SemEval 2024 Task 1 semantic textual relatedness
Models rank sentence pairs by relatedness across languages. The evaluation compares their rankings with human judgments.
MTEB scores the task using Spearman correlation.
- Made by
- Nedjma Ousidhoum and colleagues
- Released
- March 2024
- Kind
- Reading in many languages
- Level
- School
- Scored
- Checked automatically
- Answers
- Prediction
- Tasks
- All public
- Measures
- Capability
- Language
- Many languages
- Interaction
- Single turn
- Refresh
- One fixed set
- Run by
- Anyone
- In views
- Many languages
- Last model added
- October 2026
- Scores refreshed
- November 20th, 2026
google/gemini-embedding-001 tops the leaderboard with 0.73 EmbeddingGemma 2 leads with 0.65 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 EmbeddingGemma 2, at 0.65. 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
- 0.73 google/gemini-embedding-001
- 0.71 tencent/KaLM-Embedding-Gemma3-12B-2511
- 0.71 google/text-multilingual-embedding-002
- 0.70 nvidia/llama-embed-nemotron-8b
- 0.69 intfloat/multilingual-e5-large-instruct
- 0.69 OrdalieTech/Solon-embeddings-large-0.1
- 0.68 codefuse-ai/F2LLM-v2-14B
- 0.68 microsoft/harrier-oss-v1-27b
- 0.68 codefuse-ai/F2LLM-v2-8B
- 0.68 microsoft/harrier-oss-v1-0.6b
- 0.68 Lajavaness/bilingual-embedding-large
- 0.67 Linq-AI-Research/Linq-Embed-Mistral
- 0.67 codefuse-ai/F2LLM-v2-4B
- 0.67 Lajavaness/bilingual-embedding-base
- 0.67 Salesforce/SFR-Embedding-Mistral
- 0.67 Salesforce/SFR-Embedding-2_R
- 0.67 nomic-ai/nomic-embed-text-v2-moe
- 0.66 manu/bge-m3-custom-fr
- 0.66 intfloat/e5-mistral-7b-instruct
- 0.66 ai-sage/Giga-Embeddings-instruct-10B-A1.8B-0826
- 0.66 GritLM/GritLM-8x7B
- 0.66 Snowflake/snowflake-arctic-embed-l-v2.0
- 0.66 microsoft/harrier-oss-v1-270m
- 0.66 codefuse-ai/F2LLM-v2-1.7B
- 0.66 ai-sage/Giga-Embeddings-instruct-3B-0826
- 0.66 GritLM/GritLM-7B
- 0.66 Lajavaness/bilingual-embedding-small
- 0.65
EmbeddingGemma 2
- 0.65 BAAI/bge-m3
- 0.65 ICT-TIME-and-Querit/ICT-TIME-and-Querit-embedding-v1
- 0.65 openai/text-embedding-3-large
- 0.65 Alibaba-NLP/gte-multilingual-base
- 0.65 google/embeddinggemma-300m
- 0.65 BidirLM/BidirLM-1B-Embedding
- 0.65 codefuse-ai/F2LLM-v2-330M
- 0.65 Omartificial-Intelligence-Space/Arabic-labse-Matryoshka
- 0.65 ICT-TIME-and-Querit/BOOM_4B_v1
- 0.65 mongodb/voyage-multilingual-2
- 0.65 mongodb/voyage-3.5
- 0.65 codefuse-ai/F2LLM-v2-0.6B
- 0.65 mongodb/voyage-3
- 0.65 jinaai/jina-embeddings-v3
- 0.64
Qwen3-Embedding-8B
- 0.64 BidirLM/BidirLM-Omni-2.5B-Embedding
- 0.64 Octen/Octen-Embedding-8B
- 0.64 mongodb/voyage-3-lite
- 0.64 HIT-TMG/KaLM-embedding-multilingual-mini-v1
- 0.64 Cohere/Cohere-embed-multilingual-v3.0
- 0.64 Mira190/Euler-Legal-Embedding-V1
- 0.63
Qwen3-Embedding-4B
- 0.63 Alibaba-NLP/gte-Qwen2-7B-instruct
- 0.63 hotchpotch/bekko-embedding-v1-a25m
- 0.63 ibm-granite/granite-embedding-311m-multilingual-r2
- 0.63 hotchpotch/bekko-embedding-v1-a8m
- 0.62 sentence-transformers/LaBSE
- 0.62 codefuse-ai/F2LLM-v2-160M
- 0.62 BidirLM/BidirLM-1.7B-Embedding
- 0.62 jinaai/jina-embeddings-v5-omni-nano
- 0.62 jinaai/jina-embeddings-v5-text-nano
- 0.62 Alibaba-NLP/gte-Qwen2-1.5B-instruct
- 0.62 intfloat/multilingual-e5-small
- 0.61 intfloat/multilingual-e5-base
- 0.61 ibm-granite/granite-embedding-278m-multilingual
- 0.61 jinaai/jina-embeddings-v5-omni-small
- 0.61 jinaai/jina-embeddings-v5-text-small
- 0.61 openai/text-embedding-3-small
- 0.61 HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1
- 0.61 Cohere/Cohere-embed-multilingual-light-v3.0
- 0.60 Omartificial-Intelligence-Space/Arabic-all-nli-triplet-Matryoshka
- 0.60 hotchpotch/bekko-static-embedding-v1
- 0.59
Qwen3-Embedding-0.6B
- 0.59 codefuse-ai/F2LLM-v2-80M
- 0.59 ibm-granite/granite-embedding-97m-multilingual-r2
- 0.59 minishlab/potion-multilingual-128M
- 0.59 nvidia/NV-Embed-v2
- 0.59 Snowflake/snowflake-arctic-embed-m-v2.0
- 0.59 omarelshehy/arabic-english-sts-matryoshka
- 0.59 BidirLM/BidirLM-270M-Embedding
- 0.59 ibm-granite/granite-embedding-107m-multilingual
- 0.58 BidirLM/BidirLM-0.6B-Embedding
- 0.58 Bytedance/Seed1.6-embedding-1215
- 0.58 Omartificial-Intelligence-Space/Arabic-MiniLM-L12-v2-all-nli-triplet
- 0.57 cnmoro/static-nomic-384-pten-v2-st
- 0.57 nvidia/NV-Embed-v1
- 0.56 jinaai/jina-embeddings-v4
- 0.56 Gameselo/STS-multilingual-mpnet-base-v2
- 0.56 mongodb/voyage-large-2-instruct
- 0.55 sentence-transformers/paraphrase-multilingual-mpnet-base-v2
- 0.55 Alibaba-NLP/gte-Qwen1.5-7B-instruct
- 0.55 NovaSearch/jasper_en_vision_language_v1
- 0.52 sentence-transformers/static-similarity-mrl-multilingual-v1
- 0.52 NovaSearch/stella_en_1.5B_v5
- 0.52 McGill-NLP/LLM2Vec-Mistral-7B-Instruct-v2-mntp-supervised
- 0.51 zeroentropy/zembed-1
- 0.51 Haon-Chen/speed-embedding-7b-instruct
- 0.48 bigscience/sgpt-bloom-7b1-msmarco
- 0.48 sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
- 0.48 shibing624/text2vec-base-multilingual
- 0.45 McGill-NLP/LLM2Vec-Mistral-7B-Instruct-v2-mntp-unsup-simcse
- 0.44 izhx/udever-bloom-7b1
- 0.44 intfloat/e5-large-v2
- 0.44 nomic-ai/nomic-embed-text-v1
- 0.44 intfloat/e5-base-v2
- 0.44 nomic-ai/nomic-embed-text-v1-ablated
- 0.44 izhx/udever-bloom-1b1
- 0.44 nomic-ai/nomic-embed-text-v1.5
- 0.44 manu/sentence_croissant_alpha_v0.2
- 0.43 manu/sentence_croissant_alpha_v0.3
- 0.43 BAAI/bge-base-en-v1.5
- 0.43 nomic-ai/nomic-embed-text-v1-unsupervised
- 0.43 avsolatorio/GIST-Embedding-v0
- 0.42 ibm-granite/granite-embedding-125m-english
- 0.42 avsolatorio/GIST-large-Embedding-v0
- 0.42 intfloat/e5-small-v2
- 0.42 brahmairesearch/slx-v0.1
- 0.42 sentence-transformers/all-MiniLM-L6-v2
- 0.41 Omartificial-Intelligence-Space/Arabic-mpnet-base-all-nli-triplet
- 0.41 manu/sentence_croissant_alpha_v0.4
- 0.41 infgrad/stella-base-en-v2
- 0.41 thenlper/gte-base
- 0.40 NovaSearch/stella_en_400M_v5
- 0.40 Cohere/Cohere-embed-english-v3.0
- 0.40 intfloat/e5-large
- 0.40 avsolatorio/GIST-all-MiniLM-L6-v2
- 0.40 deepfile/embedder-100p
- 0.40 dwzhu/e5-base-4k
- 0.39 Mihaiii/gte-micro
- 0.39 izhx/udever-bloom-3b
- 0.39 Cohere/Cohere-embed-english-light-v3.0
- 0.39 minishlab/potion-base-8M
- 0.39 minishlab/potion-base-4M
- 0.39 Mihaiii/Squirtle
- 0.39 intfloat/e5-base
- 0.39 Mihaiii/Wartortle
- 0.38 abhinand/MedEmbed-small-v0.1
- 0.38 BAAI/bge-small-en-v1.5
- 0.38 Snowflake/snowflake-arctic-embed-m-long
- 0.38 avsolatorio/NoInstruct-small-Embedding-v0
- 0.38 sentence-transformers/all-mpnet-base-v2
- 0.38 minishlab/M2V_base_glove_subword
- 0.38 sentence-transformers/all-MiniLM-L12-v2
- 0.38 minishlab/potion-base-2M
- 0.38 Mihaiii/gte-micro-v4
- 0.38 Mihaiii/Bulbasaur
- 0.38 thenlper/gte-large
- 0.38 Mihaiii/Ivysaur
- 0.37 avsolatorio/GIST-small-Embedding-v0
- 0.37 WhereIsAI/UAE-Large-V1
- 0.37 minishlab/M2V_base_output
- 0.37 Jaume/gemma-2b-embeddings
- 0.37 thenlper/gte-small
- 0.37 intfloat/e5-small
- 0.37 sdadas/mmlw-e5-large
- 0.37 sdadas/mmlw-e5-base
- 0.36 Mihaiii/Venusaur
- 0.36 jinaai/jina-embeddings-v2-small-en
- 0.36 mixedbread-ai/mxbai-embed-large-v1
- 0.36 Omartificial-Intelligence-Space/Marbert-all-nli-triplet-Matryoshka
- 0.36 Omartificial-Intelligence-Space/Arabert-all-nli-triplet-Matryoshka
- 0.36 BAAI/bge-large-en-v1.5
- 0.35 Snowflake/snowflake-arctic-embed-xs
- 0.35 ibm-granite/granite-embedding-30m-english
- 0.35 Snowflake/snowflake-arctic-embed-s
- 0.35 Snowflake/snowflake-arctic-embed-m-v1.5
- 0.35 sdadas/mmlw-e5-small
- 0.34 deepvk/USER-base
- 0.34 silma-ai/silma-embeddding-matryoshka-v0.1
- 0.34 Snowflake/snowflake-arctic-embed-m
- 0.33 ai-forever/ru-en-RoSBERTa
- 0.32 Snowflake/snowflake-arctic-embed-l
- 0.32 deepvk/deberta-v1-base
- 0.31 deepvk/USER-bge-m3
- 0.30 izhx/udever-bloom-560m
- 0.30 consciousAI/cai-lunaris-text-embeddings
- 0.29 DeepPavlov/rubert-base-cased-sentence
- 0.27 sergeyzh/LaBSE-ru-turbo
- 0.27 malenia1/ternary-weight-embedding
- 0.27 DeepPavlov/rubert-base-cased
- 0.27 jinaai/jina-embedding-b-en-v1
- 0.27 sdadas/mmlw-roberta-large
- 0.25 aari1995/German_Semantic_STS_V2
- 0.25 cointegrated/LaBSE-en-ru
- 0.25 sdadas/mmlw-roberta-base
- 0.25 sergeyzh/rubert-tiny-turbo
- 0.25 cointegrated/rubert-tiny2
- 0.25 cointegrated/rubert-tiny
- 0.25 minishlab/M2V_base_glove
- 0.25 jinaai/jina-embedding-s-en-v1
- 0.23 ai-forever/sbert_large_mt_nlu_ru
- 0.23 DeepPavlov/distilrubert-small-cased-conversational
- 0.22 ai-forever/sbert_large_nlu_ru
- 0.19 Hum-Works/lodestone-base-4096-v1
- 0.14 jinaai/jina-embeddings-v2-base-en
- 1 google/gemini-embedding-001 0.73
- 2 tencent/KaLM-Embedding-Gemma3-12B-2511 0.71
- 3 google/text-multilingual-embedding-002 0.71
- 4 nvidia/llama-embed-nemotron-8b 0.70
- 5 intfloat/multilingual-e5-large-instruct 0.69
- 6 OrdalieTech/Solon-embeddings-large-0.1 0.69
- 7 codefuse-ai/F2LLM-v2-14B 0.68
- 8 microsoft/harrier-oss-v1-27b 0.68
- 9 codefuse-ai/F2LLM-v2-8B 0.68
- 10 microsoft/harrier-oss-v1-0.6b 0.68
- 11 Lajavaness/bilingual-embedding-large 0.68
- 12 Linq-AI-Research/Linq-Embed-Mistral 0.67
- 13 codefuse-ai/F2LLM-v2-4B 0.67
- 14 Lajavaness/bilingual-embedding-base 0.67
- 15 Salesforce/SFR-Embedding-Mistral 0.67
- 16 Salesforce/SFR-Embedding-2_R 0.67
- 17 nomic-ai/nomic-embed-text-v2-moe 0.67
- 18 manu/bge-m3-custom-fr 0.66
- 19 intfloat/e5-mistral-7b-instruct 0.66
- 20 ai-sage/Giga-Embeddings-instruct-10B-A1.8B-0826 0.66
- 21 GritLM/GritLM-8x7B 0.66
- 22 Snowflake/snowflake-arctic-embed-l-v2.0 0.66
- 23 microsoft/harrier-oss-v1-270m 0.66
- 24 codefuse-ai/F2LLM-v2-1.7B 0.66
- 25 ai-sage/Giga-Embeddings-instruct-3B-0826 0.66
- 26 GritLM/GritLM-7B 0.66
- 27 Lajavaness/bilingual-embedding-small 0.66
- 28
EmbeddingGemma 2 0.65
- 29 BAAI/bge-m3 0.65
- 30 ICT-TIME-and-Querit/ICT-TIME-and-Querit-embedding-v1 0.65
- 31 openai/text-embedding-3-large 0.65
- 32 Alibaba-NLP/gte-multilingual-base 0.65
- 33 google/embeddinggemma-300m 0.65
- 34 BidirLM/BidirLM-1B-Embedding 0.65
- 35 codefuse-ai/F2LLM-v2-330M 0.65
- 36 Omartificial-Intelligence-Space/Arabic-labse-Matryoshka 0.65
- 37 ICT-TIME-and-Querit/BOOM_4B_v1 0.65
- 38 mongodb/voyage-multilingual-2 0.65
- 39 mongodb/voyage-3.5 0.65
- 40 codefuse-ai/F2LLM-v2-0.6B 0.65
- 41 mongodb/voyage-3 0.65
- 42 jinaai/jina-embeddings-v3 0.65
- 43
Qwen3-Embedding-8B 0.64
- 44 BidirLM/BidirLM-Omni-2.5B-Embedding 0.64
- 45 Octen/Octen-Embedding-8B 0.64
- 46 mongodb/voyage-3-lite 0.64
- 47 HIT-TMG/KaLM-embedding-multilingual-mini-v1 0.64
- 48 Cohere/Cohere-embed-multilingual-v3.0 0.64
- 49 Mira190/Euler-Legal-Embedding-V1 0.64
- 50
Qwen3-Embedding-4B 0.63
- 51 Alibaba-NLP/gte-Qwen2-7B-instruct 0.63
- 52 hotchpotch/bekko-embedding-v1-a25m 0.63
- 53 ibm-granite/granite-embedding-311m-multilingual-r2 0.63
- 54 hotchpotch/bekko-embedding-v1-a8m 0.63
- 55 sentence-transformers/LaBSE 0.62
- 56 codefuse-ai/F2LLM-v2-160M 0.62
- 57 BidirLM/BidirLM-1.7B-Embedding 0.62
- 58 jinaai/jina-embeddings-v5-omni-nano 0.62
- 59 jinaai/jina-embeddings-v5-text-nano 0.62
- 60 Alibaba-NLP/gte-Qwen2-1.5B-instruct 0.62
- 61 intfloat/multilingual-e5-small 0.62
- 62 intfloat/multilingual-e5-base 0.61
- 63 ibm-granite/granite-embedding-278m-multilingual 0.61
- 64 jinaai/jina-embeddings-v5-omni-small 0.61
- 65 jinaai/jina-embeddings-v5-text-small 0.61
- 66 openai/text-embedding-3-small 0.61
- 67 HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1 0.61
- 68 Cohere/Cohere-embed-multilingual-light-v3.0 0.61
- 69 Omartificial-Intelligence-Space/Arabic-all-nli-triplet-Matryoshka 0.60
- 70 hotchpotch/bekko-static-embedding-v1 0.60
- 71
Qwen3-Embedding-0.6B 0.59
- 72 codefuse-ai/F2LLM-v2-80M 0.59
- 73 ibm-granite/granite-embedding-97m-multilingual-r2 0.59
- 74 minishlab/potion-multilingual-128M 0.59
- 75 nvidia/NV-Embed-v2 0.59
- 76 Snowflake/snowflake-arctic-embed-m-v2.0 0.59
- 77 omarelshehy/arabic-english-sts-matryoshka 0.59
- 78 BidirLM/BidirLM-270M-Embedding 0.59
- 79 ibm-granite/granite-embedding-107m-multilingual 0.59
- 80 BidirLM/BidirLM-0.6B-Embedding 0.58
- 81 Bytedance/Seed1.6-embedding-1215 0.58
- 82 Omartificial-Intelligence-Space/Arabic-MiniLM-L12-v2-all-nli-triplet 0.58
- 83 cnmoro/static-nomic-384-pten-v2-st 0.57
- 84 nvidia/NV-Embed-v1 0.57
- 85 jinaai/jina-embeddings-v4 0.56
- 86 Gameselo/STS-multilingual-mpnet-base-v2 0.56
- 87 mongodb/voyage-large-2-instruct 0.56
- 88 sentence-transformers/paraphrase-multilingual-mpnet-base-v2 0.55
- 89 Alibaba-NLP/gte-Qwen1.5-7B-instruct 0.55
- 90 NovaSearch/jasper_en_vision_language_v1 0.55
- 91 sentence-transformers/static-similarity-mrl-multilingual-v1 0.52
- 92 NovaSearch/stella_en_1.5B_v5 0.52
- 93 McGill-NLP/LLM2Vec-Mistral-7B-Instruct-v2-mntp-supervised 0.52
- 94 zeroentropy/zembed-1 0.51
- 95 Haon-Chen/speed-embedding-7b-instruct 0.51
- 96 bigscience/sgpt-bloom-7b1-msmarco 0.48
- 97 sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 0.48
- 98 shibing624/text2vec-base-multilingual 0.48
- 99 McGill-NLP/LLM2Vec-Mistral-7B-Instruct-v2-mntp-unsup-simcse 0.45
- 100 izhx/udever-bloom-7b1 0.44
- 101 intfloat/e5-large-v2 0.44
- 102 nomic-ai/nomic-embed-text-v1 0.44
- 103 intfloat/e5-base-v2 0.44
- 104 nomic-ai/nomic-embed-text-v1-ablated 0.44
- 105 izhx/udever-bloom-1b1 0.44
- 106 nomic-ai/nomic-embed-text-v1.5 0.44
- 107 manu/sentence_croissant_alpha_v0.2 0.44
- 108 manu/sentence_croissant_alpha_v0.3 0.43
- 109 BAAI/bge-base-en-v1.5 0.43
- 110 nomic-ai/nomic-embed-text-v1-unsupervised 0.43
- 111 avsolatorio/GIST-Embedding-v0 0.43
- 112 ibm-granite/granite-embedding-125m-english 0.42
- 113 avsolatorio/GIST-large-Embedding-v0 0.42
- 114 intfloat/e5-small-v2 0.42
- 115 brahmairesearch/slx-v0.1 0.42
- 116 sentence-transformers/all-MiniLM-L6-v2 0.42
- 117 Omartificial-Intelligence-Space/Arabic-mpnet-base-all-nli-triplet 0.41
- 118 manu/sentence_croissant_alpha_v0.4 0.41
- 119 infgrad/stella-base-en-v2 0.41
- 120 thenlper/gte-base 0.41
- 121 NovaSearch/stella_en_400M_v5 0.40
- 122 Cohere/Cohere-embed-english-v3.0 0.40
- 123 intfloat/e5-large 0.40
- 124 avsolatorio/GIST-all-MiniLM-L6-v2 0.40
- 125 deepfile/embedder-100p 0.40
- 126 dwzhu/e5-base-4k 0.40
- 127 Mihaiii/gte-micro 0.39
- 128 izhx/udever-bloom-3b 0.39
- 129 Cohere/Cohere-embed-english-light-v3.0 0.39
- 130 minishlab/potion-base-8M 0.39
- 131 minishlab/potion-base-4M 0.39
- 132 Mihaiii/Squirtle 0.39
- 133 intfloat/e5-base 0.39
- 134 Mihaiii/Wartortle 0.39
- 135 abhinand/MedEmbed-small-v0.1 0.38
- 136 BAAI/bge-small-en-v1.5 0.38
- 137 Snowflake/snowflake-arctic-embed-m-long 0.38
- 138 avsolatorio/NoInstruct-small-Embedding-v0 0.38
- 139 sentence-transformers/all-mpnet-base-v2 0.38
- 140 minishlab/M2V_base_glove_subword 0.38
- 141 sentence-transformers/all-MiniLM-L12-v2 0.38
- 142 minishlab/potion-base-2M 0.38
- 143 Mihaiii/gte-micro-v4 0.38
- 144 Mihaiii/Bulbasaur 0.38
- 145 thenlper/gte-large 0.38
- 146 Mihaiii/Ivysaur 0.38
- 147 avsolatorio/GIST-small-Embedding-v0 0.37
- 148 WhereIsAI/UAE-Large-V1 0.37
- 149 minishlab/M2V_base_output 0.37
- 150 Jaume/gemma-2b-embeddings 0.37
- 151 thenlper/gte-small 0.37
- 152 intfloat/e5-small 0.37
- 153 sdadas/mmlw-e5-large 0.37
- 154 sdadas/mmlw-e5-base 0.37
- 155 Mihaiii/Venusaur 0.36
- 156 jinaai/jina-embeddings-v2-small-en 0.36
- 157 mixedbread-ai/mxbai-embed-large-v1 0.36
- 158 Omartificial-Intelligence-Space/Marbert-all-nli-triplet-Matryoshka 0.36
- 159 Omartificial-Intelligence-Space/Arabert-all-nli-triplet-Matryoshka 0.36
- 160 BAAI/bge-large-en-v1.5 0.36
- 161 Snowflake/snowflake-arctic-embed-xs 0.35
- 162 ibm-granite/granite-embedding-30m-english 0.35
- 163 Snowflake/snowflake-arctic-embed-s 0.35
- 164 Snowflake/snowflake-arctic-embed-m-v1.5 0.35
- 165 sdadas/mmlw-e5-small 0.35
- 166 deepvk/USER-base 0.34
- 167 silma-ai/silma-embeddding-matryoshka-v0.1 0.34
- 168 Snowflake/snowflake-arctic-embed-m 0.34
- 169 ai-forever/ru-en-RoSBERTa 0.33
- 170 Snowflake/snowflake-arctic-embed-l 0.32
- 171 deepvk/deberta-v1-base 0.32
- 172 deepvk/USER-bge-m3 0.31
- 173 izhx/udever-bloom-560m 0.30
- 174 consciousAI/cai-lunaris-text-embeddings 0.30
- 175 DeepPavlov/rubert-base-cased-sentence 0.29
- 176 sergeyzh/LaBSE-ru-turbo 0.27
- 177 malenia1/ternary-weight-embedding 0.27
- 178 DeepPavlov/rubert-base-cased 0.27
- 179 jinaai/jina-embedding-b-en-v1 0.27
- 180 sdadas/mmlw-roberta-large 0.27
- 181 aari1995/German_Semantic_STS_V2 0.25
- 182 cointegrated/LaBSE-en-ru 0.25
- 183 sdadas/mmlw-roberta-base 0.25
- 184 sergeyzh/rubert-tiny-turbo 0.25
- 185 cointegrated/rubert-tiny2 0.25
- 186 cointegrated/rubert-tiny 0.25
- 187 minishlab/M2V_base_glove 0.25
- 188 jinaai/jina-embedding-s-en-v1 0.25
- 189 ai-forever/sbert_large_mt_nlu_ru 0.23
- 190 DeepPavlov/distilrubert-small-cased-conversational 0.23
- 191 ai-forever/sbert_large_nlu_ru 0.22
- 192 Hum-Works/lodestone-base-4096-v1 0.19
- 193 jinaai/jina-embeddings-v2-base-en 0.14
Source: MTEB’s leaderboard
- 1
EmbeddingGemma 2 0.65
- 2
Qwen3-Embedding-8B 0.64
- 3
Qwen3-Embedding-4B 0.63
- 4
Qwen3-Embedding-0.6B 0.59
Source: MTEB’s leaderboard
| # | Entry | Score | Setting | Date | Link | Source |
|---|---|---|---|---|---|---|
| 1 | google/gemini-embedding-001 closed weights | 0.73 | ai.google.dev | Official leaderboard | ||
| 2 | tencent/KaLM-Embedding-Gemma3-12B-2511 open weights, 11.8B | 0.71 | huggingface.co | Official leaderboard | ||
| 3 | google/text-multilingual-embedding-002 closed weights | 0.71 | cloud.google.com | Official leaderboard | ||
| 4 | nvidia/llama-embed-nemotron-8b open weights, 7.5B | 0.70 | huggingface.co | Official leaderboard | ||
| 5 | intfloat/multilingual-e5-large-instruct open weights, 0.6B | 0.69 | huggingface.co | Official leaderboard | ||
| 6 | OrdalieTech/Solon-embeddings-large-0.1 open weights, 0.6B | 0.69 | huggingface.co | Official leaderboard | ||
| 7 | codefuse-ai/F2LLM-v2-14B open weights, 14B | 0.68 | huggingface.co | Official leaderboard | ||
| 8 | microsoft/harrier-oss-v1-27b open weights, 27B | 0.68 | huggingface.co | Official leaderboard | ||
| 9 | codefuse-ai/F2LLM-v2-8B open weights, 7.6B | 0.68 | huggingface.co | Official leaderboard | ||
| 10 | microsoft/harrier-oss-v1-0.6b open weights, 0.6B | 0.68 | huggingface.co | Official leaderboard | ||
| 11 | Lajavaness/bilingual-embedding-large open weights, 0.6B | 0.68 | huggingface.co | Official leaderboard | ||
| 12 | Linq-AI-Research/Linq-Embed-Mistral open weights, 7.1B | 0.67 | huggingface.co | Official leaderboard | ||
| 13 | codefuse-ai/F2LLM-v2-4B open weights, 4B | 0.67 | huggingface.co | Official leaderboard | ||
| 14 | Lajavaness/bilingual-embedding-base open weights, 0.3B | 0.67 | huggingface.co | Official leaderboard | ||
| 15 | Salesforce/SFR-Embedding-Mistral open weights, 7.1B | 0.67 | huggingface.co | Official leaderboard | ||
| 16 | Salesforce/SFR-Embedding-2_R open weights, 7.1B | 0.67 | huggingface.co | Official leaderboard | ||
| 17 | nomic-ai/nomic-embed-text-v2-moe open weights, 0.5B | 0.67 | huggingface.co | Official leaderboard | ||
| 18 | manu/bge-m3-custom-fr open weights, 0.6B | 0.66 | huggingface.co | Official leaderboard | ||
| 19 | intfloat/e5-mistral-7b-instruct open weights, 7.1B | 0.66 | huggingface.co | Official leaderboard | ||
| 20 | ai-sage/Giga-Embeddings-instruct-10B-A1.8B-0826 open weights, 10.5B | 0.66 | huggingface.co | Official leaderboard | ||
| 21 | GritLM/GritLM-8x7B open weights, 57.9B | 0.66 | huggingface.co | Official leaderboard | ||
| 22 | Snowflake/snowflake-arctic-embed-l-v2.0 open weights, 0.6B | 0.66 | huggingface.co | Official leaderboard | ||
| 23 | microsoft/harrier-oss-v1-270m open weights, 0.3B | 0.66 | huggingface.co | Official leaderboard | ||
| 24 | codefuse-ai/F2LLM-v2-1.7B open weights, 1.7B | 0.66 | huggingface.co | Official leaderboard | ||
| 25 | ai-sage/Giga-Embeddings-instruct-3B-0826 open weights, 3.2B | 0.66 | huggingface.co | Official leaderboard | ||
| 26 | GritLM/GritLM-7B open weights, 7.2B | 0.66 | huggingface.co | Official leaderboard | ||
| 27 | Lajavaness/bilingual-embedding-small open weights, 0.1B | 0.66 | huggingface.co | Official leaderboard | ||
| 28 | | 0.65 | Oct 2026 | huggingface.co | Official leaderboard | |
| 29 | BAAI/bge-m3 open weights, 0.6B | 0.65 | huggingface.co | Official leaderboard | ||
| 30 | ICT-TIME-and-Querit/ICT-TIME-and-Querit-embedding-v1 open weights, 4B | 0.65 | huggingface.co | Official leaderboard | ||
| 31 | openai/text-embedding-3-large closed weights | 0.65 | openai.com | Official leaderboard | ||
| 32 | Alibaba-NLP/gte-multilingual-base open weights, 0.3B | 0.65 | huggingface.co | Official leaderboard | ||
| 33 | google/embeddinggemma-300m open weights, 0.3B | 0.65 | ai.google.dev | Official leaderboard | ||
| 34 | BidirLM/BidirLM-1B-Embedding open weights, 1B | 0.65 | huggingface.co | Official leaderboard | ||
| 35 | codefuse-ai/F2LLM-v2-330M open weights, 0.3B | 0.65 | huggingface.co | Official leaderboard | ||
| 36 | Omartificial-Intelligence-Space/Arabic-labse-Matryoshka open weights, 0.5B | 0.65 | huggingface.co | Official leaderboard | ||
| 37 | ICT-TIME-and-Querit/BOOM_4B_v1 open weights, 4B | 0.65 | huggingface.co | Official leaderboard | ||
| 38 | mongodb/voyage-multilingual-2 closed weights | 0.65 | blog.voyageai.com | Official leaderboard | ||
| 39 | mongodb/voyage-3.5 closed weights | 0.65 | blog.voyageai.com | Official leaderboard | ||
| 40 | codefuse-ai/F2LLM-v2-0.6B open weights, 0.6B | 0.65 | huggingface.co | Official leaderboard | ||
| 41 | mongodb/voyage-3 closed weights | 0.65 | blog.voyageai.com | Official leaderboard | ||
| 42 | jinaai/jina-embeddings-v3 open weights, 0.6B | 0.65 | huggingface.co | Official leaderboard | ||
| 43 | | 0.64 | Jun 2025 | huggingface.co | Official leaderboard | |
| 44 | BidirLM/BidirLM-Omni-2.5B-Embedding open weights, 2.4B | 0.64 | huggingface.co | Official leaderboard | ||
| 45 | Octen/Octen-Embedding-8B open weights, 7.6B | 0.64 | huggingface.co | Official leaderboard | ||
| 46 | mongodb/voyage-3-lite closed weights | 0.64 | blog.voyageai.com | Official leaderboard | ||
| 47 | HIT-TMG/KaLM-embedding-multilingual-mini-v1 open weights, 0.5B | 0.64 | huggingface.co | Official leaderboard | ||
| 48 | Cohere/Cohere-embed-multilingual-v3.0 closed weights | 0.64 | cohere.com | Official leaderboard | ||
| 49 | Mira190/Euler-Legal-Embedding-V1 open weights, 7.6B | 0.64 | huggingface.co | Official leaderboard | ||
| 50 | | 0.63 | Jun 2025 | huggingface.co | Official leaderboard | |
| 51 | Alibaba-NLP/gte-Qwen2-7B-instruct open weights, 7.1B | 0.63 | huggingface.co | Official leaderboard | ||
| 52 | hotchpotch/bekko-embedding-v1-a25m open weights, 0.1B | 0.63 | huggingface.co | Official leaderboard | ||
| 53 | ibm-granite/granite-embedding-311m-multilingual-r2 open weights, 0.3B | 0.63 | huggingface.co | Official leaderboard | ||
| 54 | hotchpotch/bekko-embedding-v1-a8m open weights, 0.1B | 0.63 | huggingface.co | Official leaderboard | ||
| 55 | sentence-transformers/LaBSE open weights, 0.5B | 0.62 | huggingface.co | Official leaderboard | ||
| 56 | codefuse-ai/F2LLM-v2-160M open weights, 0.2B | 0.62 | huggingface.co | Official leaderboard | ||
| 57 | BidirLM/BidirLM-1.7B-Embedding open weights, 1.7B | 0.62 | huggingface.co | Official leaderboard | ||
| 58 | jinaai/jina-embeddings-v5-omni-nano open weights, 1B | 0.62 | huggingface.co | Official leaderboard | ||
| 59 | jinaai/jina-embeddings-v5-text-nano open weights, 0.2B | 0.62 | huggingface.co | Official leaderboard | ||
| 60 | Alibaba-NLP/gte-Qwen2-1.5B-instruct open weights, 1.5B | 0.62 | huggingface.co | Official leaderboard | ||
| 61 | intfloat/multilingual-e5-small open weights, 0.1B | 0.62 | huggingface.co | Official leaderboard | ||
| 62 | intfloat/multilingual-e5-base open weights, 0.3B | 0.61 | huggingface.co | Official leaderboard | ||
| 63 | ibm-granite/granite-embedding-278m-multilingual open weights, 0.3B | 0.61 | huggingface.co | Official leaderboard | ||
| 64 | jinaai/jina-embeddings-v5-omni-small open weights, 1.6B | 0.61 | huggingface.co | Official leaderboard | ||
| 65 | jinaai/jina-embeddings-v5-text-small open weights, 0.6B | 0.61 | huggingface.co | Official leaderboard | ||
| 66 | openai/text-embedding-3-small closed weights | 0.61 | openai.com | Official leaderboard | ||
| 67 | HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1 open weights, 0.5B | 0.61 | huggingface.co | Official leaderboard | ||
| 68 | Cohere/Cohere-embed-multilingual-light-v3.0 closed weights | 0.61 | cohere.com | Official leaderboard | ||
| 69 | Omartificial-Intelligence-Space/Arabic-all-nli-triplet-Matryoshka open weights, 0.3B | 0.60 | huggingface.co | Official leaderboard | ||
| 70 | hotchpotch/bekko-static-embedding-v1 open weights, 0.2B | 0.60 | huggingface.co | Official leaderboard | ||
| 71 | | 0.59 | Jun 2025 | huggingface.co | Official leaderboard | |
| 72 | codefuse-ai/F2LLM-v2-80M open weights, 0.1B | 0.59 | huggingface.co | Official leaderboard | ||
| 73 | ibm-granite/granite-embedding-97m-multilingual-r2 open weights, 0.1B | 0.59 | huggingface.co | Official leaderboard | ||
| 74 | minishlab/potion-multilingual-128M open weights, 0.1B | 0.59 | huggingface.co | Official leaderboard | ||
| 75 | nvidia/NV-Embed-v2 open weights, 7.9B | 0.59 | huggingface.co | Official leaderboard | ||
| 76 | Snowflake/snowflake-arctic-embed-m-v2.0 open weights, 0.3B | 0.59 | huggingface.co | Official leaderboard | ||
| 77 | omarelshehy/arabic-english-sts-matryoshka open weights, 0.6B | 0.59 | huggingface.co | Official leaderboard | ||
| 78 | BidirLM/BidirLM-270M-Embedding open weights, 0.3B | 0.59 | huggingface.co | Official leaderboard | ||
| 79 | ibm-granite/granite-embedding-107m-multilingual open weights, 0.1B | 0.59 | huggingface.co | Official leaderboard | ||
| 80 | BidirLM/BidirLM-0.6B-Embedding open weights, 0.6B | 0.58 | huggingface.co | Official leaderboard | ||
| 81 | Bytedance/Seed1.6-embedding-1215 closed weights | 0.58 | console.volcengine.com | Official leaderboard | ||
| 82 | Omartificial-Intelligence-Space/Arabic-MiniLM-L12-v2-all-nli-triplet open weights, 0.1B | 0.58 | huggingface.co | Official leaderboard | ||
| 83 | cnmoro/static-nomic-384-pten-v2-st open weights, 0.1B | 0.57 | huggingface.co | Official leaderboard | ||
| 84 | nvidia/NV-Embed-v1 open weights, 7.9B | 0.57 | huggingface.co | Official leaderboard | ||
| 85 | jinaai/jina-embeddings-v4 open weights, 3.9B | 0.56 | huggingface.co | Official leaderboard | ||
| 86 | Gameselo/STS-multilingual-mpnet-base-v2 open weights, 0.3B | 0.56 | huggingface.co | Official leaderboard | ||
| 87 | mongodb/voyage-large-2-instruct closed weights | 0.56 | blog.voyageai.com | Official leaderboard | ||
| 88 | sentence-transformers/paraphrase-multilingual-mpnet-base-v2 open weights, 0.3B | 0.55 | huggingface.co | Official leaderboard | ||
| 89 | Alibaba-NLP/gte-Qwen1.5-7B-instruct open weights, 7.1B | 0.55 | huggingface.co | Official leaderboard | ||
| 90 | NovaSearch/jasper_en_vision_language_v1 open weights, 1.6B | 0.55 | huggingface.co | Official leaderboard | ||
| 91 | sentence-transformers/static-similarity-mrl-multilingual-v1 open weights, 0.1B | 0.52 | huggingface.co | Official leaderboard | ||
| 92 | NovaSearch/stella_en_1.5B_v5 open weights, 1.5B | 0.52 | huggingface.co | Official leaderboard | ||
| 93 | McGill-NLP/LLM2Vec-Mistral-7B-Instruct-v2-mntp-supervised open weights, 7.2B | 0.52 | huggingface.co | Official leaderboard | ||
| 94 | zeroentropy/zembed-1 open weights, 4B | 0.51 | huggingface.co | Official leaderboard | ||
| 95 | Haon-Chen/speed-embedding-7b-instruct open weights, 7.1B | 0.51 | huggingface.co | Official leaderboard | ||
| 96 | bigscience/sgpt-bloom-7b1-msmarco open weights, 7.1B | 0.48 | huggingface.co | Official leaderboard | ||
| 97 | sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 open weights, 0.1B | 0.48 | huggingface.co | Official leaderboard | ||
| 98 | shibing624/text2vec-base-multilingual open weights, 0.1B | 0.48 | huggingface.co | Official leaderboard | ||
| 99 | McGill-NLP/LLM2Vec-Mistral-7B-Instruct-v2-mntp-unsup-simcse open weights, 7.2B | 0.45 | huggingface.co | Official leaderboard | ||
| 100 | izhx/udever-bloom-7b1 open weights | 0.44 | huggingface.co | Official leaderboard | ||
| 101 | intfloat/e5-large-v2 open weights, 0.3B | 0.44 | huggingface.co | Official leaderboard | ||
| 102 | nomic-ai/nomic-embed-text-v1 open weights, 0.1B | 0.44 | huggingface.co | Official leaderboard | ||
| 103 | intfloat/e5-base-v2 open weights, 0.1B | 0.44 | huggingface.co | Official leaderboard | ||
| 104 | nomic-ai/nomic-embed-text-v1-ablated open weights, 0.1B | 0.44 | huggingface.co | Official leaderboard | ||
| 105 | izhx/udever-bloom-1b1 open weights, 1.1B | 0.44 | huggingface.co | Official leaderboard | ||
| 106 | nomic-ai/nomic-embed-text-v1.5 open weights, 0.1B | 0.44 | huggingface.co | Official leaderboard | ||
| 107 | manu/sentence_croissant_alpha_v0.2 open weights, 1.3B | 0.44 | huggingface.co | Official leaderboard | ||
| 108 | manu/sentence_croissant_alpha_v0.3 open weights, 1.3B | 0.43 | huggingface.co | Official leaderboard | ||
| 109 | BAAI/bge-base-en-v1.5 open weights, 0.1B | 0.43 | huggingface.co | Official leaderboard | ||
| 110 | nomic-ai/nomic-embed-text-v1-unsupervised open weights, 0.1B | 0.43 | huggingface.co | Official leaderboard | ||
| 111 | avsolatorio/GIST-Embedding-v0 open weights, 0.1B | 0.43 | huggingface.co | Official leaderboard | ||
| 112 | ibm-granite/granite-embedding-125m-english open weights, 0.1B | 0.42 | huggingface.co | Official leaderboard | ||
| 113 | avsolatorio/GIST-large-Embedding-v0 open weights, 0.3B | 0.42 | huggingface.co | Official leaderboard | ||
| 114 | intfloat/e5-small-v2 open weights, 0B | 0.42 | huggingface.co | Official leaderboard | ||
| 115 | brahmairesearch/slx-v0.1 open weights, 0B | 0.42 | huggingface.co | Official leaderboard | ||
| 116 | sentence-transformers/all-MiniLM-L6-v2 open weights, 0B | 0.42 | huggingface.co | Official leaderboard | ||
| 117 | Omartificial-Intelligence-Space/Arabic-mpnet-base-all-nli-triplet open weights, 0.1B | 0.41 | huggingface.co | Official leaderboard | ||
| 118 | manu/sentence_croissant_alpha_v0.4 open weights, 1.3B | 0.41 | huggingface.co | Official leaderboard | ||
| 119 | infgrad/stella-base-en-v2 open weights, 0.1B | 0.41 | huggingface.co | Official leaderboard | ||
| 120 | thenlper/gte-base open weights, 0.1B | 0.41 | huggingface.co | Official leaderboard | ||
| 121 | NovaSearch/stella_en_400M_v5 open weights, 0.4B | 0.40 | huggingface.co | Official leaderboard | ||
| 122 | Cohere/Cohere-embed-english-v3.0 closed weights | 0.40 | cohere.com | Official leaderboard | ||
| 123 | intfloat/e5-large open weights, 0.3B | 0.40 | huggingface.co | Official leaderboard | ||
| 124 | avsolatorio/GIST-all-MiniLM-L6-v2 open weights, 0B | 0.40 | huggingface.co | Official leaderboard | ||
| 125 | deepfile/embedder-100p open weights, 0.3B | 0.40 | huggingface.co | Official leaderboard | ||
| 126 | dwzhu/e5-base-4k open weights, 0.1B | 0.40 | huggingface.co | Official leaderboard | ||
| 127 | Mihaiii/gte-micro open weights, 0B | 0.39 | huggingface.co | Official leaderboard | ||
| 128 | izhx/udever-bloom-3b open weights, 3B | 0.39 | huggingface.co | Official leaderboard | ||
| 129 | Cohere/Cohere-embed-english-light-v3.0 closed weights | 0.39 | cohere.com | Official leaderboard | ||
| 130 | minishlab/potion-base-8M open weights, 0B | 0.39 | huggingface.co | Official leaderboard | ||
| 131 | minishlab/potion-base-4M open weights, 0B | 0.39 | huggingface.co | Official leaderboard | ||
| 132 | Mihaiii/Squirtle open weights, 0B | 0.39 | huggingface.co | Official leaderboard | ||
| 133 | intfloat/e5-base open weights, 0.1B | 0.39 | huggingface.co | Official leaderboard | ||
| 134 | Mihaiii/Wartortle open weights, 0B | 0.39 | huggingface.co | Official leaderboard | ||
| 135 | abhinand/MedEmbed-small-v0.1 open weights, 0B | 0.38 | huggingface.co | Official leaderboard | ||
| 136 | BAAI/bge-small-en-v1.5 open weights, 0B | 0.38 | huggingface.co | Official leaderboard | ||
| 137 | Snowflake/snowflake-arctic-embed-m-long open weights, 0.1B | 0.38 | huggingface.co | Official leaderboard | ||
| 138 | avsolatorio/NoInstruct-small-Embedding-v0 open weights, 0B | 0.38 | huggingface.co | Official leaderboard | ||
| 139 | sentence-transformers/all-mpnet-base-v2 open weights, 0.1B | 0.38 | huggingface.co | Official leaderboard | ||
| 140 | minishlab/M2V_base_glove_subword open weights, 0.1B | 0.38 | huggingface.co | Official leaderboard | ||
| 141 | sentence-transformers/all-MiniLM-L12-v2 open weights, 0B | 0.38 | huggingface.co | Official leaderboard | ||
| 142 | minishlab/potion-base-2M open weights, 0B | 0.38 | huggingface.co | Official leaderboard | ||
| 143 | Mihaiii/gte-micro-v4 open weights, 0B | 0.38 | huggingface.co | Official leaderboard | ||
| 144 | Mihaiii/Bulbasaur open weights, 0B | 0.38 | huggingface.co | Official leaderboard | ||
| 145 | thenlper/gte-large open weights, 0.3B | 0.38 | huggingface.co | Official leaderboard | ||
| 146 | Mihaiii/Ivysaur open weights, 0B | 0.38 | huggingface.co | Official leaderboard | ||
| 147 | avsolatorio/GIST-small-Embedding-v0 open weights, 0B | 0.37 | huggingface.co | Official leaderboard | ||
| 148 | WhereIsAI/UAE-Large-V1 open weights, 0.3B | 0.37 | huggingface.co | Official leaderboard | ||
| 149 | minishlab/M2V_base_output open weights, 0B | 0.37 | huggingface.co | Official leaderboard | ||
| 150 | Jaume/gemma-2b-embeddings open weights, 2.5B | 0.37 | huggingface.co | Official leaderboard | ||
| 151 | thenlper/gte-small open weights, 0B | 0.37 | huggingface.co | Official leaderboard | ||
| 152 | intfloat/e5-small open weights, 0B | 0.37 | huggingface.co | Official leaderboard | ||
| 153 | sdadas/mmlw-e5-large open weights, 0.6B | 0.37 | huggingface.co | Official leaderboard | ||
| 154 | sdadas/mmlw-e5-base open weights, 0.3B | 0.37 | huggingface.co | Official leaderboard | ||
| 155 | Mihaiii/Venusaur open weights, 0B | 0.36 | huggingface.co | Official leaderboard | ||
| 156 | jinaai/jina-embeddings-v2-small-en open weights, 0B | 0.36 | huggingface.co | Official leaderboard | ||
| 157 | mixedbread-ai/mxbai-embed-large-v1 open weights, 0.3B | 0.36 | huggingface.co | Official leaderboard | ||
| 158 | Omartificial-Intelligence-Space/Marbert-all-nli-triplet-Matryoshka open weights, 0.2B | 0.36 | huggingface.co | Official leaderboard | ||
| 159 | Omartificial-Intelligence-Space/Arabert-all-nli-triplet-Matryoshka open weights, 0.1B | 0.36 | huggingface.co | Official leaderboard | ||
| 160 | BAAI/bge-large-en-v1.5 open weights, 0.3B | 0.36 | huggingface.co | Official leaderboard | ||
| 161 | Snowflake/snowflake-arctic-embed-xs open weights, 0B | 0.35 | huggingface.co | Official leaderboard | ||
| 162 | ibm-granite/granite-embedding-30m-english open weights, 0B | 0.35 | huggingface.co | Official leaderboard | ||
| 163 | Snowflake/snowflake-arctic-embed-s open weights, 0B | 0.35 | huggingface.co | Official leaderboard | ||
| 164 | Snowflake/snowflake-arctic-embed-m-v1.5 open weights, 0.1B | 0.35 | huggingface.co | Official leaderboard | ||
| 165 | sdadas/mmlw-e5-small open weights, 0.1B | 0.35 | huggingface.co | Official leaderboard | ||
| 166 | deepvk/USER-base open weights, 0.4B | 0.34 | huggingface.co | Official leaderboard | ||
| 167 | silma-ai/silma-embeddding-matryoshka-v0.1 open weights, 0.1B | 0.34 | huggingface.co | Official leaderboard | ||
| 168 | Snowflake/snowflake-arctic-embed-m open weights, 0.1B | 0.34 | huggingface.co | Official leaderboard | ||
| 169 | ai-forever/ru-en-RoSBERTa open weights, 0.4B | 0.33 | huggingface.co | Official leaderboard | ||
| 170 | Snowflake/snowflake-arctic-embed-l open weights, 0.3B | 0.32 | huggingface.co | Official leaderboard | ||
| 171 | deepvk/deberta-v1-base open weights, 0.1B | 0.32 | huggingface.co | Official leaderboard | ||
| 172 | deepvk/USER-bge-m3 open weights, 0.4B | 0.31 | huggingface.co | Official leaderboard | ||
| 173 | izhx/udever-bloom-560m open weights, 0.6B | 0.30 | huggingface.co | Official leaderboard | ||
| 174 | consciousAI/cai-lunaris-text-embeddings open weights, 0.3B | 0.30 | huggingface.co | Official leaderboard | ||
| 175 | DeepPavlov/rubert-base-cased-sentence open weights, 0.1B | 0.29 | huggingface.co | Official leaderboard | ||
| 176 | sergeyzh/LaBSE-ru-turbo open weights, 0.1B | 0.27 | huggingface.co | Official leaderboard | ||
| 177 | malenia1/ternary-weight-embedding open weights, 0.1B | 0.27 | huggingface.co | Official leaderboard | ||
| 178 | DeepPavlov/rubert-base-cased open weights, 1.3B | 0.27 | huggingface.co | Official leaderboard | ||
| 179 | jinaai/jina-embedding-b-en-v1 open weights, 0.1B | 0.27 | huggingface.co | Official leaderboard | ||
| 180 | sdadas/mmlw-roberta-large open weights, 0.4B | 0.27 | huggingface.co | Official leaderboard | ||
| 181 | aari1995/German_Semantic_STS_V2 open weights, 0.3B | 0.25 | huggingface.co | Official leaderboard | ||
| 182 | cointegrated/LaBSE-en-ru open weights, 0.1B | 0.25 | huggingface.co | Official leaderboard | ||
| 183 | sdadas/mmlw-roberta-base open weights, 0.1B | 0.25 | huggingface.co | Official leaderboard | ||
| 184 | sergeyzh/rubert-tiny-turbo open weights, 0B | 0.25 | huggingface.co | Official leaderboard | ||
| 185 | cointegrated/rubert-tiny2 open weights, 0B | 0.25 | huggingface.co | Official leaderboard | ||
| 186 | cointegrated/rubert-tiny open weights, 0B | 0.25 | huggingface.co | Official leaderboard | ||
| 187 | minishlab/M2V_base_glove open weights, 0.1B | 0.25 | huggingface.co | Official leaderboard | ||
| 188 | jinaai/jina-embedding-s-en-v1 open weights, 0B | 0.25 | huggingface.co | Official leaderboard | ||
| 189 | ai-forever/sbert_large_mt_nlu_ru open weights, 0.4B | 0.23 | huggingface.co | Official leaderboard | ||
| 190 | DeepPavlov/distilrubert-small-cased-conversational open weights, 0.1B | 0.23 | huggingface.co | Official leaderboard | ||
| 191 | ai-forever/sbert_large_nlu_ru open weights, 0.4B | 0.22 | huggingface.co | Official leaderboard | ||
| 192 | Hum-Works/lodestone-base-4096-v1 open weights, 0.1B | 0.19 | huggingface.co | Official leaderboard | ||
| 193 | jinaai/jina-embeddings-v2-base-en open weights, 0.1B | 0.14 | huggingface.co | Official leaderboard |
| # | Model | Score | Setting | Date | Link | Source |
|---|---|---|---|---|---|---|
| 1 | | 0.65 | Oct 2026 | huggingface.co | Official leaderboard | |
| 2 | | 0.64 | Jun 2025 | huggingface.co | Official leaderboard | |
| 3 | | 0.63 | Jun 2025 | huggingface.co | Official leaderboard | |
| 4 | | 0.59 | Jun 2025 | huggingface.co | Official leaderboard |
Rankings by part
We read 12 parts from MTEB’s leaderboard, each ranking models on one part of the test, such as Afrikaans, Amharic and Standard Arabic. EmbeddingGemma 2 leads 8 of them, and 2 other models lead the rest. Arrows show how far a model moved from its overall rank among the models we track.
Afrikaans
4 models we track have a score here.
- 1
EmbeddingGemma 2 0.79
- 2
Qwen3-Embedding-4B ↑1 0.79
- 3
Qwen3-Embedding-8B ↓1 0.79
- 4
Qwen3-Embedding-0.6B 0.75
Amharic
4 models we track have a score here.
- 1
EmbeddingGemma 2 0.78
- 2
Qwen3-Embedding-8B 0.78
- 3
Qwen3-Embedding-4B 0.73
- 4
Qwen3-Embedding-0.6B 0.60
Standard Arabic
4 models we track have a score here.
- 1
Qwen3-Embedding-4B ↑2 0.63
- 2
Qwen3-Embedding-8B 0.62
- 3
EmbeddingGemma 2 ↓2 0.58
- 4
Qwen3-Embedding-0.6B 0.55
Algerian Arabic
4 models we track have a score here.
- 1
EmbeddingGemma 2 0.47
- 2
Qwen3-Embedding-8B 0.41
- 3
Qwen3-Embedding-4B 0.40
- 4
Qwen3-Embedding-0.6B 0.35
Moroccan Arabic
4 models we track have a score here.
- 1
EmbeddingGemma 2 0.47
- 2
Qwen3-Embedding-8B 0.44
- 3
Qwen3-Embedding-4B 0.35
- 4
Qwen3-Embedding-0.6B 0.35
English
4 models we track have a score here.
- 1
EmbeddingGemma 2 0.84
- 2
Qwen3-Embedding-4B ↑1 0.83
- 3
Qwen3-Embedding-8B ↓1 0.82
- 4
Qwen3-Embedding-0.6B 0.82
Hausa
4 models we track have a score here.
- 1
EmbeddingGemma 2 0.46
- 2
Qwen3-Embedding-4B ↑1 0.44
- 3
Qwen3-Embedding-8B ↓1 0.44
- 4
Qwen3-Embedding-0.6B 0.41
Hindi
4 models we track have a score here.
- 1
EmbeddingGemma 2 0.79
- 2
Qwen3-Embedding-8B 0.78
- 3
Qwen3-Embedding-4B 0.77
- 4
Qwen3-Embedding-0.6B 0.74
Indonesian
4 models we track have a score here.
- 1
EmbeddingGemma 2 0.50
- 2
Qwen3-Embedding-0.6B ↑2 0.48
- 3
Qwen3-Embedding-8B ↓1 0.47
- 4
Qwen3-Embedding-4B ↓1 0.46
Kinyarwanda
4 models we track have a score here.
- 1
Qwen3-Embedding-8B ↑1 0.52
- 2
Qwen3-Embedding-0.6B ↑2 0.51
- 3
EmbeddingGemma 2 ↓2 0.51
- 4
Qwen3-Embedding-4B ↓1 0.51
Marathi
4 models we track have a score here.
- 1
Qwen3-Embedding-4B ↑2 0.83
- 2
EmbeddingGemma 2 ↓1 0.81
- 3
Qwen3-Embedding-8B ↓1 0.81
- 4
Qwen3-Embedding-0.6B 0.75
Telugu
4 models we track have a score here.
- 1
Qwen3-Embedding-8B ↑1 0.85
- 2
EmbeddingGemma 2 ↓1 0.84
- 3
Qwen3-Embedding-4B 0.84
- 4
Qwen3-Embedding-0.6B 0.79
2 models have held number one on MTEB’s leaderboard since its release in March 2024
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 Multilingual
- MMMLU In use MMLU professionally translated into 14 languages. Multiple-choice accuracy. Claude Mythos Preview 92.7%
- WMT24++ In use English-to-55-language translation of WMT24 test data. Scored with automatic metrics such as MetricX or xCOMET.
K-EXAONE 90.5%
- MMLU-ProX In use MMLU-Pro translated into up to 29 languages with expert review. Multiple-choice accuracy per language.
Qwen3.7-Max 87%
- CLIcK In use Models answer 1,995 multiple-choice questions on Korean language and culture. Questions come from official Korean exams and textbooks in eleven categories.
Solar Open 2 90.7%
- Global MMLU Lite 3.0 In use Models answer 400 human-translated MMLU questions per language in 23 languages. Version 3.0 adds Czech, Hungarian, Oriya, Slovak and Tajik and updates Italian. Accuracy. Claude Opus 5 95.7%
- MMMB In use Models answer multiple-choice questions about images in six languages across 15 categories. The set has about 12,000 questions. LFM2.5-VL-3B 83%
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 4 models we track, plus 189 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 189 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.