SemEval 2022 Task 8 multilingual news article similarity
Models rate the similarity of two news articles, including articles in different languages. The evaluation compares predicted similarities with human judgments.
- Made by
- Xi Chen and colleagues
- Released
- July 2022
- Kind
- Reading in many languages
- Level
- School
- Scored
- Checked automatically
- Answers
- Prediction
- Tasks
- All public
- Measures
- Capability
- Language
- Many languages
- Interaction
- Single turn
- Items from
- Real work and use
- Refresh
- One fixed set
- Run by
- Anyone
- In views
- Many languages
- Last model added
- June 2025
- Scores refreshed
- November 20th, 2026
Qwen3-Embedding-8B leads with 0.72 among models released by June 2025 Qwen3-Embedding-8B leads with 0.72 among models released by June 2025
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. This view shows only models we track, each at its best.
The newest model with a score here came out in June 2025, 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 Astra
- and 16 more
- 0.72
Qwen3-Embedding-8B
- 0.72
Qwen3-Embedding-4B
- 0.71
Qwen3-Embedding-0.6B
- 0.69 microsoft/harrier-oss-v1-0.6b
- 0.69 Lajavaness/bilingual-embedding-large
- 0.69 jinaai/jina-embeddings-v3
- 0.69 microsoft/harrier-oss-v1-270m
- 0.68 OrdalieTech/Solon-embeddings-large-0.1
- 0.68 Linq-AI-Research/Linq-Embed-Mistral
- 0.68 NovaSearch/jasper_en_vision_language_v1
- 0.67 Alibaba-NLP/gte-multilingual-base
- 0.67 Alibaba-NLP/gte-Qwen2-7B-instruct
- 0.67 Cohere/Cohere-embed-multilingual-v3.0
- 0.67 manu/bge-m3-custom-fr
- 0.67 Alibaba-NLP/gte-Qwen2-1.5B-instruct
- 0.67 intfloat/multilingual-e5-large-instruct
- 0.67 Salesforce/SFR-Embedding-Mistral
- 0.67 Alibaba-NLP/gte-Qwen1.5-7B-instruct
- 0.67 NovaSearch/stella_en_1.5B_v5
- 0.67 Lajavaness/bilingual-embedding-small
- 0.66 Cohere/Cohere-embed-multilingual-light-v3.0
- 0.66 Snowflake/snowflake-arctic-embed-l-v2.0
- 0.66 ibm-granite/granite-embedding-278m-multilingual
- 0.66 amazon/Titan-text-embeddings-v2
- 0.66 intfloat/e5-mistral-7b-instruct
- 0.66 Salesforce/SFR-Embedding-2_R
- 0.65 Lajavaness/bilingual-embedding-base
- 0.65 ibm-granite/granite-embedding-107m-multilingual
- 0.65 omarelshehy/arabic-english-sts-matryoshka
- 0.64 intfloat/multilingual-e5-small
- 0.63 intfloat/multilingual-e5-base
- 0.62 deepvk/USER-bge-m3
- 0.62 Omartificial-Intelligence-Space/Arabic-labse-Matryoshka
- 0.62 manu/sentence_croissant_alpha_v0.4
- 0.61 sentence-transformers/LaBSE
- 0.60 manu/sentence_croissant_alpha_v0.3
- 0.60 McGill-NLP/LLM2Vec-Mistral-7B-Instruct-v2-mntp-supervised
- 0.60 NovaSearch/stella_en_400M_v5
- 0.60 Omartificial-Intelligence-Space/Arabic-all-nli-triplet-Matryoshka
- 0.59 sentence-transformers/paraphrase-multilingual-mpnet-base-v2
- 0.58 Omartificial-Intelligence-Space/Arabic-MiniLM-L12-v2-all-nli-triplet
- 0.58 Cohere/Cohere-embed-english-v3.0
- 0.58 manu/sentence_croissant_alpha_v0.2
- 0.55 nomic-ai/nomic-embed-text-v1-unsupervised
- 0.55 bigscience/sgpt-bloom-7b1-msmarco
- 0.55 intfloat/e5-large-v2
- 0.55 sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
- 0.54 nomic-ai/nomic-embed-text-v1
- 0.54 intfloat/e5-large
- 0.53 thenlper/gte-large
- 0.53 sdadas/mmlw-e5-large
- 0.53 cointegrated/LaBSE-en-ru
- 0.52 avsolatorio/GIST-large-Embedding-v0
- 0.52 sentence-transformers/gtr-t5-xl
- 0.52 McGill-NLP/LLM2Vec-Mistral-7B-Instruct-v2-mntp-unsup-simcse
- 0.52 sergeyzh/LaBSE-ru-turbo
- 0.51 thenlper/gte-small
- 0.50 deepfile/embedder-100p
- 0.50 ibm-granite/granite-embedding-125m-english
- 0.50 Mihaiii/Ivysaur
- 0.50 sdadas/mmlw-e5-small
- 0.50 intfloat/e5-base-v2
- 0.50 avsolatorio/GIST-small-Embedding-v0
- 0.50 infgrad/stella-base-en-v2
- 0.50 thenlper/gte-base
- 0.50 sentence-transformers/gtr-t5-large
- 0.50 sentence-transformers/sentence-t5-xl
- 0.49 nomic-ai/nomic-embed-text-v1.5
- 0.49 intfloat/e5-base
- 0.49 intfloat/e5-small
- 0.49 mixedbread-ai/mxbai-embed-large-v1
- 0.49 WhereIsAI/UAE-Large-V1
- 0.49 sdadas/mmlw-roberta-large
- 0.49 avsolatorio/GIST-Embedding-v0
- 0.48 sdadas/mmlw-e5-base
- 0.48 ibm-granite/granite-embedding-30m-english
- 0.48 Cohere/Cohere-embed-english-light-v3.0
- 0.48 dwzhu/e5-base-4k
- 0.48 jinaai/jina-embedding-b-en-v1
- 0.47 Snowflake/snowflake-arctic-embed-s
- 0.47 BAAI/bge-large-en-v1.5
- 0.47 sdadas/mmlw-roberta-base
- 0.46
sonar
- 0.46 abhinand/MedEmbed-small-v0.1
- 0.45 spartan8806/atles-champion-embedding
- 0.45 BAAI/bge-small-en-v1.5
- 0.45 BAAI/bge-base-en-v1.5
- 0.45 sentence-transformers/sentence-t5-large
- 0.44 intfloat/e5-small-v2
- 0.44 sentence-transformers/sentence-t5-base
- 0.43 jinaai/jina-embedding-s-en-v1
- 0.42 deepvk/USER-base
- 0.42 sentence-transformers/multi-qa-MiniLM-L6-cos-v1
- 0.42 Snowflake/snowflake-arctic-embed-l
- 0.42 avsolatorio/GIST-all-MiniLM-L6-v2
- 0.42 ai-forever/ru-en-RoSBERTa
- 0.41 aari1995/German_Semantic_STS_V2
- 0.40 brahmairesearch/slx-v0.1
- 0.40 sentence-transformers/all-MiniLM-L6-v2
- 0.40 consciousAI/cai-lunaris-text-embeddings
- 0.40 Snowflake/snowflake-arctic-embed-m-v1.5
- 0.38 silma-ai/silma-embeddding-matryoshka-v0.1
- 0.37 Mihaiii/Wartortle
- 0.37 Snowflake/snowflake-arctic-embed-xs
- 0.36 Mihaiii/gte-micro-v4
- 0.35 Mihaiii/Venusaur
- 0.35 Mihaiii/Bulbasaur
- 0.34 Mihaiii/Squirtle
- 0.34 Snowflake/snowflake-arctic-embed-m
- 0.33 DeepPavlov/rubert-base-cased-sentence
- 0.33 Omartificial-Intelligence-Space/Arabert-all-nli-triplet-Matryoshka
- 0.33 sergeyzh/rubert-tiny-turbo
- 0.32 minishlab/potion-base-8M
- 0.31 minishlab/potion-base-2M
- 0.31 minishlab/potion-base-4M
- 0.30 minishlab/M2V_base_output
- 0.30 dmedhi/PawanEmbd-68M
- 0.29 Mihaiii/gte-micro
- 0.29 Omartificial-Intelligence-Space/Arabic-mpnet-base-all-nli-triplet
- 0.27 cointegrated/rubert-tiny2
- 0.26 ai-forever/sbert_large_nlu_ru
- 0.26 Omartificial-Intelligence-Space/Marbert-all-nli-triplet-Matryoshka
- 0.24 cointegrated/rubert-tiny
- 0.23 DeepPavlov/distilrubert-small-cased-conversational
- 0.23 DeepPavlov/rubert-base-cased
- 0.22 ai-forever/sbert_large_mt_nlu_ru
- 0.20 deepvk/deberta-v1-base
- 1
Qwen3-Embedding-8B 0.72
- 2
Qwen3-Embedding-4B 0.72
- 3
Qwen3-Embedding-0.6B 0.71
- 4 microsoft/harrier-oss-v1-0.6b 0.69
- 5 Lajavaness/bilingual-embedding-large 0.69
- 6 jinaai/jina-embeddings-v3 0.69
- 7 microsoft/harrier-oss-v1-270m 0.69
- 8 OrdalieTech/Solon-embeddings-large-0.1 0.68
- 9 Linq-AI-Research/Linq-Embed-Mistral 0.68
- 10 NovaSearch/jasper_en_vision_language_v1 0.68
- 11 Alibaba-NLP/gte-multilingual-base 0.67
- 12 Alibaba-NLP/gte-Qwen2-7B-instruct 0.67
- 13 Cohere/Cohere-embed-multilingual-v3.0 0.67
- 14 manu/bge-m3-custom-fr 0.67
- 15 Alibaba-NLP/gte-Qwen2-1.5B-instruct 0.67
- 16 intfloat/multilingual-e5-large-instruct 0.67
- 17 Salesforce/SFR-Embedding-Mistral 0.67
- 18 Alibaba-NLP/gte-Qwen1.5-7B-instruct 0.67
- 19 NovaSearch/stella_en_1.5B_v5 0.67
- 20 Lajavaness/bilingual-embedding-small 0.67
- 21 Cohere/Cohere-embed-multilingual-light-v3.0 0.66
- 22 Snowflake/snowflake-arctic-embed-l-v2.0 0.66
- 23 ibm-granite/granite-embedding-278m-multilingual 0.66
- 24 amazon/Titan-text-embeddings-v2 0.66
- 25 intfloat/e5-mistral-7b-instruct 0.66
- 26 Salesforce/SFR-Embedding-2_R 0.66
- 27 Lajavaness/bilingual-embedding-base 0.65
- 28 ibm-granite/granite-embedding-107m-multilingual 0.65
- 29 omarelshehy/arabic-english-sts-matryoshka 0.65
- 30 intfloat/multilingual-e5-small 0.64
- 31 intfloat/multilingual-e5-base 0.63
- 32 deepvk/USER-bge-m3 0.62
- 33 Omartificial-Intelligence-Space/Arabic-labse-Matryoshka 0.62
- 34 manu/sentence_croissant_alpha_v0.4 0.62
- 35 sentence-transformers/LaBSE 0.61
- 36 manu/sentence_croissant_alpha_v0.3 0.60
- 37 McGill-NLP/LLM2Vec-Mistral-7B-Instruct-v2-mntp-supervised 0.60
- 38 NovaSearch/stella_en_400M_v5 0.60
- 39 Omartificial-Intelligence-Space/Arabic-all-nli-triplet-Matryoshka 0.60
- 40 sentence-transformers/paraphrase-multilingual-mpnet-base-v2 0.59
- 41 Omartificial-Intelligence-Space/Arabic-MiniLM-L12-v2-all-nli-triplet 0.58
- 42 Cohere/Cohere-embed-english-v3.0 0.58
- 43 manu/sentence_croissant_alpha_v0.2 0.58
- 44 nomic-ai/nomic-embed-text-v1-unsupervised 0.55
- 45 bigscience/sgpt-bloom-7b1-msmarco 0.55
- 46 intfloat/e5-large-v2 0.55
- 47 sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 0.55
- 48 nomic-ai/nomic-embed-text-v1 0.54
- 49 intfloat/e5-large 0.54
- 50 thenlper/gte-large 0.53
- 51 sdadas/mmlw-e5-large 0.53
- 52 cointegrated/LaBSE-en-ru 0.53
- 53 avsolatorio/GIST-large-Embedding-v0 0.52
- 54 sentence-transformers/gtr-t5-xl 0.52
- 55 McGill-NLP/LLM2Vec-Mistral-7B-Instruct-v2-mntp-unsup-simcse 0.52
- 56 sergeyzh/LaBSE-ru-turbo 0.52
- 57 thenlper/gte-small 0.51
- 58 deepfile/embedder-100p 0.50
- 59 ibm-granite/granite-embedding-125m-english 0.50
- 60 Mihaiii/Ivysaur 0.50
- 61 sdadas/mmlw-e5-small 0.50
- 62 intfloat/e5-base-v2 0.50
- 63 avsolatorio/GIST-small-Embedding-v0 0.50
- 64 infgrad/stella-base-en-v2 0.50
- 65 thenlper/gte-base 0.50
- 66 sentence-transformers/gtr-t5-large 0.50
- 67 sentence-transformers/sentence-t5-xl 0.50
- 68 nomic-ai/nomic-embed-text-v1.5 0.49
- 69 intfloat/e5-base 0.49
- 70 intfloat/e5-small 0.49
- 71 mixedbread-ai/mxbai-embed-large-v1 0.49
- 72 WhereIsAI/UAE-Large-V1 0.49
- 73 sdadas/mmlw-roberta-large 0.49
- 74 avsolatorio/GIST-Embedding-v0 0.49
- 75 sdadas/mmlw-e5-base 0.48
- 76 ibm-granite/granite-embedding-30m-english 0.48
- 77 Cohere/Cohere-embed-english-light-v3.0 0.48
- 78 dwzhu/e5-base-4k 0.48
- 79 jinaai/jina-embedding-b-en-v1 0.48
- 80 Snowflake/snowflake-arctic-embed-s 0.47
- 81 BAAI/bge-large-en-v1.5 0.47
- 82 sdadas/mmlw-roberta-base 0.47
- 83
sonar 0.46
- 84 abhinand/MedEmbed-small-v0.1 0.46
- 85 spartan8806/atles-champion-embedding 0.45
- 86 BAAI/bge-small-en-v1.5 0.45
- 87 BAAI/bge-base-en-v1.5 0.45
- 88 sentence-transformers/sentence-t5-large 0.45
- 89 intfloat/e5-small-v2 0.44
- 90 sentence-transformers/sentence-t5-base 0.44
- 91 jinaai/jina-embedding-s-en-v1 0.43
- 92 deepvk/USER-base 0.42
- 93 sentence-transformers/multi-qa-MiniLM-L6-cos-v1 0.42
- 94 Snowflake/snowflake-arctic-embed-l 0.42
- 95 avsolatorio/GIST-all-MiniLM-L6-v2 0.42
- 96 ai-forever/ru-en-RoSBERTa 0.42
- 97 aari1995/German_Semantic_STS_V2 0.41
- 98 brahmairesearch/slx-v0.1 0.40
- 99 sentence-transformers/all-MiniLM-L6-v2 0.40
- 100 consciousAI/cai-lunaris-text-embeddings 0.40
- 101 Snowflake/snowflake-arctic-embed-m-v1.5 0.40
- 102 silma-ai/silma-embeddding-matryoshka-v0.1 0.38
- 103 Mihaiii/Wartortle 0.37
- 104 Snowflake/snowflake-arctic-embed-xs 0.37
- 105 Mihaiii/gte-micro-v4 0.36
- 106 Mihaiii/Venusaur 0.35
- 107 Mihaiii/Bulbasaur 0.35
- 108 Mihaiii/Squirtle 0.34
- 109 Snowflake/snowflake-arctic-embed-m 0.34
- 110 DeepPavlov/rubert-base-cased-sentence 0.33
- 111 Omartificial-Intelligence-Space/Arabert-all-nli-triplet-Matryoshka 0.33
- 112 sergeyzh/rubert-tiny-turbo 0.33
- 113 minishlab/potion-base-8M 0.32
- 114 minishlab/potion-base-2M 0.31
- 115 minishlab/potion-base-4M 0.31
- 116 minishlab/M2V_base_output 0.30
- 117 dmedhi/PawanEmbd-68M 0.30
- 118 Mihaiii/gte-micro 0.29
- 119 Omartificial-Intelligence-Space/Arabic-mpnet-base-all-nli-triplet 0.29
- 120 cointegrated/rubert-tiny2 0.27
- 121 ai-forever/sbert_large_nlu_ru 0.26
- 122 Omartificial-Intelligence-Space/Marbert-all-nli-triplet-Matryoshka 0.26
- 123 cointegrated/rubert-tiny 0.24
- 124 DeepPavlov/distilrubert-small-cased-conversational 0.23
- 125 DeepPavlov/rubert-base-cased 0.23
- 126 ai-forever/sbert_large_mt_nlu_ru 0.22
- 127 deepvk/deberta-v1-base 0.20
Source: MTEB’s leaderboard
- 1
Qwen3-Embedding-8B 0.72
- 2
Qwen3-Embedding-4B 0.72
- 3
Qwen3-Embedding-0.6B 0.71
- 4
sonar 0.46
Source: MTEB’s leaderboard
| # | Entry | Score | Setting | Date | Link | Source |
|---|---|---|---|---|---|---|
| 1 | | 0.72 | Jun 2025 | huggingface.co | Official leaderboard | |
| 2 | | 0.72 | Jun 2025 | huggingface.co | Official leaderboard | |
| 3 | | 0.71 | Jun 2025 | huggingface.co | Official leaderboard | |
| 4 | microsoft/harrier-oss-v1-0.6b open weights, 0.6B | 0.69 | huggingface.co | Official leaderboard | ||
| 5 | Lajavaness/bilingual-embedding-large open weights, 0.6B | 0.69 | huggingface.co | Official leaderboard | ||
| 6 | jinaai/jina-embeddings-v3 open weights, 0.6B | 0.69 | huggingface.co | Official leaderboard | ||
| 7 | microsoft/harrier-oss-v1-270m open weights, 0.3B | 0.69 | huggingface.co | Official leaderboard | ||
| 8 | OrdalieTech/Solon-embeddings-large-0.1 open weights, 0.6B | 0.68 | huggingface.co | Official leaderboard | ||
| 9 | Linq-AI-Research/Linq-Embed-Mistral open weights, 7.1B | 0.68 | huggingface.co | Official leaderboard | ||
| 10 | NovaSearch/jasper_en_vision_language_v1 open weights, 1.6B | 0.68 | huggingface.co | Official leaderboard | ||
| 11 | Alibaba-NLP/gte-multilingual-base open weights, 0.3B | 0.67 | huggingface.co | Official leaderboard | ||
| 12 | Alibaba-NLP/gte-Qwen2-7B-instruct open weights, 7.1B | 0.67 | huggingface.co | Official leaderboard | ||
| 13 | Cohere/Cohere-embed-multilingual-v3.0 closed weights | 0.67 | cohere.com | Official leaderboard | ||
| 14 | manu/bge-m3-custom-fr open weights, 0.6B | 0.67 | huggingface.co | Official leaderboard | ||
| 15 | Alibaba-NLP/gte-Qwen2-1.5B-instruct open weights, 1.5B | 0.67 | huggingface.co | Official leaderboard | ||
| 16 | intfloat/multilingual-e5-large-instruct open weights, 0.6B | 0.67 | huggingface.co | Official leaderboard | ||
| 17 | Salesforce/SFR-Embedding-Mistral open weights, 7.1B | 0.67 | huggingface.co | Official leaderboard | ||
| 18 | Alibaba-NLP/gte-Qwen1.5-7B-instruct open weights, 7.1B | 0.67 | huggingface.co | Official leaderboard | ||
| 19 | NovaSearch/stella_en_1.5B_v5 open weights, 1.5B | 0.67 | huggingface.co | Official leaderboard | ||
| 20 | Lajavaness/bilingual-embedding-small open weights, 0.1B | 0.67 | huggingface.co | Official leaderboard | ||
| 21 | Cohere/Cohere-embed-multilingual-light-v3.0 closed weights | 0.66 | cohere.com | Official leaderboard | ||
| 22 | Snowflake/snowflake-arctic-embed-l-v2.0 open weights, 0.6B | 0.66 | huggingface.co | Official leaderboard | ||
| 23 | ibm-granite/granite-embedding-278m-multilingual open weights, 0.3B | 0.66 | huggingface.co | Official leaderboard | ||
| 24 | amazon/Titan-text-embeddings-v2 closed weights | 0.66 | huggingface.co | Official leaderboard | ||
| 25 | intfloat/e5-mistral-7b-instruct open weights, 7.1B | 0.66 | huggingface.co | Official leaderboard | ||
| 26 | Salesforce/SFR-Embedding-2_R open weights, 7.1B | 0.66 | huggingface.co | Official leaderboard | ||
| 27 | Lajavaness/bilingual-embedding-base open weights, 0.3B | 0.65 | huggingface.co | Official leaderboard | ||
| 28 | ibm-granite/granite-embedding-107m-multilingual open weights, 0.1B | 0.65 | huggingface.co | Official leaderboard | ||
| 29 | omarelshehy/arabic-english-sts-matryoshka open weights, 0.6B | 0.65 | huggingface.co | Official leaderboard | ||
| 30 | intfloat/multilingual-e5-small open weights, 0.1B | 0.64 | huggingface.co | Official leaderboard | ||
| 31 | intfloat/multilingual-e5-base open weights, 0.3B | 0.63 | huggingface.co | Official leaderboard | ||
| 32 | deepvk/USER-bge-m3 open weights, 0.4B | 0.62 | huggingface.co | Official leaderboard | ||
| 33 | Omartificial-Intelligence-Space/Arabic-labse-Matryoshka open weights, 0.5B | 0.62 | huggingface.co | Official leaderboard | ||
| 34 | manu/sentence_croissant_alpha_v0.4 open weights, 1.3B | 0.62 | huggingface.co | Official leaderboard | ||
| 35 | sentence-transformers/LaBSE open weights, 0.5B | 0.61 | huggingface.co | Official leaderboard | ||
| 36 | manu/sentence_croissant_alpha_v0.3 open weights, 1.3B | 0.60 | huggingface.co | Official leaderboard | ||
| 37 | McGill-NLP/LLM2Vec-Mistral-7B-Instruct-v2-mntp-supervised open weights, 7.2B | 0.60 | huggingface.co | Official leaderboard | ||
| 38 | NovaSearch/stella_en_400M_v5 open weights, 0.4B | 0.60 | huggingface.co | Official leaderboard | ||
| 39 | Omartificial-Intelligence-Space/Arabic-all-nli-triplet-Matryoshka open weights, 0.3B | 0.60 | huggingface.co | Official leaderboard | ||
| 40 | sentence-transformers/paraphrase-multilingual-mpnet-base-v2 open weights, 0.3B | 0.59 | huggingface.co | Official leaderboard | ||
| 41 | Omartificial-Intelligence-Space/Arabic-MiniLM-L12-v2-all-nli-triplet open weights, 0.1B | 0.58 | huggingface.co | Official leaderboard | ||
| 42 | Cohere/Cohere-embed-english-v3.0 closed weights | 0.58 | cohere.com | Official leaderboard | ||
| 43 | manu/sentence_croissant_alpha_v0.2 open weights, 1.3B | 0.58 | huggingface.co | Official leaderboard | ||
| 44 | nomic-ai/nomic-embed-text-v1-unsupervised open weights, 0.1B | 0.55 | huggingface.co | Official leaderboard | ||
| 45 | bigscience/sgpt-bloom-7b1-msmarco open weights, 7.1B | 0.55 | huggingface.co | Official leaderboard | ||
| 46 | intfloat/e5-large-v2 open weights, 0.3B | 0.55 | huggingface.co | Official leaderboard | ||
| 47 | sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 open weights, 0.1B | 0.55 | huggingface.co | Official leaderboard | ||
| 48 | nomic-ai/nomic-embed-text-v1 open weights, 0.1B | 0.54 | huggingface.co | Official leaderboard | ||
| 49 | intfloat/e5-large open weights, 0.3B | 0.54 | huggingface.co | Official leaderboard | ||
| 50 | thenlper/gte-large open weights, 0.3B | 0.53 | huggingface.co | Official leaderboard | ||
| 51 | sdadas/mmlw-e5-large open weights, 0.6B | 0.53 | huggingface.co | Official leaderboard | ||
| 52 | cointegrated/LaBSE-en-ru open weights, 0.1B | 0.53 | huggingface.co | Official leaderboard | ||
| 53 | avsolatorio/GIST-large-Embedding-v0 open weights, 0.3B | 0.52 | huggingface.co | Official leaderboard | ||
| 54 | sentence-transformers/gtr-t5-xl open weights, 1.2B | 0.52 | huggingface.co | Official leaderboard | ||
| 55 | McGill-NLP/LLM2Vec-Mistral-7B-Instruct-v2-mntp-unsup-simcse open weights, 7.2B | 0.52 | huggingface.co | Official leaderboard | ||
| 56 | sergeyzh/LaBSE-ru-turbo open weights, 0.1B | 0.52 | huggingface.co | Official leaderboard | ||
| 57 | thenlper/gte-small open weights, 0B | 0.51 | huggingface.co | Official leaderboard | ||
| 58 | deepfile/embedder-100p open weights, 0.3B | 0.50 | huggingface.co | Official leaderboard | ||
| 59 | ibm-granite/granite-embedding-125m-english open weights, 0.1B | 0.50 | huggingface.co | Official leaderboard | ||
| 60 | Mihaiii/Ivysaur open weights, 0B | 0.50 | huggingface.co | Official leaderboard | ||
| 61 | sdadas/mmlw-e5-small open weights, 0.1B | 0.50 | huggingface.co | Official leaderboard | ||
| 62 | intfloat/e5-base-v2 open weights, 0.1B | 0.50 | huggingface.co | Official leaderboard | ||
| 63 | avsolatorio/GIST-small-Embedding-v0 open weights, 0B | 0.50 | huggingface.co | Official leaderboard | ||
| 64 | infgrad/stella-base-en-v2 open weights, 0.1B | 0.50 | huggingface.co | Official leaderboard | ||
| 65 | thenlper/gte-base open weights, 0.1B | 0.50 | huggingface.co | Official leaderboard | ||
| 66 | sentence-transformers/gtr-t5-large open weights, 0.3B | 0.50 | huggingface.co | Official leaderboard | ||
| 67 | sentence-transformers/sentence-t5-xl open weights, 1.2B | 0.50 | huggingface.co | Official leaderboard | ||
| 68 | nomic-ai/nomic-embed-text-v1.5 open weights, 0.1B | 0.49 | huggingface.co | Official leaderboard | ||
| 69 | intfloat/e5-base open weights, 0.1B | 0.49 | huggingface.co | Official leaderboard | ||
| 70 | intfloat/e5-small open weights, 0B | 0.49 | huggingface.co | Official leaderboard | ||
| 71 | mixedbread-ai/mxbai-embed-large-v1 open weights, 0.3B | 0.49 | huggingface.co | Official leaderboard | ||
| 72 | WhereIsAI/UAE-Large-V1 open weights, 0.3B | 0.49 | huggingface.co | Official leaderboard | ||
| 73 | sdadas/mmlw-roberta-large open weights, 0.4B | 0.49 | huggingface.co | Official leaderboard | ||
| 74 | avsolatorio/GIST-Embedding-v0 open weights, 0.1B | 0.49 | huggingface.co | Official leaderboard | ||
| 75 | sdadas/mmlw-e5-base open weights, 0.3B | 0.48 | huggingface.co | Official leaderboard | ||
| 76 | ibm-granite/granite-embedding-30m-english open weights, 0B | 0.48 | huggingface.co | Official leaderboard | ||
| 77 | Cohere/Cohere-embed-english-light-v3.0 closed weights | 0.48 | cohere.com | Official leaderboard | ||
| 78 | dwzhu/e5-base-4k open weights, 0.1B | 0.48 | huggingface.co | Official leaderboard | ||
| 79 | jinaai/jina-embedding-b-en-v1 open weights, 0.1B | 0.48 | huggingface.co | Official leaderboard | ||
| 80 | Snowflake/snowflake-arctic-embed-s open weights, 0B | 0.47 | huggingface.co | Official leaderboard | ||
| 81 | BAAI/bge-large-en-v1.5 open weights, 0.3B | 0.47 | huggingface.co | Official leaderboard | ||
| 82 | sdadas/mmlw-roberta-base open weights, 0.1B | 0.47 | huggingface.co | Official leaderboard | ||
| 83 | | 0.46 | Jan 2025 | ai.meta.com | Official leaderboard | |
| 84 | abhinand/MedEmbed-small-v0.1 open weights, 0B | 0.46 | huggingface.co | Official leaderboard | ||
| 85 | spartan8806/atles-champion-embedding open weights, 0.1B | 0.45 | huggingface.co | Official leaderboard | ||
| 86 | BAAI/bge-small-en-v1.5 open weights, 0B | 0.45 | huggingface.co | Official leaderboard | ||
| 87 | BAAI/bge-base-en-v1.5 open weights, 0.1B | 0.45 | huggingface.co | Official leaderboard | ||
| 88 | sentence-transformers/sentence-t5-large open weights, 0.3B | 0.45 | huggingface.co | Official leaderboard | ||
| 89 | intfloat/e5-small-v2 open weights, 0B | 0.44 | huggingface.co | Official leaderboard | ||
| 90 | sentence-transformers/sentence-t5-base open weights, 0.2B | 0.44 | huggingface.co | Official leaderboard | ||
| 91 | jinaai/jina-embedding-s-en-v1 open weights, 0B | 0.43 | huggingface.co | Official leaderboard | ||
| 92 | deepvk/USER-base open weights, 0.4B | 0.42 | huggingface.co | Official leaderboard | ||
| 93 | sentence-transformers/multi-qa-MiniLM-L6-cos-v1 open weights, 0B | 0.42 | huggingface.co | Official leaderboard | ||
| 94 | Snowflake/snowflake-arctic-embed-l open weights, 0.3B | 0.42 | huggingface.co | Official leaderboard | ||
| 95 | avsolatorio/GIST-all-MiniLM-L6-v2 open weights, 0B | 0.42 | huggingface.co | Official leaderboard | ||
| 96 | ai-forever/ru-en-RoSBERTa open weights, 0.4B | 0.42 | huggingface.co | Official leaderboard | ||
| 97 | aari1995/German_Semantic_STS_V2 open weights, 0.3B | 0.41 | huggingface.co | Official leaderboard | ||
| 98 | brahmairesearch/slx-v0.1 open weights, 0B | 0.40 | huggingface.co | Official leaderboard | ||
| 99 | sentence-transformers/all-MiniLM-L6-v2 open weights, 0B | 0.40 | huggingface.co | Official leaderboard | ||
| 100 | consciousAI/cai-lunaris-text-embeddings open weights, 0.3B | 0.40 | huggingface.co | Official leaderboard | ||
| 101 | Snowflake/snowflake-arctic-embed-m-v1.5 open weights, 0.1B | 0.40 | huggingface.co | Official leaderboard | ||
| 102 | silma-ai/silma-embeddding-matryoshka-v0.1 open weights, 0.1B | 0.38 | huggingface.co | Official leaderboard | ||
| 103 | Mihaiii/Wartortle open weights, 0B | 0.37 | huggingface.co | Official leaderboard | ||
| 104 | Snowflake/snowflake-arctic-embed-xs open weights, 0B | 0.37 | huggingface.co | Official leaderboard | ||
| 105 | Mihaiii/gte-micro-v4 open weights, 0B | 0.36 | huggingface.co | Official leaderboard | ||
| 106 | Mihaiii/Venusaur open weights, 0B | 0.35 | huggingface.co | Official leaderboard | ||
| 107 | Mihaiii/Bulbasaur open weights, 0B | 0.35 | huggingface.co | Official leaderboard | ||
| 108 | Mihaiii/Squirtle open weights, 0B | 0.34 | huggingface.co | Official leaderboard | ||
| 109 | Snowflake/snowflake-arctic-embed-m open weights, 0.1B | 0.34 | huggingface.co | Official leaderboard | ||
| 110 | DeepPavlov/rubert-base-cased-sentence open weights, 0.1B | 0.33 | huggingface.co | Official leaderboard | ||
| 111 | Omartificial-Intelligence-Space/Arabert-all-nli-triplet-Matryoshka open weights, 0.1B | 0.33 | huggingface.co | Official leaderboard | ||
| 112 | sergeyzh/rubert-tiny-turbo open weights, 0B | 0.33 | huggingface.co | Official leaderboard | ||
| 113 | minishlab/potion-base-8M open weights, 0B | 0.32 | huggingface.co | Official leaderboard | ||
| 114 | minishlab/potion-base-2M open weights, 0B | 0.31 | huggingface.co | Official leaderboard | ||
| 115 | minishlab/potion-base-4M open weights, 0B | 0.31 | huggingface.co | Official leaderboard | ||
| 116 | minishlab/M2V_base_output open weights, 0B | 0.30 | huggingface.co | Official leaderboard | ||
| 117 | dmedhi/PawanEmbd-68M open weights, 0.1B | 0.30 | huggingface.co | Official leaderboard | ||
| 118 | Mihaiii/gte-micro open weights, 0B | 0.29 | huggingface.co | Official leaderboard | ||
| 119 | Omartificial-Intelligence-Space/Arabic-mpnet-base-all-nli-triplet open weights, 0.1B | 0.29 | huggingface.co | Official leaderboard | ||
| 120 | cointegrated/rubert-tiny2 open weights, 0B | 0.27 | huggingface.co | Official leaderboard | ||
| 121 | ai-forever/sbert_large_nlu_ru open weights, 0.4B | 0.26 | huggingface.co | Official leaderboard | ||
| 122 | Omartificial-Intelligence-Space/Marbert-all-nli-triplet-Matryoshka open weights, 0.2B | 0.26 | huggingface.co | Official leaderboard | ||
| 123 | cointegrated/rubert-tiny open weights, 0B | 0.24 | huggingface.co | Official leaderboard | ||
| 124 | DeepPavlov/distilrubert-small-cased-conversational open weights, 0.1B | 0.23 | huggingface.co | Official leaderboard | ||
| 125 | DeepPavlov/rubert-base-cased open weights, 1.3B | 0.23 | huggingface.co | Official leaderboard | ||
| 126 | ai-forever/sbert_large_mt_nlu_ru open weights, 0.4B | 0.22 | huggingface.co | Official leaderboard | ||
| 127 | deepvk/deberta-v1-base open weights, 0.1B | 0.20 | huggingface.co | Official leaderboard |
| # | Model | Score | Setting | Date | Link | Source |
|---|---|---|---|---|---|---|
| 1 | | 0.72 | Jun 2025 | huggingface.co | Official leaderboard | |
| 2 | | 0.72 | Jun 2025 | huggingface.co | Official leaderboard | |
| 3 | | 0.71 | Jun 2025 | huggingface.co | Official leaderboard | |
| 4 | | 0.46 | Jan 2025 | ai.meta.com | Official leaderboard |
2 models have held number one on MTEB’s leaderboard since 2023
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
8 of 9 checks pass, 1 warning. Look first at the Newest score check. The newest came 17 months ago, in June 2025, for Qwen3-Embedding-0.6B. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 1 warning 2 pass 2 notes
- Pass Independent runs Scores from the benchmark’s paper (127 entries).
- Pass Models scored 4 models we track, plus 123 other entries on its leaderboard.
- Warning Newest score The newest came 17 months ago, in June 2025, for Qwen3-Embedding-0.6B.
- 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 123 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.