FollowIR
Models rank documents in response to a search instruction. The benchmark tests whether revising the instruction changes the ranking of the affected documents.
- Made by
- Orion Weller and colleagues
- Released
- March 2024
- Kind
- Questions that need search
- Level
- School
- Scored
- Checked automatically
- Answers
- Prediction
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Single turn
- Items from
- Real work and use
- Refresh
- One fixed set
- Run by
- Anyone
- Last model added
- October 2026
- Scores refreshed
- November 20th, 2026
jhu-clsp/FollowIR-7B tops the leaderboard with 0.12 Qwen3-Embedding-4B leads with 0.12 among models released by October 2026
Best score per entry from MTEB’s leaderboard, read on November 20th, 2026. Mean pairwise mean reciprocal rank across Robust04, News21 and Core17, on the MTEB scale from -1 to 1. 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-4B, at 0.12. 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
- 0.12 jhu-clsp/FollowIR-7B
- 0.12
Qwen3-Embedding-4B
- 0.11 nvidia/llama-embed-nemotron-8b
- 0.10
Qwen3-Embedding-8B
- 0.09 Octen/Octen-Embedding-8B
- 0.07 Mira190/Euler-Legal-Embedding-V1
- 0.07 mongodb/voyage-3.5
- 0.06 google/embeddinggemma-300m
- 0.05 tencent/KaLM-Embedding-Gemma3-12B-2511
- 0.05 microsoft/harrier-oss-v1-27b
- 0.05 Alibaba-NLP/gte-Qwen1.5-7B-instruct
- 0.05 google/gemini-embedding-001
- 0.05
Qwen3-Embedding-0.6B
- 0.05 Alibaba-NLP/gte-Qwen2-7B-instruct
- 0.05 google/flan-t5-large
- 0.05 zeroentropy/zembed-1
- 0.04 google/text-multilingual-embedding-002
- 0.04 mongodb/voyage-3-large
- 0.03 GritLM/GritLM-7B
- 0.03 nvidia/NV-Embed-v1
- 0.03 infly/inf-retriever-v1
- 0.03 castorini/monot5-3b-msmarco-10k
- 0.02 GritLM/GritLM-8x7B
- 0.02 google/text-embedding-004
- 0.02 codefuse-ai/F2LLM-v2-4B
- 0.02 ai-sage/Giga-Embeddings-instruct-3B-0826
- 0.02 IEITYuan/Yuan-embedding-2.0-en
- 0.01 codefuse-ai/F2LLM-v2-0.6B
- 0.01 omarelshehy/arabic-english-sts-matryoshka
- 0.01 jinaai/jina-embeddings-v5-omni-small
- 0.01 jinaai/jina-embeddings-v5-text-small
- 0.01 mongodb/voyage-3
- 0.01 BidirLM/BidirLM-0.6B-Embedding
- 0.01 codefuse-ai/F2LLM-4B
- 0.01 Omartificial-Intelligence-Space/Arabert-all-nli-triplet-Matryoshka
- 0.01 nvidia/NV-Embed-v2
- 0.01 BidirLM/BidirLM-Omni-2.5B-Embedding
- 0.01 minishlab/M2V_base_glove_subword
- 0.01 Linq-AI-Research/Linq-Embed-Mistral
- 0.01 malenia1/ternary-weight-embedding
- 0.01 ai-sage/Giga-Embeddings-instruct-10B-A1.8B-0826
- 0.01 codefuse-ai/F2LLM-v2-8B
- 0.01 microsoft/harrier-oss-v1-0.6b
- 0.01 DeepPavlov/rubert-base-cased
- 0.01 Alibaba-NLP/gte-Qwen2-1.5B-instruct
- 0.01 Jaume/gemma-2b-embeddings
- 0.01 google/flan-t5-base
- 0.01 codefuse-ai/F2LLM-v2-14B
- 0.01 minishlab/potion-base-4M
- 0.01 minishlab/potion-base-2M
- 0.01 silma-ai/silma-embeddding-matryoshka-v0.1
- 0.01 ai-forever/sbert_large_nlu_ru
- 0.01 codefuse-ai/F2LLM-v2-1.7B
- 0.00 BidirLM/BidirLM-1.7B-Embedding
- 0.00 codefuse-ai/F2LLM-1.7B
- 0.00 minishlab/potion-base-32M
- 0.00 VPLabs/SearchMap_Preview
- 0.00 mteb/baseline-random-encoder
- 0.00 DeepPavlov/rubert-base-cased-sentence
- 0.00 NovaSearch/jasper_en_vision_language_v1
- 0.00 minishlab/potion-base-8M
- 0.00 NovaSearch/stella_en_1.5B_v5
- 0.00 Salesforce/SFR-Embedding-Mistral
- 0.00 infly/inf-retriever-v1-1.5b
- 0.00 jinaai/jina-embeddings-v5-omni-nano
- 0.00 jinaai/jina-embeddings-v5-text-nano
- -0.00 Bytedance/Seed1.6-embedding-1215
- -0.00 manu/sentence_croissant_alpha_v0.4
- -0.00 cointegrated/rubert-tiny2
- -0.00 Haon-Chen/speed-embedding-7b-instruct
- -0.00 minishlab/M2V_base_output
- -0.00 Cohere/Cohere-embed-english-v3.0
- -0.00 Omartificial-Intelligence-Space/Marbert-all-nli-triplet-Matryoshka
- -0.00 BidirLM/BidirLM-1B-Embedding
- -0.00 manu/sentence_croissant_alpha_v0.2
- -0.00 intfloat/multilingual-e5-large-instruct
- -0.00 minishlab/M2V_base_glove
- -0.00 KaLM-Embedding/KaLM-embedding-multilingual-mini-instruct-v2.5
- -0.00 microsoft/harrier-oss-v1-270m
- -0.00 ai-forever/sbert_large_mt_nlu_ru
- -0.01 ICT-TIME-and-Querit/BOOM_4B_v1
- -0.01 DeepPavlov/distilrubert-small-cased-conversational
- -0.01
EmbeddingGemma 2
- -0.01 intfloat/e5-mistral-7b-instruct
- -0.01 NovaSearch/stella_en_400M_v5
- -0.01 Alibaba-NLP/gte-multilingual-base
- -0.01 izhx/udever-bloom-3b
- -0.01 jinaai/jina-embeddings-v2-small-en
- -0.01 sentence-transformers/all-MiniLM-L12-v2
- -0.01 infgrad/Jasper-Token-Compression-600M
- -0.01 izhx/udever-bloom-560m
- -0.01 McGill-NLP/LLM2Vec-Mistral-7B-Instruct-v2-mntp-supervised
- -0.01 ICT-TIME-and-Querit/ICT-TIME-and-Querit-embedding-v1
- -0.01 cointegrated/rubert-tiny
- -0.01 intfloat/e5-large-v2
- -0.01 Omartificial-Intelligence-Space/Arabic-all-nli-triplet-Matryoshka
- -0.01 McGill-NLP/LLM2Vec-Mistral-7B-Instruct-v2-mntp-unsup-simcse
- -0.01 izhx/udever-bloom-1b1
- -0.01 sentence-transformers/paraphrase-multilingual-mpnet-base-v2
- -0.01 mongodb/voyage-3-lite
- -0.01 manu/sentence_croissant_alpha_v0.3
- -0.01 Omartificial-Intelligence-Space/Arabic-MiniLM-L12-v2-all-nli-triplet
- -0.01 sentence-transformers/static-similarity-mrl-multilingual-v1
- -0.01 ibm-granite/granite-embedding-125m-english
- -0.01 thenlper/gte-large
- -0.01 prdev/mini-gte
- -0.01 sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
- -0.01 izhx/udever-bloom-7b1
- -0.01 jinaai/jina-embeddings-v3
- -0.01 Cohere/Cohere-embed-english-light-v3.0
- -0.01 intfloat/e5-small
- -0.01 consciousAI/cai-lunaris-text-embeddings
- -0.01 Mihaiii/Venusaur
- -0.01 Snowflake/snowflake-arctic-embed-l
- -0.01 HIT-TMG/KaLM-embedding-multilingual-mini-v1
- -0.02 Mihaiii/Wartortle
- -0.02 thenlper/gte-small
- -0.02 cnmoro/static-nomic-384-pten-v2-st
- -0.02 codefuse-ai/F2LLM-v2-80M
- -0.02 jinaai/jina-embeddings-v2-base-en
- -0.02 codefuse-ai/F2LLM-v2-330M
- -0.02 hotchpotch/bekko-static-embedding-v1
- -0.02 Mihaiii/Squirtle
- -0.02 abhinand/MedEmbed-small-v0.1
- -0.02 castorini/monot5-base-msmarco-10k
- -0.02 ibm-granite/granite-embedding-278m-multilingual
- -0.02 Omartificial-Intelligence-Space/Arabic-labse-Matryoshka
- -0.02 Mihaiii/gte-micro
- -0.02 Salesforce/SFR-Embedding-2_R
- -0.02 avsolatorio/GIST-large-Embedding-v0
- -0.02 nomic-ai/nomic-embed-text-v1.5
- -0.02 BAAI/bge-small-en-v1.5
- -0.02 Cohere/Cohere-embed-multilingual-v3.0
- -0.02 Snowflake/snowflake-arctic-embed-m-long
- -0.02 avsolatorio/GIST-all-MiniLM-L6-v2
- -0.02 mixedbread-ai/mxbai-embed-large-v1
- -0.02 deepvk/USER-base
- -0.02 Gameselo/STS-multilingual-mpnet-base-v2
- -0.02 ibm-granite/granite-embedding-97m-multilingual-r2
- -0.02 minishlab/potion-multilingual-128M
- -0.02 WhereIsAI/UAE-Large-V1
- -0.02 nomic-ai/nomic-embed-text-v1-unsupervised
- -0.02 Mihaiii/Ivysaur
- -0.02 BidirLM/BidirLM-270M-Embedding
- -0.02 sergeyzh/rubert-tiny-turbo
- -0.02 BAAI/bge-large-en-v1.5
- -0.02 intfloat/e5-large
- -0.02 Snowflake/snowflake-arctic-embed-m
- -0.02 Snowflake/snowflake-arctic-embed-xs
- -0.02 BAAI/bge-large-en
- -0.02 deepvk/deberta-v1-base
- -0.02 openai/text-embedding-3-small
- -0.02 ibm-granite/granite-embedding-311m-multilingual-r2
- -0.02 Cohere/Cohere-embed-multilingual-light-v3.0
- -0.02 intfloat/multilingual-e5-small
- -0.02 thenlper/gte-base
- -0.02 Snowflake/snowflake-arctic-embed-l-v2.0
- -0.03 manu/bge-m3-custom-fr
- -0.03 aari1995/German_Semantic_STS_V2
- -0.03 avsolatorio/NoInstruct-small-Embedding-v0
- -0.03 HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1
- -0.03 deepvk/USER-bge-m3
- -0.03 intfloat/multilingual-e5-base
- -0.03 openai/text-embedding-3-large
- -0.03 avsolatorio/GIST-small-Embedding-v0
- -0.03 ibm-granite/granite-embedding-30m-english
- -0.03 deepfile/embedder-100p
- -0.03 MongoDB/mdbr-leaf-mt
- -0.03 brahmairesearch/slx-v0.1
- -0.03 Omartificial-Intelligence-Space/Arabic-mpnet-base-all-nli-triplet
- -0.03 sentence-transformers/all-MiniLM-L6-v2
- -0.03 intfloat/e5-small-v2
- -0.03 dwzhu/e5-base-4k
- -0.03 mteb/baseline-bm25s
- -0.03 ibm-granite/granite-embedding-107m-multilingual
- -0.03 sentence-transformers/LaBSE
- -0.03 bigscience/sgpt-bloom-7b1-msmarco
- -0.03 Lajavaness/bilingual-embedding-large
- -0.03 intfloat/multilingual-e5-large
- -0.03 sentence-transformers/all-mpnet-base-v2
- -0.03 Snowflake/snowflake-arctic-embed-s
- -0.03 BAAI/bge-base-en
- -0.03 BAAI/bge-m3
- -0.03 jinaai/jina-embedding-s-en-v1
- -0.03 Mihaiii/Bulbasaur
- -0.03 nomic-ai/nomic-embed-text-v1
- -0.03 infgrad/stella-base-en-v2
- -0.03 sdadas/mmlw-e5-base
- -0.03 hotchpotch/bekko-embedding-v1-a8m
- -0.03 Snowflake/snowflake-arctic-embed-m-v2.0
- -0.03 avsolatorio/GIST-Embedding-v0
- -0.03 Lajavaness/bilingual-embedding-small
- -0.03 codefuse-ai/F2LLM-v2-160M
- -0.03 sdadas/mmlw-e5-large
- -0.03 Snowflake/snowflake-arctic-embed-m-v1.5
- -0.03 sdadas/mmlw-roberta-base
- -0.03 OrdalieTech/Solon-embeddings-large-0.1
- -0.03 intfloat/e5-base
- -0.04 sergeyzh/LaBSE-ru-turbo
- -0.04 ai-forever/ru-en-RoSBERTa
- -0.04 sdadas/mmlw-roberta-large
- -0.04 cointegrated/LaBSE-en-ru
- -0.04 nomic-ai/nomic-embed-text-v1-ablated
- -0.04 Mihaiii/gte-micro-v4
- -0.04 Lajavaness/bilingual-embedding-base
- -0.04 intfloat/e5-base-v2
- -0.04 nomic-ai/nomic-embed-text-v2-moe
- -0.04 shibing624/text2vec-base-multilingual
- -0.04 BAAI/bge-base-en-v1.5
- -0.04 jinaai/jina-embedding-b-en-v1
- -0.04 sdadas/mmlw-e5-small
- -0.05 hotchpotch/bekko-embedding-v1-a25m
- 1 jhu-clsp/FollowIR-7B 0.12
- 2
Qwen3-Embedding-4B 0.12
- 3 nvidia/llama-embed-nemotron-8b 0.11
- 4
Qwen3-Embedding-8B 0.10
- 5 Octen/Octen-Embedding-8B 0.09
- 6 Mira190/Euler-Legal-Embedding-V1 0.07
- 7 mongodb/voyage-3.5 0.07
- 8 google/embeddinggemma-300m 0.06
- 9 tencent/KaLM-Embedding-Gemma3-12B-2511 0.05
- 10 microsoft/harrier-oss-v1-27b 0.05
- 11 Alibaba-NLP/gte-Qwen1.5-7B-instruct 0.05
- 12 google/gemini-embedding-001 0.05
- 13
Qwen3-Embedding-0.6B 0.05
- 14 Alibaba-NLP/gte-Qwen2-7B-instruct 0.05
- 15 google/flan-t5-large 0.05
- 16 zeroentropy/zembed-1 0.05
- 17 google/text-multilingual-embedding-002 0.04
- 18 mongodb/voyage-3-large 0.04
- 19 GritLM/GritLM-7B 0.03
- 20 nvidia/NV-Embed-v1 0.03
- 21 infly/inf-retriever-v1 0.03
- 22 castorini/monot5-3b-msmarco-10k 0.03
- 23 GritLM/GritLM-8x7B 0.02
- 24 google/text-embedding-004 0.02
- 25 codefuse-ai/F2LLM-v2-4B 0.02
- 26 ai-sage/Giga-Embeddings-instruct-3B-0826 0.02
- 27 IEITYuan/Yuan-embedding-2.0-en 0.02
- 28 codefuse-ai/F2LLM-v2-0.6B 0.01
- 29 omarelshehy/arabic-english-sts-matryoshka 0.01
- 30 jinaai/jina-embeddings-v5-omni-small 0.01
- 31 jinaai/jina-embeddings-v5-text-small 0.01
- 32 mongodb/voyage-3 0.01
- 33 BidirLM/BidirLM-0.6B-Embedding 0.01
- 34 codefuse-ai/F2LLM-4B 0.01
- 35 Omartificial-Intelligence-Space/Arabert-all-nli-triplet-Matryoshka 0.01
- 36 nvidia/NV-Embed-v2 0.01
- 37 BidirLM/BidirLM-Omni-2.5B-Embedding 0.01
- 38 minishlab/M2V_base_glove_subword 0.01
- 39 Linq-AI-Research/Linq-Embed-Mistral 0.01
- 40 malenia1/ternary-weight-embedding 0.01
- 41 ai-sage/Giga-Embeddings-instruct-10B-A1.8B-0826 0.01
- 42 codefuse-ai/F2LLM-v2-8B 0.01
- 43 microsoft/harrier-oss-v1-0.6b 0.01
- 44 DeepPavlov/rubert-base-cased 0.01
- 45 Alibaba-NLP/gte-Qwen2-1.5B-instruct 0.01
- 46 Jaume/gemma-2b-embeddings 0.01
- 47 google/flan-t5-base 0.01
- 48 codefuse-ai/F2LLM-v2-14B 0.01
- 49 minishlab/potion-base-4M 0.01
- 50 minishlab/potion-base-2M 0.01
- 51 silma-ai/silma-embeddding-matryoshka-v0.1 0.01
- 52 ai-forever/sbert_large_nlu_ru 0.01
- 53 codefuse-ai/F2LLM-v2-1.7B 0.01
- 54 BidirLM/BidirLM-1.7B-Embedding 0.00
- 55 codefuse-ai/F2LLM-1.7B 0.00
- 56 minishlab/potion-base-32M 0.00
- 57 VPLabs/SearchMap_Preview 0.00
- 58 mteb/baseline-random-encoder 0.00
- 59 DeepPavlov/rubert-base-cased-sentence 0.00
- 60 NovaSearch/jasper_en_vision_language_v1 0.00
- 61 minishlab/potion-base-8M 0.00
- 62 NovaSearch/stella_en_1.5B_v5 0.00
- 63 Salesforce/SFR-Embedding-Mistral 0.00
- 64 infly/inf-retriever-v1-1.5b 0.00
- 65 jinaai/jina-embeddings-v5-omni-nano 0.00
- 66 jinaai/jina-embeddings-v5-text-nano 0.00
- 67 Bytedance/Seed1.6-embedding-1215 -0.00
- 68 manu/sentence_croissant_alpha_v0.4 -0.00
- 69 cointegrated/rubert-tiny2 -0.00
- 70 Haon-Chen/speed-embedding-7b-instruct -0.00
- 71 minishlab/M2V_base_output -0.00
- 72 Cohere/Cohere-embed-english-v3.0 -0.00
- 73 Omartificial-Intelligence-Space/Marbert-all-nli-triplet-Matryoshka -0.00
- 74 BidirLM/BidirLM-1B-Embedding -0.00
- 75 manu/sentence_croissant_alpha_v0.2 -0.00
- 76 intfloat/multilingual-e5-large-instruct -0.00
- 77 minishlab/M2V_base_glove -0.00
- 78 KaLM-Embedding/KaLM-embedding-multilingual-mini-instruct-v2.5 -0.00
- 79 microsoft/harrier-oss-v1-270m -0.00
- 80 ai-forever/sbert_large_mt_nlu_ru -0.00
- 81 ICT-TIME-and-Querit/BOOM_4B_v1 -0.01
- 82 DeepPavlov/distilrubert-small-cased-conversational -0.01
- 83
EmbeddingGemma 2 -0.01
- 84 intfloat/e5-mistral-7b-instruct -0.01
- 85 NovaSearch/stella_en_400M_v5 -0.01
- 86 Alibaba-NLP/gte-multilingual-base -0.01
- 87 izhx/udever-bloom-3b -0.01
- 88 jinaai/jina-embeddings-v2-small-en -0.01
- 89 sentence-transformers/all-MiniLM-L12-v2 -0.01
- 90 infgrad/Jasper-Token-Compression-600M -0.01
- 91 izhx/udever-bloom-560m -0.01
- 92 McGill-NLP/LLM2Vec-Mistral-7B-Instruct-v2-mntp-supervised -0.01
- 93 ICT-TIME-and-Querit/ICT-TIME-and-Querit-embedding-v1 -0.01
- 94 cointegrated/rubert-tiny -0.01
- 95 intfloat/e5-large-v2 -0.01
- 96 Omartificial-Intelligence-Space/Arabic-all-nli-triplet-Matryoshka -0.01
- 97 McGill-NLP/LLM2Vec-Mistral-7B-Instruct-v2-mntp-unsup-simcse -0.01
- 98 izhx/udever-bloom-1b1 -0.01
- 99 sentence-transformers/paraphrase-multilingual-mpnet-base-v2 -0.01
- 100 mongodb/voyage-3-lite -0.01
- 101 manu/sentence_croissant_alpha_v0.3 -0.01
- 102 Omartificial-Intelligence-Space/Arabic-MiniLM-L12-v2-all-nli-triplet -0.01
- 103 sentence-transformers/static-similarity-mrl-multilingual-v1 -0.01
- 104 ibm-granite/granite-embedding-125m-english -0.01
- 105 thenlper/gte-large -0.01
- 106 prdev/mini-gte -0.01
- 107 sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 -0.01
- 108 izhx/udever-bloom-7b1 -0.01
- 109 jinaai/jina-embeddings-v3 -0.01
- 110 Cohere/Cohere-embed-english-light-v3.0 -0.01
- 111 intfloat/e5-small -0.01
- 112 consciousAI/cai-lunaris-text-embeddings -0.01
- 113 Mihaiii/Venusaur -0.01
- 114 Snowflake/snowflake-arctic-embed-l -0.01
- 115 HIT-TMG/KaLM-embedding-multilingual-mini-v1 -0.01
- 116 Mihaiii/Wartortle -0.02
- 117 thenlper/gte-small -0.02
- 118 cnmoro/static-nomic-384-pten-v2-st -0.02
- 119 codefuse-ai/F2LLM-v2-80M -0.02
- 120 jinaai/jina-embeddings-v2-base-en -0.02
- 121 codefuse-ai/F2LLM-v2-330M -0.02
- 122 hotchpotch/bekko-static-embedding-v1 -0.02
- 123 Mihaiii/Squirtle -0.02
- 124 abhinand/MedEmbed-small-v0.1 -0.02
- 125 castorini/monot5-base-msmarco-10k -0.02
- 126 ibm-granite/granite-embedding-278m-multilingual -0.02
- 127 Omartificial-Intelligence-Space/Arabic-labse-Matryoshka -0.02
- 128 Mihaiii/gte-micro -0.02
- 129 Salesforce/SFR-Embedding-2_R -0.02
- 130 avsolatorio/GIST-large-Embedding-v0 -0.02
- 131 nomic-ai/nomic-embed-text-v1.5 -0.02
- 132 BAAI/bge-small-en-v1.5 -0.02
- 133 Cohere/Cohere-embed-multilingual-v3.0 -0.02
- 134 Snowflake/snowflake-arctic-embed-m-long -0.02
- 135 avsolatorio/GIST-all-MiniLM-L6-v2 -0.02
- 136 mixedbread-ai/mxbai-embed-large-v1 -0.02
- 137 deepvk/USER-base -0.02
- 138 Gameselo/STS-multilingual-mpnet-base-v2 -0.02
- 139 ibm-granite/granite-embedding-97m-multilingual-r2 -0.02
- 140 minishlab/potion-multilingual-128M -0.02
- 141 WhereIsAI/UAE-Large-V1 -0.02
- 142 nomic-ai/nomic-embed-text-v1-unsupervised -0.02
- 143 Mihaiii/Ivysaur -0.02
- 144 BidirLM/BidirLM-270M-Embedding -0.02
- 145 sergeyzh/rubert-tiny-turbo -0.02
- 146 BAAI/bge-large-en-v1.5 -0.02
- 147 intfloat/e5-large -0.02
- 148 Snowflake/snowflake-arctic-embed-m -0.02
- 149 Snowflake/snowflake-arctic-embed-xs -0.02
- 150 BAAI/bge-large-en -0.02
- 151 deepvk/deberta-v1-base -0.02
- 152 openai/text-embedding-3-small -0.02
- 153 ibm-granite/granite-embedding-311m-multilingual-r2 -0.02
- 154 Cohere/Cohere-embed-multilingual-light-v3.0 -0.02
- 155 intfloat/multilingual-e5-small -0.02
- 156 thenlper/gte-base -0.02
- 157 Snowflake/snowflake-arctic-embed-l-v2.0 -0.02
- 158 manu/bge-m3-custom-fr -0.03
- 159 aari1995/German_Semantic_STS_V2 -0.03
- 160 avsolatorio/NoInstruct-small-Embedding-v0 -0.03
- 161 HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1 -0.03
- 162 deepvk/USER-bge-m3 -0.03
- 163 intfloat/multilingual-e5-base -0.03
- 164 openai/text-embedding-3-large -0.03
- 165 avsolatorio/GIST-small-Embedding-v0 -0.03
- 166 ibm-granite/granite-embedding-30m-english -0.03
- 167 deepfile/embedder-100p -0.03
- 168 MongoDB/mdbr-leaf-mt -0.03
- 169 brahmairesearch/slx-v0.1 -0.03
- 170 Omartificial-Intelligence-Space/Arabic-mpnet-base-all-nli-triplet -0.03
- 171 sentence-transformers/all-MiniLM-L6-v2 -0.03
- 172 intfloat/e5-small-v2 -0.03
- 173 dwzhu/e5-base-4k -0.03
- 174 mteb/baseline-bm25s -0.03
- 175 ibm-granite/granite-embedding-107m-multilingual -0.03
- 176 sentence-transformers/LaBSE -0.03
- 177 bigscience/sgpt-bloom-7b1-msmarco -0.03
- 178 Lajavaness/bilingual-embedding-large -0.03
- 179 intfloat/multilingual-e5-large -0.03
- 180 sentence-transformers/all-mpnet-base-v2 -0.03
- 181 Snowflake/snowflake-arctic-embed-s -0.03
- 182 BAAI/bge-base-en -0.03
- 183 BAAI/bge-m3 -0.03
- 184 jinaai/jina-embedding-s-en-v1 -0.03
- 185 Mihaiii/Bulbasaur -0.03
- 186 nomic-ai/nomic-embed-text-v1 -0.03
- 187 infgrad/stella-base-en-v2 -0.03
- 188 sdadas/mmlw-e5-base -0.03
- 189 hotchpotch/bekko-embedding-v1-a8m -0.03
- 190 Snowflake/snowflake-arctic-embed-m-v2.0 -0.03
- 191 avsolatorio/GIST-Embedding-v0 -0.03
- 192 Lajavaness/bilingual-embedding-small -0.03
- 193 codefuse-ai/F2LLM-v2-160M -0.03
- 194 sdadas/mmlw-e5-large -0.03
- 195 Snowflake/snowflake-arctic-embed-m-v1.5 -0.03
- 196 sdadas/mmlw-roberta-base -0.03
- 197 OrdalieTech/Solon-embeddings-large-0.1 -0.03
- 198 intfloat/e5-base -0.03
- 199 sergeyzh/LaBSE-ru-turbo -0.04
- 200 ai-forever/ru-en-RoSBERTa -0.04
- 201 sdadas/mmlw-roberta-large -0.04
- 202 cointegrated/LaBSE-en-ru -0.04
- 203 nomic-ai/nomic-embed-text-v1-ablated -0.04
- 204 Mihaiii/gte-micro-v4 -0.04
- 205 Lajavaness/bilingual-embedding-base -0.04
- 206 intfloat/e5-base-v2 -0.04
- 207 nomic-ai/nomic-embed-text-v2-moe -0.04
- 208 shibing624/text2vec-base-multilingual -0.04
- 209 BAAI/bge-base-en-v1.5 -0.04
- 210 jinaai/jina-embedding-b-en-v1 -0.04
- 211 sdadas/mmlw-e5-small -0.04
- 212 hotchpotch/bekko-embedding-v1-a25m -0.05
Source: MTEB’s leaderboard
- 1
Qwen3-Embedding-4B 0.12
- 2
Qwen3-Embedding-8B 0.10
- 3
Qwen3-Embedding-0.6B 0.05
- 4
EmbeddingGemma 2 -0.01
Source: MTEB’s leaderboard
| # | Entry | Score | Setting | Date | Link | Source |
|---|---|---|---|---|---|---|
| 1 | jhu-clsp/FollowIR-7B open weights, 7.1B | 0.12 | huggingface.co | Official leaderboard | ||
| 2 | | 0.12 | Jun 2025 | huggingface.co | Official leaderboard | |
| 3 | nvidia/llama-embed-nemotron-8b open weights, 7.5B | 0.11 | huggingface.co | Official leaderboard | ||
| 4 | | 0.10 | Jun 2025 | huggingface.co | Official leaderboard | |
| 5 | Octen/Octen-Embedding-8B open weights, 7.6B | 0.09 | huggingface.co | Official leaderboard | ||
| 6 | Mira190/Euler-Legal-Embedding-V1 open weights, 7.6B | 0.07 | huggingface.co | Official leaderboard | ||
| 7 | mongodb/voyage-3.5 closed weights | 0.07 | blog.voyageai.com | Official leaderboard | ||
| 8 | google/embeddinggemma-300m open weights, 0.3B | 0.06 | ai.google.dev | Official leaderboard | ||
| 9 | tencent/KaLM-Embedding-Gemma3-12B-2511 open weights, 11.8B | 0.05 | huggingface.co | Official leaderboard | ||
| 10 | microsoft/harrier-oss-v1-27b open weights, 27B | 0.05 | huggingface.co | Official leaderboard | ||
| 11 | Alibaba-NLP/gte-Qwen1.5-7B-instruct open weights, 7.1B | 0.05 | huggingface.co | Official leaderboard | ||
| 12 | google/gemini-embedding-001 closed weights | 0.05 | ai.google.dev | Official leaderboard | ||
| 13 | | 0.05 | Jun 2025 | huggingface.co | Official leaderboard | |
| 14 | Alibaba-NLP/gte-Qwen2-7B-instruct open weights, 7.1B | 0.05 | huggingface.co | Official leaderboard | ||
| 15 | google/flan-t5-large open weights, 0.8B | 0.05 | huggingface.co | Official leaderboard | ||
| 16 | zeroentropy/zembed-1 open weights, 4B | 0.05 | huggingface.co | Official leaderboard | ||
| 17 | google/text-multilingual-embedding-002 closed weights | 0.04 | cloud.google.com | Official leaderboard | ||
| 18 | mongodb/voyage-3-large closed weights | 0.04 | blog.voyageai.com | Official leaderboard | ||
| 19 | GritLM/GritLM-7B open weights, 7.2B | 0.03 | huggingface.co | Official leaderboard | ||
| 20 | nvidia/NV-Embed-v1 open weights, 7.9B | 0.03 | huggingface.co | Official leaderboard | ||
| 21 | infly/inf-retriever-v1 open weights, 7.1B | 0.03 | huggingface.co | Official leaderboard | ||
| 22 | castorini/monot5-3b-msmarco-10k open weights, 3B | 0.03 | huggingface.co | Official leaderboard | ||
| 23 | GritLM/GritLM-8x7B open weights, 57.9B | 0.02 | huggingface.co | Official leaderboard | ||
| 24 | google/text-embedding-004 closed weights | 0.02 | cloud.google.com | Official leaderboard | ||
| 25 | codefuse-ai/F2LLM-v2-4B open weights, 4B | 0.02 | huggingface.co | Official leaderboard | ||
| 26 | ai-sage/Giga-Embeddings-instruct-3B-0826 open weights, 3.2B | 0.02 | huggingface.co | Official leaderboard | ||
| 27 | IEITYuan/Yuan-embedding-2.0-en open weights, 0.6B | 0.02 | huggingface.co | Official leaderboard | ||
| 28 | codefuse-ai/F2LLM-v2-0.6B open weights, 0.6B | 0.01 | huggingface.co | Official leaderboard | ||
| 29 | omarelshehy/arabic-english-sts-matryoshka open weights, 0.6B | 0.01 | huggingface.co | Official leaderboard | ||
| 30 | jinaai/jina-embeddings-v5-omni-small open weights, 1.6B | 0.01 | huggingface.co | Official leaderboard | ||
| 31 | jinaai/jina-embeddings-v5-text-small open weights, 0.6B | 0.01 | huggingface.co | Official leaderboard | ||
| 32 | mongodb/voyage-3 closed weights | 0.01 | blog.voyageai.com | Official leaderboard | ||
| 33 | BidirLM/BidirLM-0.6B-Embedding open weights, 0.6B | 0.01 | huggingface.co | Official leaderboard | ||
| 34 | codefuse-ai/F2LLM-4B open weights, 4B | 0.01 | huggingface.co | Official leaderboard | ||
| 35 | Omartificial-Intelligence-Space/Arabert-all-nli-triplet-Matryoshka open weights, 0.1B | 0.01 | huggingface.co | Official leaderboard | ||
| 36 | nvidia/NV-Embed-v2 open weights, 7.9B | 0.01 | huggingface.co | Official leaderboard | ||
| 37 | BidirLM/BidirLM-Omni-2.5B-Embedding open weights, 2.4B | 0.01 | huggingface.co | Official leaderboard | ||
| 38 | minishlab/M2V_base_glove_subword open weights, 0.1B | 0.01 | huggingface.co | Official leaderboard | ||
| 39 | Linq-AI-Research/Linq-Embed-Mistral open weights, 7.1B | 0.01 | huggingface.co | Official leaderboard | ||
| 40 | malenia1/ternary-weight-embedding open weights, 0.1B | 0.01 | huggingface.co | Official leaderboard | ||
| 41 | ai-sage/Giga-Embeddings-instruct-10B-A1.8B-0826 open weights, 10.5B | 0.01 | huggingface.co | Official leaderboard | ||
| 42 | codefuse-ai/F2LLM-v2-8B open weights, 7.6B | 0.01 | huggingface.co | Official leaderboard | ||
| 43 | microsoft/harrier-oss-v1-0.6b open weights, 0.6B | 0.01 | huggingface.co | Official leaderboard | ||
| 44 | DeepPavlov/rubert-base-cased open weights, 1.3B | 0.01 | huggingface.co | Official leaderboard | ||
| 45 | Alibaba-NLP/gte-Qwen2-1.5B-instruct open weights, 1.5B | 0.01 | huggingface.co | Official leaderboard | ||
| 46 | Jaume/gemma-2b-embeddings open weights, 2.5B | 0.01 | huggingface.co | Official leaderboard | ||
| 47 | google/flan-t5-base open weights, 0.2B | 0.01 | huggingface.co | Official leaderboard | ||
| 48 | codefuse-ai/F2LLM-v2-14B open weights, 14B | 0.01 | huggingface.co | Official leaderboard | ||
| 49 | minishlab/potion-base-4M open weights, 0B | 0.01 | huggingface.co | Official leaderboard | ||
| 50 | minishlab/potion-base-2M open weights, 0B | 0.01 | huggingface.co | Official leaderboard | ||
| 51 | silma-ai/silma-embeddding-matryoshka-v0.1 open weights, 0.1B | 0.01 | huggingface.co | Official leaderboard | ||
| 52 | ai-forever/sbert_large_nlu_ru open weights, 0.4B | 0.01 | huggingface.co | Official leaderboard | ||
| 53 | codefuse-ai/F2LLM-v2-1.7B open weights, 1.7B | 0.01 | huggingface.co | Official leaderboard | ||
| 54 | BidirLM/BidirLM-1.7B-Embedding open weights, 1.7B | 0.00 | huggingface.co | Official leaderboard | ||
| 55 | codefuse-ai/F2LLM-1.7B open weights, 1.7B | 0.00 | huggingface.co | Official leaderboard | ||
| 56 | minishlab/potion-base-32M open weights, 0B | 0.00 | huggingface.co | Official leaderboard | ||
| 57 | VPLabs/SearchMap_Preview open weights, 0.4B | 0.00 | huggingface.co | Official leaderboard | ||
| 58 | mteb/baseline-random-encoder open weights | 0.00 | Official leaderboard | |||
| 59 | DeepPavlov/rubert-base-cased-sentence open weights, 0.1B | 0.00 | huggingface.co | Official leaderboard | ||
| 60 | NovaSearch/jasper_en_vision_language_v1 open weights, 1.6B | 0.00 | huggingface.co | Official leaderboard | ||
| 61 | minishlab/potion-base-8M open weights, 0B | 0.00 | huggingface.co | Official leaderboard | ||
| 62 | NovaSearch/stella_en_1.5B_v5 open weights, 1.5B | 0.00 | huggingface.co | Official leaderboard | ||
| 63 | Salesforce/SFR-Embedding-Mistral open weights, 7.1B | 0.00 | huggingface.co | Official leaderboard | ||
| 64 | infly/inf-retriever-v1-1.5b open weights, 1.5B | 0.00 | huggingface.co | Official leaderboard | ||
| 65 | jinaai/jina-embeddings-v5-omni-nano open weights, 1B | 0.00 | huggingface.co | Official leaderboard | ||
| 66 | jinaai/jina-embeddings-v5-text-nano open weights, 0.2B | 0.00 | huggingface.co | Official leaderboard | ||
| 67 | Bytedance/Seed1.6-embedding-1215 closed weights | -0.00 | console.volcengine.com | Official leaderboard | ||
| 68 | manu/sentence_croissant_alpha_v0.4 open weights, 1.3B | -0.00 | huggingface.co | Official leaderboard | ||
| 69 | cointegrated/rubert-tiny2 open weights, 0B | -0.00 | huggingface.co | Official leaderboard | ||
| 70 | Haon-Chen/speed-embedding-7b-instruct open weights, 7.1B | -0.00 | huggingface.co | Official leaderboard | ||
| 71 | minishlab/M2V_base_output open weights, 0B | -0.00 | huggingface.co | Official leaderboard | ||
| 72 | Cohere/Cohere-embed-english-v3.0 closed weights | -0.00 | cohere.com | Official leaderboard | ||
| 73 | Omartificial-Intelligence-Space/Marbert-all-nli-triplet-Matryoshka open weights, 0.2B | -0.00 | huggingface.co | Official leaderboard | ||
| 74 | BidirLM/BidirLM-1B-Embedding open weights, 1B | -0.00 | huggingface.co | Official leaderboard | ||
| 75 | manu/sentence_croissant_alpha_v0.2 open weights, 1.3B | -0.00 | huggingface.co | Official leaderboard | ||
| 76 | intfloat/multilingual-e5-large-instruct open weights, 0.6B | -0.00 | huggingface.co | Official leaderboard | ||
| 77 | minishlab/M2V_base_glove open weights, 0.1B | -0.00 | huggingface.co | Official leaderboard | ||
| 78 | KaLM-Embedding/KaLM-embedding-multilingual-mini-instruct-v2.5 open weights, 0.5B | -0.00 | huggingface.co | Official leaderboard | ||
| 79 | microsoft/harrier-oss-v1-270m open weights, 0.3B | -0.00 | huggingface.co | Official leaderboard | ||
| 80 | ai-forever/sbert_large_mt_nlu_ru open weights, 0.4B | -0.00 | huggingface.co | Official leaderboard | ||
| 81 | ICT-TIME-and-Querit/BOOM_4B_v1 open weights, 4B | -0.01 | huggingface.co | Official leaderboard | ||
| 82 | DeepPavlov/distilrubert-small-cased-conversational open weights, 0.1B | -0.01 | huggingface.co | Official leaderboard | ||
| 83 | | -0.01 | Oct 2026 | huggingface.co | Official leaderboard | |
| 84 | intfloat/e5-mistral-7b-instruct open weights, 7.1B | -0.01 | huggingface.co | Official leaderboard | ||
| 85 | NovaSearch/stella_en_400M_v5 open weights, 0.4B | -0.01 | huggingface.co | Official leaderboard | ||
| 86 | Alibaba-NLP/gte-multilingual-base open weights, 0.3B | -0.01 | huggingface.co | Official leaderboard | ||
| 87 | izhx/udever-bloom-3b open weights, 3B | -0.01 | huggingface.co | Official leaderboard | ||
| 88 | jinaai/jina-embeddings-v2-small-en open weights, 0B | -0.01 | huggingface.co | Official leaderboard | ||
| 89 | sentence-transformers/all-MiniLM-L12-v2 open weights, 0B | -0.01 | huggingface.co | Official leaderboard | ||
| 90 | infgrad/Jasper-Token-Compression-600M open weights, 0.6B | -0.01 | huggingface.co | Official leaderboard | ||
| 91 | izhx/udever-bloom-560m open weights, 0.6B | -0.01 | huggingface.co | Official leaderboard | ||
| 92 | McGill-NLP/LLM2Vec-Mistral-7B-Instruct-v2-mntp-supervised open weights, 7.2B | -0.01 | huggingface.co | Official leaderboard | ||
| 93 | ICT-TIME-and-Querit/ICT-TIME-and-Querit-embedding-v1 open weights, 4B | -0.01 | huggingface.co | Official leaderboard | ||
| 94 | cointegrated/rubert-tiny open weights, 0B | -0.01 | huggingface.co | Official leaderboard | ||
| 95 | intfloat/e5-large-v2 open weights, 0.3B | -0.01 | huggingface.co | Official leaderboard | ||
| 96 | Omartificial-Intelligence-Space/Arabic-all-nli-triplet-Matryoshka open weights, 0.3B | -0.01 | huggingface.co | Official leaderboard | ||
| 97 | McGill-NLP/LLM2Vec-Mistral-7B-Instruct-v2-mntp-unsup-simcse open weights, 7.2B | -0.01 | huggingface.co | Official leaderboard | ||
| 98 | izhx/udever-bloom-1b1 open weights, 1.1B | -0.01 | huggingface.co | Official leaderboard | ||
| 99 | sentence-transformers/paraphrase-multilingual-mpnet-base-v2 open weights, 0.3B | -0.01 | huggingface.co | Official leaderboard | ||
| 100 | mongodb/voyage-3-lite closed weights | -0.01 | blog.voyageai.com | Official leaderboard | ||
| 101 | manu/sentence_croissant_alpha_v0.3 open weights, 1.3B | -0.01 | huggingface.co | Official leaderboard | ||
| 102 | Omartificial-Intelligence-Space/Arabic-MiniLM-L12-v2-all-nli-triplet open weights, 0.1B | -0.01 | huggingface.co | Official leaderboard | ||
| 103 | sentence-transformers/static-similarity-mrl-multilingual-v1 open weights, 0.1B | -0.01 | huggingface.co | Official leaderboard | ||
| 104 | ibm-granite/granite-embedding-125m-english open weights, 0.1B | -0.01 | huggingface.co | Official leaderboard | ||
| 105 | thenlper/gte-large open weights, 0.3B | -0.01 | huggingface.co | Official leaderboard | ||
| 106 | prdev/mini-gte open weights, 0.1B | -0.01 | huggingface.co | Official leaderboard | ||
| 107 | sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 open weights, 0.1B | -0.01 | huggingface.co | Official leaderboard | ||
| 108 | izhx/udever-bloom-7b1 open weights | -0.01 | huggingface.co | Official leaderboard | ||
| 109 | jinaai/jina-embeddings-v3 open weights, 0.6B | -0.01 | huggingface.co | Official leaderboard | ||
| 110 | Cohere/Cohere-embed-english-light-v3.0 closed weights | -0.01 | cohere.com | Official leaderboard | ||
| 111 | intfloat/e5-small open weights, 0B | -0.01 | huggingface.co | Official leaderboard | ||
| 112 | consciousAI/cai-lunaris-text-embeddings open weights, 0.3B | -0.01 | huggingface.co | Official leaderboard | ||
| 113 | Mihaiii/Venusaur open weights, 0B | -0.01 | huggingface.co | Official leaderboard | ||
| 114 | Snowflake/snowflake-arctic-embed-l open weights, 0.3B | -0.01 | huggingface.co | Official leaderboard | ||
| 115 | HIT-TMG/KaLM-embedding-multilingual-mini-v1 open weights, 0.5B | -0.01 | huggingface.co | Official leaderboard | ||
| 116 | Mihaiii/Wartortle open weights, 0B | -0.02 | huggingface.co | Official leaderboard | ||
| 117 | thenlper/gte-small open weights, 0B | -0.02 | huggingface.co | Official leaderboard | ||
| 118 | cnmoro/static-nomic-384-pten-v2-st open weights, 0.1B | -0.02 | huggingface.co | Official leaderboard | ||
| 119 | codefuse-ai/F2LLM-v2-80M open weights, 0.1B | -0.02 | huggingface.co | Official leaderboard | ||
| 120 | jinaai/jina-embeddings-v2-base-en open weights, 0.1B | -0.02 | huggingface.co | Official leaderboard | ||
| 121 | codefuse-ai/F2LLM-v2-330M open weights, 0.3B | -0.02 | huggingface.co | Official leaderboard | ||
| 122 | hotchpotch/bekko-static-embedding-v1 open weights, 0.2B | -0.02 | huggingface.co | Official leaderboard | ||
| 123 | Mihaiii/Squirtle open weights, 0B | -0.02 | huggingface.co | Official leaderboard | ||
| 124 | abhinand/MedEmbed-small-v0.1 open weights, 0B | -0.02 | huggingface.co | Official leaderboard | ||
| 125 | castorini/monot5-base-msmarco-10k open weights, 0.3B | -0.02 | Official leaderboard | |||
| 126 | ibm-granite/granite-embedding-278m-multilingual open weights, 0.3B | -0.02 | huggingface.co | Official leaderboard | ||
| 127 | Omartificial-Intelligence-Space/Arabic-labse-Matryoshka open weights, 0.5B | -0.02 | huggingface.co | Official leaderboard | ||
| 128 | Mihaiii/gte-micro open weights, 0B | -0.02 | huggingface.co | Official leaderboard | ||
| 129 | Salesforce/SFR-Embedding-2_R open weights, 7.1B | -0.02 | huggingface.co | Official leaderboard | ||
| 130 | avsolatorio/GIST-large-Embedding-v0 open weights, 0.3B | -0.02 | huggingface.co | Official leaderboard | ||
| 131 | nomic-ai/nomic-embed-text-v1.5 open weights, 0.1B | -0.02 | huggingface.co | Official leaderboard | ||
| 132 | BAAI/bge-small-en-v1.5 open weights, 0B | -0.02 | huggingface.co | Official leaderboard | ||
| 133 | Cohere/Cohere-embed-multilingual-v3.0 closed weights | -0.02 | cohere.com | Official leaderboard | ||
| 134 | Snowflake/snowflake-arctic-embed-m-long open weights, 0.1B | -0.02 | huggingface.co | Official leaderboard | ||
| 135 | avsolatorio/GIST-all-MiniLM-L6-v2 open weights, 0B | -0.02 | huggingface.co | Official leaderboard | ||
| 136 | mixedbread-ai/mxbai-embed-large-v1 open weights, 0.3B | -0.02 | huggingface.co | Official leaderboard | ||
| 137 | deepvk/USER-base open weights, 0.4B | -0.02 | huggingface.co | Official leaderboard | ||
| 138 | Gameselo/STS-multilingual-mpnet-base-v2 open weights, 0.3B | -0.02 | huggingface.co | Official leaderboard | ||
| 139 | ibm-granite/granite-embedding-97m-multilingual-r2 open weights, 0.1B | -0.02 | huggingface.co | Official leaderboard | ||
| 140 | minishlab/potion-multilingual-128M open weights, 0.1B | -0.02 | huggingface.co | Official leaderboard | ||
| 141 | WhereIsAI/UAE-Large-V1 open weights, 0.3B | -0.02 | huggingface.co | Official leaderboard | ||
| 142 | nomic-ai/nomic-embed-text-v1-unsupervised open weights, 0.1B | -0.02 | huggingface.co | Official leaderboard | ||
| 143 | Mihaiii/Ivysaur open weights, 0B | -0.02 | huggingface.co | Official leaderboard | ||
| 144 | BidirLM/BidirLM-270M-Embedding open weights, 0.3B | -0.02 | huggingface.co | Official leaderboard | ||
| 145 | sergeyzh/rubert-tiny-turbo open weights, 0B | -0.02 | huggingface.co | Official leaderboard | ||
| 146 | BAAI/bge-large-en-v1.5 open weights, 0.3B | -0.02 | huggingface.co | Official leaderboard | ||
| 147 | intfloat/e5-large open weights, 0.3B | -0.02 | huggingface.co | Official leaderboard | ||
| 148 | Snowflake/snowflake-arctic-embed-m open weights, 0.1B | -0.02 | huggingface.co | Official leaderboard | ||
| 149 | Snowflake/snowflake-arctic-embed-xs open weights, 0B | -0.02 | huggingface.co | Official leaderboard | ||
| 150 | BAAI/bge-large-en open weights, 0.3B | -0.02 | huggingface.co | Official leaderboard | ||
| 151 | deepvk/deberta-v1-base open weights, 0.1B | -0.02 | huggingface.co | Official leaderboard | ||
| 152 | openai/text-embedding-3-small closed weights | -0.02 | openai.com | Official leaderboard | ||
| 153 | ibm-granite/granite-embedding-311m-multilingual-r2 open weights, 0.3B | -0.02 | huggingface.co | Official leaderboard | ||
| 154 | Cohere/Cohere-embed-multilingual-light-v3.0 closed weights | -0.02 | cohere.com | Official leaderboard | ||
| 155 | intfloat/multilingual-e5-small open weights, 0.1B | -0.02 | huggingface.co | Official leaderboard | ||
| 156 | thenlper/gte-base open weights, 0.1B | -0.02 | huggingface.co | Official leaderboard | ||
| 157 | Snowflake/snowflake-arctic-embed-l-v2.0 open weights, 0.6B | -0.02 | huggingface.co | Official leaderboard | ||
| 158 | manu/bge-m3-custom-fr open weights, 0.6B | -0.03 | huggingface.co | Official leaderboard | ||
| 159 | aari1995/German_Semantic_STS_V2 open weights, 0.3B | -0.03 | huggingface.co | Official leaderboard | ||
| 160 | avsolatorio/NoInstruct-small-Embedding-v0 open weights, 0B | -0.03 | huggingface.co | Official leaderboard | ||
| 161 | HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1 open weights, 0.5B | -0.03 | huggingface.co | Official leaderboard | ||
| 162 | deepvk/USER-bge-m3 open weights, 0.4B | -0.03 | huggingface.co | Official leaderboard | ||
| 163 | intfloat/multilingual-e5-base open weights, 0.3B | -0.03 | huggingface.co | Official leaderboard | ||
| 164 | openai/text-embedding-3-large closed weights | -0.03 | openai.com | Official leaderboard | ||
| 165 | avsolatorio/GIST-small-Embedding-v0 open weights, 0B | -0.03 | huggingface.co | Official leaderboard | ||
| 166 | ibm-granite/granite-embedding-30m-english open weights, 0B | -0.03 | huggingface.co | Official leaderboard | ||
| 167 | deepfile/embedder-100p open weights, 0.3B | -0.03 | huggingface.co | Official leaderboard | ||
| 168 | MongoDB/mdbr-leaf-mt open weights, 0B | -0.03 | huggingface.co | Official leaderboard | ||
| 169 | brahmairesearch/slx-v0.1 open weights, 0B | -0.03 | huggingface.co | Official leaderboard | ||
| 170 | Omartificial-Intelligence-Space/Arabic-mpnet-base-all-nli-triplet open weights, 0.1B | -0.03 | huggingface.co | Official leaderboard | ||
| 171 | sentence-transformers/all-MiniLM-L6-v2 open weights, 0B | -0.03 | huggingface.co | Official leaderboard | ||
| 172 | intfloat/e5-small-v2 open weights, 0B | -0.03 | huggingface.co | Official leaderboard | ||
| 173 | dwzhu/e5-base-4k open weights, 0.1B | -0.03 | huggingface.co | Official leaderboard | ||
| 174 | mteb/baseline-bm25s open weights | -0.03 | github.com | Official leaderboard | ||
| 175 | ibm-granite/granite-embedding-107m-multilingual open weights, 0.1B | -0.03 | huggingface.co | Official leaderboard | ||
| 176 | sentence-transformers/LaBSE open weights, 0.5B | -0.03 | huggingface.co | Official leaderboard | ||
| 177 | bigscience/sgpt-bloom-7b1-msmarco open weights, 7.1B | -0.03 | huggingface.co | Official leaderboard | ||
| 178 | Lajavaness/bilingual-embedding-large open weights, 0.6B | -0.03 | huggingface.co | Official leaderboard | ||
| 179 | intfloat/multilingual-e5-large open weights, 0.6B | -0.03 | huggingface.co | Official leaderboard | ||
| 180 | sentence-transformers/all-mpnet-base-v2 open weights, 0.1B | -0.03 | huggingface.co | Official leaderboard | ||
| 181 | Snowflake/snowflake-arctic-embed-s open weights, 0B | -0.03 | huggingface.co | Official leaderboard | ||
| 182 | BAAI/bge-base-en open weights, 0.1B | -0.03 | huggingface.co | Official leaderboard | ||
| 183 | BAAI/bge-m3 open weights, 0.6B | -0.03 | huggingface.co | Official leaderboard | ||
| 184 | jinaai/jina-embedding-s-en-v1 open weights, 0B | -0.03 | huggingface.co | Official leaderboard | ||
| 185 | Mihaiii/Bulbasaur open weights, 0B | -0.03 | huggingface.co | Official leaderboard | ||
| 186 | nomic-ai/nomic-embed-text-v1 open weights, 0.1B | -0.03 | huggingface.co | Official leaderboard | ||
| 187 | infgrad/stella-base-en-v2 open weights, 0.1B | -0.03 | huggingface.co | Official leaderboard | ||
| 188 | sdadas/mmlw-e5-base open weights, 0.3B | -0.03 | huggingface.co | Official leaderboard | ||
| 189 | hotchpotch/bekko-embedding-v1-a8m open weights, 0.1B | -0.03 | huggingface.co | Official leaderboard | ||
| 190 | Snowflake/snowflake-arctic-embed-m-v2.0 open weights, 0.3B | -0.03 | huggingface.co | Official leaderboard | ||
| 191 | avsolatorio/GIST-Embedding-v0 open weights, 0.1B | -0.03 | huggingface.co | Official leaderboard | ||
| 192 | Lajavaness/bilingual-embedding-small open weights, 0.1B | -0.03 | huggingface.co | Official leaderboard | ||
| 193 | codefuse-ai/F2LLM-v2-160M open weights, 0.2B | -0.03 | huggingface.co | Official leaderboard | ||
| 194 | sdadas/mmlw-e5-large open weights, 0.6B | -0.03 | huggingface.co | Official leaderboard | ||
| 195 | Snowflake/snowflake-arctic-embed-m-v1.5 open weights, 0.1B | -0.03 | huggingface.co | Official leaderboard | ||
| 196 | sdadas/mmlw-roberta-base open weights, 0.1B | -0.03 | huggingface.co | Official leaderboard | ||
| 197 | OrdalieTech/Solon-embeddings-large-0.1 open weights, 0.6B | -0.03 | huggingface.co | Official leaderboard | ||
| 198 | intfloat/e5-base open weights, 0.1B | -0.03 | huggingface.co | Official leaderboard | ||
| 199 | sergeyzh/LaBSE-ru-turbo open weights, 0.1B | -0.04 | huggingface.co | Official leaderboard | ||
| 200 | ai-forever/ru-en-RoSBERTa open weights, 0.4B | -0.04 | huggingface.co | Official leaderboard | ||
| 201 | sdadas/mmlw-roberta-large open weights, 0.4B | -0.04 | huggingface.co | Official leaderboard | ||
| 202 | cointegrated/LaBSE-en-ru open weights, 0.1B | -0.04 | huggingface.co | Official leaderboard | ||
| 203 | nomic-ai/nomic-embed-text-v1-ablated open weights, 0.1B | -0.04 | huggingface.co | Official leaderboard | ||
| 204 | Mihaiii/gte-micro-v4 open weights, 0B | -0.04 | huggingface.co | Official leaderboard | ||
| 205 | Lajavaness/bilingual-embedding-base open weights, 0.3B | -0.04 | huggingface.co | Official leaderboard | ||
| 206 | intfloat/e5-base-v2 open weights, 0.1B | -0.04 | huggingface.co | Official leaderboard | ||
| 207 | nomic-ai/nomic-embed-text-v2-moe open weights, 0.5B | -0.04 | huggingface.co | Official leaderboard | ||
| 208 | shibing624/text2vec-base-multilingual open weights, 0.1B | -0.04 | huggingface.co | Official leaderboard | ||
| 209 | BAAI/bge-base-en-v1.5 open weights, 0.1B | -0.04 | huggingface.co | Official leaderboard | ||
| 210 | jinaai/jina-embedding-b-en-v1 open weights, 0.1B | -0.04 | huggingface.co | Official leaderboard | ||
| 211 | sdadas/mmlw-e5-small open weights, 0.1B | -0.04 | huggingface.co | Official leaderboard | ||
| 212 | hotchpotch/bekko-embedding-v1-a25m open weights, 0.1B | -0.05 | huggingface.co | Official leaderboard |
| # | Model | Score | Setting | Date | Link | Source |
|---|---|---|---|---|---|---|
| 1 | | 0.12 | Jun 2025 | huggingface.co | Official leaderboard | |
| 2 | | 0.10 | Jun 2025 | huggingface.co | Official leaderboard | |
| 3 | | 0.05 | Jun 2025 | huggingface.co | Official leaderboard | |
| 4 | | -0.01 | Oct 2026 | huggingface.co | Official leaderboard |
Rankings by part
We read 3 parts from MTEB’s leaderboard: Robust04 p-MRR, News21 p-MRR and Core17 p-MRR. Each ranks models on one part of the test. Qwen3-Embedding-4B leads 2 of them, and Qwen3-Embedding-8B leads the other one. Arrows show how far a model moved from its overall rank among the models we track.
Robust04 p-MRR
4 models we track have a score here.
- 1
Qwen3-Embedding-4B 0.12
- 2
Qwen3-Embedding-8B 0.09
- 3
Qwen3-Embedding-0.6B 0.03
- 4
EmbeddingGemma 2 -0.03
News21 p-MRR
4 models we track have a score here.
- 1
Qwen3-Embedding-8B ↑1 0.09
- 2
Qwen3-Embedding-4B ↓1 0.09
- 3
Qwen3-Embedding-0.6B 0.04
- 4
EmbeddingGemma 2 -0.01
Core17 p-MRR
4 models we track have a score here.
- 1
Qwen3-Embedding-4B 0.14
- 2
Qwen3-Embedding-8B 0.13
- 3
Qwen3-Embedding-0.6B 0.09
- 4
EmbeddingGemma 2 0.02
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
Scores over time
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 Knowledge
- MMLU-Pro In use Harder 10-option version of MMLU with reasoning-focused questions across 14 subjects.
Intern-S2-397B 89.8%
- MMLU In use 57-subject multiple-choice exam questions from elementary to professional level. Scored by accuracy.
Seed1.8 92.3%
- SuperGPQA In use 26,529 graduate-level multiple-choice questions across 285 disciplines. Accuracy.
Qwen 3.6 Max (Preview) 73.9%
- WideSearch In use 200 bilingual broad info-seeking tasks: agent collects many atomic facts into a table. Scored by success rate and row/item F1.
Tencent Hy4 preview 83.9%
- BBEH micro average In use Models solve harder replacements for each of the 23 BIG-Bench Hard tasks, 4,520 examples in total. The score is the share of all examples answered correctly.
Gemma 4 31B IT 74.4%
- HLE-Diamond In use Models answer 1,000 cleaned expert questions from Humanity's Last Exam, 500 on reasoning and 500 on knowledge, closed book. Graded on exact answers. Claude Fable 5.2 77.9%
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 (212 entries).
- Pass Models scored 4 models we track, plus 208 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 Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on MTEB: 4 rows for models we track and 208 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.