/potion-base-8M 64.7%
- 161 jinaai/jina-embeddings-v5-omni-small 63.4%
- 162 jinaai/jina-embeddings-v5-text-small 63.4%
- 163 deepvk/USER-base 62.9%
- 164 cointegrated/rubert-tiny2 62.6%
- 165 minishlab/potion-multilingual-128M 62.4%
- 166 minishlab/potion-base-4M 61.9%
- 167 jinaai/jina-embedding-b-en-v1 61.9%
- 168 consciousAI/cai-lunaris-text-embeddings 61.7%
- 169 cointegrated/rubert-tiny 60.6%
- 170 minishlab/potion-base-2M 59%
- 171 jinaai/jina-embedding-s-en-v1 58.4%
- 172 izhx/udever-bloom-560m 58.4%
- 173 ai-forever/sbert_large_nlu_ru 57.1%
- 174 minishlab/M2V_base_output 56.4%
- 175 minishlab/M2V_base_glove_subword 56.3%
- 176 Jaume/gemma-2b-embeddings 56.2%
- 177 silma-ai/silma-embeddding-matryoshka-v0.1 55.9%
- 178 DeepPavlov/distilrubert-small-cased-conversational 55.3%
- 179 ai-forever/sbert_large_mt_nlu_ru 54.8%
- 180 jinaai/jina-embeddings-v2-small-en 54.8%
- 181 minishlab/M2V_base_glove 53.9%
- 182 DeepPavlov/rubert-base-cased 53.5%
- 183 Omartificial-Intelligence-Space/Marbert-all-nli-triplet-Matryoshka 52.8%
- 184 Omartificial-Intelligence-Space/Arabic-mpnet-base-all-nli-triplet 52.7%
- 185 sentence-transformers/static-similarity-mrl-multilingual-v1 52.2%
- 186 deepvk/deberta-v1-base 50.3%
- 187 DeepPavlov/rubert-base-cased-sentence 48.8%
- 188 jinaai/jina-embeddings-v5-omni-nano 48.6%
- 189 jinaai/jina-embeddings-v5-text-nano 48.6%
- 190 Omartificial-Intelligence-Space/Arabert-all-nli-triplet-Matryoshka 46%
- 191 malenia1/ternary-weight-embedding 44.3%
- 192 Hum-Works/lodestone-base-4096-v1 44%
- 193 jinaai/jina-embeddings-v2-base-en 37.5%
Source: MTEB’s leaderboard
- 1
Qwen3-Embedding-8B 95.2%
- 2
Qwen3-Embedding-4B 93.9%
- 3
Qwen3-Embedding-0.6B 90.6%
- 4
Gemini Embedding 2 84.5%
- 5
EmbeddingGemma 2 82.2%
Source: MTEB’s leaderboard
| # | Entry | Score | Setting | Date | Link | Source |
|---|---|---|---|---|---|---|
| 1 | ai-sage/Giga-Embeddings-instruct-3B-0826 open weights, 3.2B | 100% | huggingface.co | Official leaderboard | ||
| 2 | ai-sage/Giga-Embeddings-instruct-10B-A1.8B-0826 open weights, 10.5B | 99.9% | huggingface.co | Official leaderboard | ||
| 3 | microsoft/harrier-oss-v1-0.6b open weights, 0.6B | 95.2% | huggingface.co | Official leaderboard | ||
| 4 | | 95.2% | Jun 2025 | huggingface.co | Official leaderboard | |
| 5 | nvidia/llama-embed-nemotron-8b open weights, 7.5B | 94.4% | huggingface.co | Official leaderboard | ||
| 6 | tencent/KaLM-Embedding-Gemma3-12B-2511 open weights, 11.8B | 94.1% | huggingface.co | Official leaderboard | ||
| 7 | codefuse-ai/F2LLM-v2-14B open weights, 14B | 94% | huggingface.co | Official leaderboard | ||
| 8 | | 93.9% | Jun 2025 | huggingface.co | Official leaderboard | |
| 9 | codefuse-ai/F2LLM-v2-8B open weights, 7.6B | 93.8% | huggingface.co | Official leaderboard | ||
| 10 | microsoft/harrier-oss-v1-27b open weights, 27B | 93.4% | huggingface.co | Official leaderboard | ||
| 11 | codefuse-ai/F2LLM-v2-4B open weights, 4B | 93% | huggingface.co | Official leaderboard | ||
| 12 | BidirLM/BidirLM-Omni-2.5B-Embedding open weights, 2.4B | 91.7% | huggingface.co | Official leaderboard | ||
| 13 | ICT-TIME-and-Querit/BOOM_4B_v1 open weights, 4B | 91.2% | huggingface.co | Official leaderboard | ||
| 14 | ICT-TIME-and-Querit/ICT-TIME-and-Querit-embedding-v1 open weights, 4B | 91.1% | huggingface.co | Official leaderboard | ||
| 15 | | 90.6% | Jun 2025 | huggingface.co | Official leaderboard | |
| 16 | Bytedance/Seed1.6-embedding-1215 closed weights | 90.1% | console.volcengine.com | Official leaderboard | ||
| 17 | google/gemini-embedding-001 closed weights | 88.6% | ai.google.dev | Official leaderboard | ||
| 18 | BidirLM/BidirLM-1.7B-Embedding open weights, 1.7B | 87.7% | huggingface.co | Official leaderboard | ||
| 19 | BidirLM/BidirLM-1B-Embedding open weights, 1B | 86.5% | huggingface.co | Official leaderboard | ||
| 20 | google/embeddinggemma-300m open weights, 0.3B | 86.5% | ai.google.dev | Official leaderboard | ||
| 21 | Linq-AI-Research/Linq-Embed-Mistral open weights, 7.1B | 86.2% | huggingface.co | Official leaderboard | ||
| 22 | BidirLM/BidirLM-270M-Embedding open weights, 0.3B | 85.6% | huggingface.co | Official leaderboard | ||
| 23 | codefuse-ai/F2LLM-v2-1.7B open weights, 1.7B | 85.4% | huggingface.co | Official leaderboard | ||
| 24 | BidirLM/BidirLM-0.6B-Embedding open weights, 0.6B | 85.4% | huggingface.co | Official leaderboard | ||
| 25 | codefuse-ai/F2LLM-v2-0.6B open weights, 0.6B | 85.1% | huggingface.co | Official leaderboard | ||
| 26 | Octen/Octen-Embedding-8B open weights, 7.6B | 84.9% | huggingface.co | Official leaderboard | ||
| 27 | | 84.5% | Mar 2026 | ai.google.dev | Official leaderboard | |
| 28 | intfloat/multilingual-e5-large-instruct open weights, 0.6B | 84.4% | huggingface.co | Official leaderboard | ||
| 29 | GritLM/GritLM-7B open weights, 7.2B | 84.4% | huggingface.co | Official leaderboard | ||
| 30 | google/text-multilingual-embedding-002 closed weights | 84.3% | cloud.google.com | Official leaderboard | ||
| 31 | nomic-ai/nomic-embed-text-v1.5 open weights, 0.1B | 84.2% | huggingface.co | Official leaderboard | ||
| 32 | nomic-ai/nomic-embed-text-v1 open weights, 0.1B | 84% | huggingface.co | Official leaderboard | ||
| 33 | intfloat/multilingual-e5-large open weights, 0.6B | 83.9% | huggingface.co | Official leaderboard | ||
| 34 | Cohere/Cohere-embed-multilingual-v3.0 closed weights | 83.9% | cohere.com | Official leaderboard | ||
| 35 | deepvk/USER-bge-m3 open weights, 0.4B | 83.5% | huggingface.co | Official leaderboard | ||
| 36 | nomic-ai/nomic-embed-text-v1-ablated open weights, 0.1B | 83.5% | huggingface.co | Official leaderboard | ||
| 37 | NovaSearch/jasper_en_vision_language_v1 open weights, 1.6B | 83.3% | huggingface.co | Official leaderboard | ||
| 38 | intfloat/e5-large-v2 open weights, 0.3B | 83.1% | huggingface.co | Official leaderboard | ||
| 39 | sentence-transformers/all-mpnet-base-v2 open weights, 0.1B | 83% | huggingface.co | Official leaderboard | ||
| 40 | intfloat/e5-base-v2 open weights, 0.1B | 82.9% | huggingface.co | Official leaderboard | ||
| 41 | HIT-TMG/KaLM-embedding-multilingual-mini-v1 open weights, 0.5B | 82.9% | huggingface.co | Official leaderboard | ||
| 42 | Lajavaness/bilingual-embedding-large open weights, 0.6B | 82.8% | huggingface.co | Official leaderboard | ||
| 43 | thenlper/gte-large open weights, 0.3B | 82.8% | huggingface.co | Official leaderboard | ||
| 44 | mongodb/voyage-large-2-instruct closed weights | 82.7% | blog.voyageai.com | Official leaderboard | ||
| 45 | McGill-NLP/LLM2Vec-Mistral-7B-Instruct-v2-mntp-supervised open weights, 7.2B | 82.6% | huggingface.co | Official leaderboard | ||
| 46 | manu/bge-m3-custom-fr open weights, 0.6B | 82.3% | huggingface.co | Official leaderboard | ||
| 47 | openai/text-embedding-3-large closed weights | 82.2% | openai.com | Official leaderboard | ||
| 48 | | 82.2% | Oct 2026 | huggingface.co | Official leaderboard | |
| 49 | abhinand/MedEmbed-small-v0.1 open weights, 0B | 82.2% | huggingface.co | Official leaderboard | ||
| 50 | intfloat/multilingual-e5-base open weights, 0.3B | 82.1% | huggingface.co | Official leaderboard | ||
| 51 | nomic-ai/nomic-embed-text-v1-unsupervised open weights, 0.1B | 81.9% | huggingface.co | Official leaderboard | ||
| 52 | thenlper/gte-base open weights, 0.1B | 81.9% | huggingface.co | Official leaderboard | ||
| 53 | BAAI/bge-m3 open weights, 0.6B | 81.9% | huggingface.co | Official leaderboard | ||
| 54 | thenlper/gte-small open weights, 0B | 81.9% | huggingface.co | Official leaderboard | ||
| 55 | GritLM/GritLM-8x7B open weights, 57.9B | 81.7% | huggingface.co | Official leaderboard | ||
| 56 | Cohere/Cohere-embed-english-v3.0 closed weights | 81.7% | cohere.com | Official leaderboard | ||
| 57 | mongodb/voyage-3 closed weights | 81.6% | blog.voyageai.com | Official leaderboard | ||
| 58 | avsolatorio/GIST-Embedding-v0 open weights, 0.1B | 81.6% | huggingface.co | Official leaderboard | ||
| 59 | OrdalieTech/Solon-embeddings-large-0.1 open weights, 0.6B | 81.6% | huggingface.co | Official leaderboard | ||
| 60 | avsolatorio/GIST-small-Embedding-v0 open weights, 0B | 81.5% | huggingface.co | Official leaderboard | ||
| 61 | intfloat/e5-large open weights, 0.3B | 81% | huggingface.co | Official leaderboard | ||
| 62 | avsolatorio/GIST-large-Embedding-v0 open weights, 0.3B | 80.9% | huggingface.co | Official leaderboard | ||
| 63 | intfloat/e5-small-v2 open weights, 0B | 80.8% | huggingface.co | Official leaderboard | ||
| 64 | sergeyzh/LaBSE-ru-turbo open weights, 0.1B | 80.8% | huggingface.co | Official leaderboard | ||
| 65 | nomic-ai/nomic-embed-text-v2-moe open weights, 0.5B | 80.7% | huggingface.co | Official leaderboard | ||
| 66 | mongodb/voyage-3.5 closed weights | 80.7% | blog.voyageai.com | Official leaderboard | ||
| 67 | Alibaba-NLP/gte-Qwen2-1.5B-instruct open weights, 1.5B | 80.6% | huggingface.co | Official leaderboard | ||
| 68 | infgrad/stella-base-en-v2 open weights, 0.1B | 80.6% | huggingface.co | Official leaderboard | ||
| 69 | BAAI/bge-base-en-v1.5 open weights, 0.1B | 80.5% | huggingface.co | Official leaderboard | ||
| 70 | microsoft/harrier-oss-v1-270m open weights, 0.3B | 80.3% | huggingface.co | Official leaderboard | ||
| 71 | BAAI/bge-large-en-v1.5 open weights, 0.3B | 80.3% | huggingface.co | Official leaderboard | ||
| 72 | sdadas/mmlw-e5-base open weights, 0.3B | 80.3% | huggingface.co | Official leaderboard | ||
| 73 | HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1 open weights, 0.5B | 80.2% | huggingface.co | Official leaderboard | ||
| 74 | NovaSearch/stella_en_1.5B_v5 open weights, 1.5B | 80.2% | huggingface.co | Official leaderboard | ||
| 75 | intfloat/e5-small open weights, 0B | 80.1% | huggingface.co | Official leaderboard | ||
| 76 | Alibaba-NLP/gte-multilingual-base open weights, 0.3B | 80.1% | huggingface.co | Official leaderboard | ||
| 77 | BAAI/bge-small-en-v1.5 open weights, 0B | 80% | huggingface.co | Official leaderboard | ||
| 78 | sdadas/mmlw-roberta-base open weights, 0.1B | 80% | huggingface.co | Official leaderboard | ||
| 79 | sdadas/mmlw-roberta-large open weights, 0.4B | 80% | huggingface.co | Official leaderboard | ||
| 80 | Lajavaness/bilingual-embedding-base open weights, 0.3B | 79.9% | huggingface.co | Official leaderboard | ||
| 81 | mongodb/voyage-3-lite closed weights | 79.9% | blog.voyageai.com | Official leaderboard | ||
| 82 | sdadas/mmlw-e5-large open weights, 0.6B | 79.9% | huggingface.co | Official leaderboard | ||
| 83 | Omartificial-Intelligence-Space/Arabic-labse-Matryoshka open weights, 0.5B | 79.8% | huggingface.co | Official leaderboard | ||
| 84 | mongodb/voyage-multilingual-2 closed weights | 79.7% | blog.voyageai.com | Official leaderboard | ||
| 85 | avsolatorio/NoInstruct-small-Embedding-v0 open weights, 0B | 79.7% | huggingface.co | Official leaderboard | ||
| 86 | mixedbread-ai/mxbai-embed-large-v1 open weights, 0.3B | 79.6% | huggingface.co | Official leaderboard | ||
| 87 | jinaai/jina-embeddings-v3 open weights, 0.6B | 79.5% | huggingface.co | Official leaderboard | ||
| 88 | omarelshehy/arabic-english-sts-matryoshka open weights, 0.6B | 79.4% | huggingface.co | Official leaderboard | ||
| 89 | intfloat/e5-mistral-7b-instruct open weights, 7.1B | 79.2% | huggingface.co | Official leaderboard | ||
| 90 | intfloat/e5-base open weights, 0.1B | 79.1% | huggingface.co | Official leaderboard | ||
| 91 | dwzhu/e5-base-4k open weights, 0.1B | 78.8% | huggingface.co | Official leaderboard | ||
| 92 | WhereIsAI/UAE-Large-V1 open weights, 0.3B | 78.5% | huggingface.co | Official leaderboard | ||
| 93 | Cohere/Cohere-embed-english-light-v3.0 closed weights | 78.5% | cohere.com | Official leaderboard | ||
| 94 | zeroentropy/zembed-1 open weights, 4B | 78.4% | huggingface.co | Official leaderboard | ||
| 95 | nvidia/NV-Embed-v2 open weights, 7.9B | 78.3% | huggingface.co | Official leaderboard | ||
| 96 | sdadas/mmlw-e5-small open weights, 0.1B | 78.2% | huggingface.co | Official leaderboard | ||
| 97 | intfloat/multilingual-e5-small open weights, 0.1B | 78.2% | huggingface.co | Official leaderboard | ||
| 98 | deepfile/embedder-100p open weights, 0.3B | 78.1% | huggingface.co | Official leaderboard | ||
| 99 | openai/text-embedding-3-small closed weights | 77.8% | openai.com | Official leaderboard | ||
| 100 | Alibaba-NLP/gte-Qwen1.5-7B-instruct open weights, 7.1B | 77.8% | huggingface.co | Official leaderboard | ||
| 101 | hotchpotch/bekko-embedding-v1-a25m open weights, 0.1B | 77.7% | huggingface.co | Official leaderboard | ||
| 102 | sentence-transformers/all-MiniLM-L12-v2 open weights, 0B | 77.5% | huggingface.co | Official leaderboard | ||
| 103 | sentence-transformers/paraphrase-multilingual-mpnet-base-v2 open weights, 0.3B | 77.4% | huggingface.co | Official leaderboard | ||
| 104 | Lajavaness/bilingual-embedding-small open weights, 0.1B | 77.4% | huggingface.co | Official leaderboard | ||
| 105 | ai-forever/ru-en-RoSBERTa open weights, 0.4B | 77.1% | huggingface.co | Official leaderboard | ||
| 106 | Cohere/Cohere-embed-multilingual-light-v3.0 closed weights | 77.1% | cohere.com | Official leaderboard | ||
| 107 | Omartificial-Intelligence-Space/Arabic-all-nli-triplet-Matryoshka open weights, 0.3B | 76.6% | huggingface.co | Official leaderboard | ||
| 108 | avsolatorio/GIST-all-MiniLM-L6-v2 open weights, 0B | 76.4% | huggingface.co | Official leaderboard | ||
| 109 | aari1995/German_Semantic_STS_V2 open weights, 0.3B | 76.4% | huggingface.co | Official leaderboard | ||
| 110 | Mihaiii/Ivysaur open weights, 0B | 76.2% | huggingface.co | Official leaderboard | ||
| 111 | nvidia/NV-Embed-v1 open weights, 7.9B | 76.2% | huggingface.co | Official leaderboard | ||
| 112 | Salesforce/SFR-Embedding-2_R open weights, 7.1B | 75.8% | huggingface.co | Official leaderboard | ||
| 113 | NovaSearch/stella_en_400M_v5 open weights, 0.4B | 75.7% | huggingface.co | Official leaderboard | ||
| 114 | Salesforce/SFR-Embedding-Mistral open weights, 7.1B | 75.6% | huggingface.co | Official leaderboard | ||
| 115 | Alibaba-NLP/gte-Qwen2-7B-instruct open weights, 7.1B | 75.4% | huggingface.co | Official leaderboard | ||
| 116 | brahmairesearch/slx-v0.1 open weights, 0B | 74.5% | huggingface.co | Official leaderboard | ||
| 117 | sentence-transformers/all-MiniLM-L6-v2 open weights, 0B | 74.5% | huggingface.co | Official leaderboard | ||
| 118 | codefuse-ai/F2LLM-v2-160M open weights, 0.2B | 74.3% | huggingface.co | Official leaderboard | ||
| 119 | sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 open weights, 0.1B | 74% | huggingface.co | Official leaderboard | ||
| 120 | Mihaiii/Venusaur open weights, 0B | 73% | huggingface.co | Official leaderboard | ||
| 121 | Snowflake/snowflake-arctic-embed-m-v2.0 open weights, 0.3B | 73% | huggingface.co | Official leaderboard | ||
| 122 | Mihaiii/Wartortle open weights, 0B | 72.7% | huggingface.co | Official leaderboard | ||
| 123 | Mihaiii/Squirtle open weights, 0B | 72.7% | huggingface.co | Official leaderboard | ||
| 124 | manu/sentence_croissant_alpha_v0.4 open weights, 1.3B | 72.5% | huggingface.co | Official leaderboard | ||
| 125 | codefuse-ai/F2LLM-v2-330M open weights, 0.3B | 72.2% | huggingface.co | Official leaderboard | ||
| 126 | Omartificial-Intelligence-Space/Arabic-MiniLM-L12-v2-all-nli-triplet open weights, 0.1B | 72.1% | huggingface.co | Official leaderboard | ||
| 127 | Snowflake/snowflake-arctic-embed-m-v1.5 open weights, 0.1B | 72% | huggingface.co | Official leaderboard | ||
| 128 | Snowflake/snowflake-arctic-embed-l-v2.0 open weights, 0.6B | 72% | huggingface.co | Official leaderboard | ||
| 129 | sentence-transformers/LaBSE open weights, 0.5B | 71.9% | huggingface.co | Official leaderboard | ||
| 130 | cointegrated/LaBSE-en-ru open weights, 0.1B | 71.6% | huggingface.co | Official leaderboard | ||
| 131 | Mihaiii/gte-micro-v4 open weights, 0B | 71.6% | huggingface.co | Official leaderboard | ||
| 132 | Snowflake/snowflake-arctic-embed-s open weights, 0B | 71.5% | huggingface.co | Official leaderboard | ||
| 133 | ibm-granite/granite-embedding-278m-multilingual open weights, 0.3B | 71.4% | huggingface.co | Official leaderboard | ||
| 134 | Mihaiii/Bulbasaur open weights, 0B | 71.1% | huggingface.co | Official leaderboard | ||
| 135 | manu/sentence_croissant_alpha_v0.3 open weights, 1.3B | 71% | huggingface.co | Official leaderboard | ||
| 136 | Mihaiii/gte-micro open weights, 0B | 71% | huggingface.co | Official leaderboard | ||
| 137 | ibm-granite/granite-embedding-107m-multilingual open weights, 0.1B | 70.9% | huggingface.co | Official leaderboard | ||
| 138 | shibing624/text2vec-base-multilingual open weights, 0.1B | 70.9% | huggingface.co | Official leaderboard | ||
| 139 | hotchpotch/bekko-embedding-v1-a8m open weights, 0.1B | 70.7% | huggingface.co | Official leaderboard | ||
| 140 | codefuse-ai/F2LLM-v2-80M open weights, 0.1B | 70.5% | huggingface.co | Official leaderboard | ||
| 141 | manu/sentence_croissant_alpha_v0.2 open weights, 1.3B | 69.8% | huggingface.co | Official leaderboard | ||
| 142 | ibm-granite/granite-embedding-311m-multilingual-r2 open weights, 0.3B | 69.7% | huggingface.co | Official leaderboard | ||
| 143 | ibm-granite/granite-embedding-125m-english open weights, 0.1B | 69.6% | huggingface.co | Official leaderboard | ||
| 144 | McGill-NLP/LLM2Vec-Mistral-7B-Instruct-v2-mntp-unsup-simcse open weights, 7.2B | 69.4% | huggingface.co | Official leaderboard | ||
| 145 | Snowflake/snowflake-arctic-embed-m-long open weights, 0.1B | 69.2% | huggingface.co | Official leaderboard | ||
| 146 | Snowflake/snowflake-arctic-embed-l open weights, 0.3B | 69% | huggingface.co | Official leaderboard | ||
| 147 | hotchpotch/bekko-static-embedding-v1 open weights, 0.2B | 68.9% | huggingface.co | Official leaderboard | ||
| 148 | Gameselo/STS-multilingual-mpnet-base-v2 open weights, 0.3B | 68.7% | huggingface.co | Official leaderboard | ||
| 149 | Haon-Chen/speed-embedding-7b-instruct open weights, 7.1B | 68.4% | huggingface.co | Official leaderboard | ||
| 150 | izhx/udever-bloom-7b1 open weights | 68.4% | huggingface.co | Official leaderboard | ||
| 151 | sergeyzh/rubert-tiny-turbo open weights, 0B | 68% | huggingface.co | Official leaderboard | ||
| 152 | Snowflake/snowflake-arctic-embed-xs open weights, 0B | 67.8% | huggingface.co | Official leaderboard | ||
| 153 | ibm-granite/granite-embedding-97m-multilingual-r2 open weights, 0.1B | 67.6% | huggingface.co | Official leaderboard | ||
| 154 | Snowflake/snowflake-arctic-embed-m open weights, 0.1B | 67.1% | huggingface.co | Official leaderboard | ||
| 155 | bigscience/sgpt-bloom-7b1-msmarco open weights, 7.1B | 67% | huggingface.co | Official leaderboard | ||
| 156 | ibm-granite/granite-embedding-30m-english open weights, 0B | 66.6% | huggingface.co | Official leaderboard | ||
| 157 | cnmoro/static-nomic-384-pten-v2-st open weights, 0.1B | 66.1% | huggingface.co | Official leaderboard | ||
| 158 | izhx/udever-bloom-3b open weights, 3B | 66.1% | huggingface.co | Official leaderboard | ||
| 159 | izhx/udever-bloom-1b1 open weights, 1.1B | 64.8% | huggingface.co | Official leaderboard | ||
| 160 | minishlab/potion-base-8M open weights, 0B | 64.7% | huggingface.co | Official leaderboard | ||
| 161 | jinaai/jina-embeddings-v5-omni-small open weights, 1.6B | 63.4% | huggingface.co | Official leaderboard | ||
| 162 | jinaai/jina-embeddings-v5-text-small open weights, 0.6B | 63.4% | huggingface.co | Official leaderboard | ||
| 163 | deepvk/USER-base open weights, 0.4B | 62.9% | huggingface.co | Official leaderboard | ||
| 164 | cointegrated/rubert-tiny2 open weights, 0B | 62.6% | huggingface.co | Official leaderboard | ||
| 165 | minishlab/potion-multilingual-128M open weights, 0.1B | 62.4% | huggingface.co | Official leaderboard | ||
| 166 | minishlab/potion-base-4M open weights, 0B | 61.9% | huggingface.co | Official leaderboard | ||
| 167 | jinaai/jina-embedding-b-en-v1 open weights, 0.1B | 61.9% | huggingface.co | Official leaderboard | ||
| 168 | consciousAI/cai-lunaris-text-embeddings open weights, 0.3B | 61.7% | huggingface.co | Official leaderboard | ||
| 169 | cointegrated/rubert-tiny open weights, 0B | 60.6% | huggingface.co | Official leaderboard | ||
| 170 | minishlab/potion-base-2M open weights, 0B | 59% | huggingface.co | Official leaderboard | ||
| 171 | jinaai/jina-embedding-s-en-v1 open weights, 0B | 58.4% | huggingface.co | Official leaderboard | ||
| 172 | izhx/udever-bloom-560m open weights, 0.6B | 58.4% | huggingface.co | Official leaderboard | ||
| 173 | ai-forever/sbert_large_nlu_ru open weights, 0.4B | 57.1% | huggingface.co | Official leaderboard | ||
| 174 | minishlab/M2V_base_output open weights, 0B | 56.4% | huggingface.co | Official leaderboard | ||
| 175 | minishlab/M2V_base_glove_subword open weights, 0.1B | 56.3% | huggingface.co | Official leaderboard | ||
| 176 | Jaume/gemma-2b-embeddings open weights, 2.5B | 56.2% | huggingface.co | Official leaderboard | ||
| 177 | silma-ai/silma-embeddding-matryoshka-v0.1 open weights, 0.1B | 55.9% | huggingface.co | Official leaderboard | ||
| 178 | DeepPavlov/distilrubert-small-cased-conversational open weights, 0.1B | 55.3% | huggingface.co | Official leaderboard | ||
| 179 | ai-forever/sbert_large_mt_nlu_ru open weights, 0.4B | 54.8% | huggingface.co | Official leaderboard | ||
| 180 | jinaai/jina-embeddings-v2-small-en open weights, 0B | 54.8% | huggingface.co | Official leaderboard | ||
| 181 | minishlab/M2V_base_glove open weights, 0.1B | 53.9% | huggingface.co | Official leaderboard | ||
| 182 | DeepPavlov/rubert-base-cased open weights, 1.3B | 53.5% | huggingface.co | Official leaderboard | ||
| 183 | Omartificial-Intelligence-Space/Marbert-all-nli-triplet-Matryoshka open weights, 0.2B | 52.8% | huggingface.co | Official leaderboard | ||
| 184 | Omartificial-Intelligence-Space/Arabic-mpnet-base-all-nli-triplet open weights, 0.1B | 52.7% | huggingface.co | Official leaderboard | ||
| 185 | sentence-transformers/static-similarity-mrl-multilingual-v1 open weights, 0.1B | 52.2% | huggingface.co | Official leaderboard | ||
| 186 | deepvk/deberta-v1-base open weights, 0.1B | 50.3% | huggingface.co | Official leaderboard | ||
| 187 | DeepPavlov/rubert-base-cased-sentence open weights, 0.1B | 48.8% | huggingface.co | Official leaderboard | ||
| 188 | jinaai/jina-embeddings-v5-omni-nano open weights, 1B | 48.6% | huggingface.co | Official leaderboard | ||
| 189 | jinaai/jina-embeddings-v5-text-nano open weights, 0.2B | 48.6% | huggingface.co | Official leaderboard | ||
| 190 | Omartificial-Intelligence-Space/Arabert-all-nli-triplet-Matryoshka open weights, 0.1B | 46% | huggingface.co | Official leaderboard | ||
| 191 | malenia1/ternary-weight-embedding open weights, 0.1B | 44.3% | huggingface.co | Official leaderboard | ||
| 192 | Hum-Works/lodestone-base-4096-v1 open weights, 0.1B | 44% | huggingface.co | Official leaderboard | ||
| 193 | jinaai/jina-embeddings-v2-base-en open weights, 0.1B | 37.5% | huggingface.co | Official leaderboard |
| # | Model | Score | Setting | Date | Link | Source |
|---|---|---|---|---|---|---|
| 1 | | 95.2% | Jun 2025 | huggingface.co | Official leaderboard | |
| 2 | | 93.9% | Jun 2025 | huggingface.co | Official leaderboard | |
| 3 | | 90.6% | Jun 2025 | huggingface.co | Official leaderboard | |
| 4 | | 84.5% | Mar 2026 | ai.google.dev | Official leaderboard | |
| 5 | | 82.2% | Oct 2026 | huggingface.co | Official leaderboard |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: MTEB’s leaderboard
Qwen3-Embedding-8B on the official leaderboard passed 85% in June 2025
That was 143 months after its release. All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: MTEB’s leaderboard
No lab model card reports it yet
We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.
More in Law, finance and medicine
- MedXpertQA-MM In use Models answer expert-level medical exam questions that combine images with clinical records and test results. Scoring is accuracy.
Qwen 3.8 Max 80.4%
- HealthBench Professional In use 525 physician-authored tasks from real clinician chats (care consult, documentation, research) with physician-adjudicated rubrics. Claude Sonnet 5.5 69.2%
- HealthBench In use 5,000 realistic health conversations graded against physician-written rubrics. A length-adjusted variant penalizes verbosity. GPT-5 67.2%
- FinSearchComp In use Agents search the web to fetch live financial data, look up history, and run multi-step investigations, across 635 expert-written questions. Scored by answer accuracy.
Ling-3.1-flash 81.7%
- KorMedMCQA In use Models answer 7,469 multiple-choice questions from Korean licensing exams for doctors, nurses, pharmacists and dentists, held from 2012 to 2024. o1-preview 92.7%
- Harvey LAB-AA v1.1 In use Artificial Analysis's run of Harvey's Legal Agent Benchmark on Harvey's newer private set of 120 tasks across 24 practice areas. A deliverable with a material hallucination scores zero, and the headline is the share of judges who find every rubric criterion passed. GPT-6.2 Astra 15%
Data audit
All 9 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 3 pass 2 notes
- Pass Independent runs Scores from the official leaderboard (193 entries).
- Pass Models scored 5 models we track, plus 188 other entries on its leaderboard.
- Pass Newest score The newest is from October 2026, for EmbeddingGemma 2.
- Note Frontier models None of its models are on the capabilities index.
- Note Headroom Saturated. The best is 95.2%, past 85% since June 2025.
Leaderboard import 3 pass
- Pass Importer We read the board on MTEB: 5 rows for models we track and 188 other entries at the last read.
- Pass Last read November 20th, 2026.
- Pass Read worked The last read worked.
Consistency 1 pass 1 note
- Note Lab claims No model has both a lab number and an independent run.
- Pass Known issues No published audit found problems.