ScaLA
Models judge whether sentences in mainland Scandinavian languages are linguistically acceptable.
MTEB scores the task using accuracy.
- Made by
- Dan Nielsen
- Released
- May 2023
- Kind
- Reading in many languages
- Level
- School
- Scored
- Checked automatically
- Answers
- Prediction
- Tasks
- All public
- Measures
- Capability
- Subject
- Languages and literature
- Interaction
- Single turn
- Refresh
- One fixed set
- Run by
- Anyone
- Last model added
- October 2026
- Scores refreshed
- November 20th, 2026
microsoft/harrier-oss-v1-27b tops the leaderboard with 91.1% Qwen3-Embedding-8B leads with 57.4% among models released by October 2026
Best score per entry from MTEB’s leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. The best model we track is Qwen3-Embedding-8B, at 57.4%. 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
- 91.1 microsoft/harrier-oss-v1-27b
- 86.3 tencent/KaLM-Embedding-Gemma3-12B-2511
- 84.7 codefuse-ai/F2LLM-v2-14B
- 80.8 codefuse-ai/F2LLM-v2-8B
- 78.6 codefuse-ai/F2LLM-v2-4B
- 76.5 codefuse-ai/F2LLM-v2-1.7B
- 72.9 microsoft/harrier-oss-v1-0.6b
- 68.6 codefuse-ai/F2LLM-v2-0.6B
- 65.9 nvidia/llama-embed-nemotron-8b
- 64.3 codefuse-ai/F2LLM-v2-330M
- 63.5 KennethEnevoldsen/dfm-sentence-encoder-large
- 62.8 FacebookAI/xlm-roberta-large
- 62.2 microsoft/harrier-oss-v1-270m
- 60.4 FacebookAI/xlm-roberta-base
- 57.4
Qwen3-Embedding-8B
- 56.5 Octen/Octen-Embedding-8B
- 55.7 Alibaba-NLP/gte-Qwen2-7B-instruct
- 55.6 Alibaba-NLP/gte-Qwen1.5-7B-instruct
- 53.3 Salesforce/SFR-Embedding-2_R
- 53.2 Haon-Chen/speed-embedding-7b-instruct
- 53.1 BidirLM/BidirLM-1.7B-Embedding
- 52.9 emillykkejensen/mmBERTscandi-base-embedding
- 52.8 Jaume/gemma-2b-embeddings
- 52.8 BidirLM/BidirLM-Omni-2.5B-Embedding
- 52.5 McGill-NLP/LLM2Vec-Mistral-7B-Instruct-v2-mntp-unsup-simcse
- 52.3 BidirLM/BidirLM-1B-Embedding
- 52.1 nicher92/saga-embed_v1
- 52.1 GritLM/GritLM-7B
- 52.0 Bytedance/Seed1.6-embedding-1215
- 51.9 google/gemini-embedding-001
- 51.8 google/text-multilingual-embedding-002
- 51.8 KennethEnevoldsen/dfm-sentence-encoder-medium
- 51.6 McGill-NLP/LLM2Vec-Mistral-7B-Instruct-v2-mntp-supervised
- 51.4 GritLM/GritLM-8x7B
- 51.3
Qwen3-Embedding-4B
- 51.3 BidirLM/BidirLM-270M-Embedding
- 51.2 BidirLM/BidirLM-0.6B-Embedding
- 51.2 NbAiLab/nb-sbert-base
- 51.1 ai-sage/Giga-Embeddings-instruct-3B-0826
- 51.1 Linq-AI-Research/Linq-Embed-Mistral
- 51.1 intfloat/multilingual-e5-large
- 51.1 mongodb/voyage-3.5 (output_dtype=int8)
- 51.1 intfloat/e5-mistral-7b-instruct
- 51.1 mongodb/voyage-multilingual-2
- 51.0 codefuse-ai/F2LLM-v2-160M
- 51.0 mongodb/voyage-finance-2
- 51.0 ai-sage/Giga-Embeddings-instruct-10B-A1.8B-0826
- 51.0 Salesforce/SFR-Embedding-Mistral
- 50.9 intfloat/multilingual-e5-base
- 50.9 mongodb/voyage-3-lite
- 50.9 Cohere/Cohere-embed-multilingual-v3.0
- 50.8 google/embeddinggemma-300m
- 50.8 openai/text-embedding-3-large
- 50.7 nvidia/NV-Embed-v2
- 50.7 OrdalieTech/Solon-embeddings-large-0.1
- 50.6 izhx/udever-bloom-7b1
- 50.6 mongodb/voyage-3
- 50.6 nomic-ai/nomic-embed-text-v2-moe
- 50.6 openai/text-embedding-3-large (embed_dim=512)
- 50.6 emillykkejensen/Qwen3-Embedding-Scandi-0.6B
- 50.6 Snowflake/snowflake-arctic-embed-l-v2.0
- 50.6 mongodb/voyage-3.5
- 50.6 mongodb/voyage-code-3
- 50.6 sentence-transformers/LaBSE
- 50.5 zeroentropy/zembed-1
- 50.5 Lajavaness/bilingual-embedding-base
- 50.5
Qwen3-Embedding-0.6B
- 50.5 omarelshehy/arabic-english-sts-matryoshka
- 50.5 mongodb/voyage-3.5 (output_dtype=binary)
- 50.4 BAAI/bge-m3
- 50.4 bigscience/sgpt-bloom-7b1-msmarco
- 50.4 mongodb/voyage-multimodal-3
- 50.4 openai/text-embedding-3-small
- 50.4 cointegrated/LaBSE-en-ru
- 50.4 HIT-TMG/KaLM-embedding-multilingual-mini-v1
- 50.4 intfloat/multilingual-e5-small
- 50.4 HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1
- 50.4 izhx/udever-bloom-3b
- 50.4 mongodb/voyage-large-2-instruct
- 50.4 openai/text-embedding-3-small (embed_dim=512)
- 50.4 Alibaba-NLP/gte-Qwen2-1.5B-instruct
- 50.4 nvidia/NV-Embed-v1
- 50.4 deepfile/embedder-100p
- 50.4 intfloat/multilingual-e5-large-instruct
- 50.4 izhx/udever-bloom-1b1
- 50.4 deepvk/USER-bge-m3
- 50.4 ICT-TIME-and-Querit/ICT-TIME-and-Querit-embedding-v1
- 50.4 manu/bge-m3-custom-fr
- 50.4 mongodb/voyage-law-2
- 50.3 NovaSearch/stella_en_1.5B_v5
- 50.3 ICT-TIME-and-Querit/BOOM_4B_v1
- 50.3 Lajavaness/bilingual-embedding-small
- 50.3 mongodb/voyage-code-2
- 50.3 ai-forever/sbert_large_mt_nlu_ru
- 50.3 Cohere/Cohere-embed-multilingual-light-v3.0
- 50.3 izhx/udever-bloom-560m
- 50.3 brahmairesearch/slx-v0.1
- 50.3 sentence-transformers/all-MiniLM-L6-v2
- 50.3 cointegrated/rubert-tiny2
- 50.3 DeepPavlov/rubert-base-cased
- 50.3 cointegrated/rubert-tiny
- 50.3 hotchpotch/bekko-embedding-v1-a25m
- 50.3 Lajavaness/bilingual-embedding-large
- 50.2 deepvk/deberta-v1-base
- 50.2 deepvk/USER-base
- 50.2 jinaai/jina-embeddings-v5-omni-small
- 50.2 jinaai/jina-embeddings-v5-text-small
- 50.2 emillykkejensen/EmbeddingGemma-Scandi-300m
- 50.2 KFST/XLMRoberta-en-da-sv-nb
- 50.2 silma-ai/silma-embeddding-matryoshka-v0.1
- 50.2 Snowflake/snowflake-arctic-embed-m
- 50.2 Omartificial-Intelligence-Space/Arabic-all-nli-triplet-Matryoshka
- 50.2 codefuse-ai/F2LLM-v2-80M
- 50.2 DeepPavlov/rubert-base-cased-sentence
- 50.2 ibm-granite/granite-embedding-107m-multilingual
- 50.2 jinaai/jina-embedding-s-en-v1
- 50.2 manu/sentence_croissant_alpha_v0.2
- 50.2 Mira190/Euler-Legal-Embedding-V1
- 50.2 jinaai/jina-embeddings-v2-small-en
- 50.2 WhereIsAI/UAE-Large-V1
- 50.2 ai-forever/sbert_large_nlu_ru
- 50.2 dwzhu/e5-base-4k
- 50.2 Hum-Works/lodestone-base-4096-v1
- 50.2 ibm-granite/granite-embedding-278m-multilingual
- 50.2 jinaai/jina-embeddings-v3
- 50.2 avsolatorio/GIST-Embedding-v0
- 50.2 infgrad/stella-base-en-v2
- 50.2 intfloat/e5-small-v2
- 50.2 Mihaiii/gte-micro-v4
- 50.2 Omartificial-Intelligence-Space/Arabert-all-nli-triplet-Matryoshka
- 50.2 Snowflake/snowflake-arctic-embed-m-v2.0
- 50.1 avsolatorio/GIST-all-MiniLM-L6-v2
- 50.1 intfloat/e5-base-v2
- 50.1 intfloat/e5-large-v2
- 50.1 jinaai/jina-embeddings-v2-base-en
- 50.1 Mihaiii/Bulbasaur
- 50.1 abhinand/MedEmbed-small-v0.1
- 50.1 BAAI/bge-base-en-v1.5
- 50.1 mixedbread-ai/mxbai-embed-large-v1
- 50.1 sdadas/mmlw-e5-small
- 50.1 sergeyzh/LaBSE-ru-turbo
- 50.1 avsolatorio/GIST-small-Embedding-v0
- 50.1 Gameselo/STS-multilingual-mpnet-base-v2
- 50.1 mongodb/voyage-2
- 50.1 mongodb/voyage-large-2
- 50.1 Omartificial-Intelligence-Space/Arabic-mpnet-base-all-nli-triplet
- 50.1 sentence-transformers/all-MiniLM-L12-v2
- 50.1 Snowflake/snowflake-arctic-embed-s
- 50.1 manu/sentence_croissant_alpha_v0.4
- 50.1 nomic-ai/nomic-embed-text-v1-ablated
- 50.1 sdadas/mmlw-e5-base
- 50.1 sentence-transformers/static-similarity-mrl-multilingual-v1
- 50.1 DeepPavlov/distilrubert-small-cased-conversational
- 50.1 jinaai/jina-embeddings-v5-omni-nano
- 50.1 jinaai/jina-embeddings-v5-text-nano
- 50.1 Mihaiii/Squirtle
- 50.1 minishlab/M2V_base_glove
- 50.1 NovaSearch/stella_en_400M_v5
- 50.1 Omartificial-Intelligence-Space/Arabic-labse-Matryoshka
- 50.1 sdadas/mmlw-roberta-base
- 50.1 sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
- 50.1 Snowflake/snowflake-arctic-embed-m-long
- 50.1 BAAI/bge-large-en-v1.5
- 50.1 BAAI/bge-small-en-v1.5
- 50.1 hotchpotch/bekko-embedding-v1-a8m
- 50.1 ibm-granite/granite-embedding-30m-english
- 50.1 jinaai/jina-embedding-b-en-v1
- 50.1 Omartificial-Intelligence-Space/Marbert-all-nli-triplet-Matryoshka
- 50.1 sdadas/mmlw-roberta-large
- 50.1 shibing624/text2vec-base-multilingual
- 50.1 Alibaba-NLP/gte-multilingual-base
- 50.1 Mihaiii/gte-micro
- 50.1 thenlper/gte-small
- 50.1 aari1995/German_Semantic_STS_V2
- 50.1 avsolatorio/NoInstruct-small-Embedding-v0
- 50.1 hotchpotch/bekko-static-embedding-v1
- 50.1 ibm-granite/granite-embedding-97m-multilingual-r2
- 50.1 manu/sentence_croissant_alpha_v0.3
- 50.1 thenlper/gte-base
- 50.1
EmbeddingGemma 2
- 50.1 Mihaiii/Ivysaur
- 50.1 minishlab/M2V_base_output
- 50.1 minishlab/potion-multilingual-128M
- 50.1 sergeyzh/rubert-tiny-turbo
- 50.1 andersborges/model2vecdk
- 50.1 Mihaiii/Venusaur
- 50.1 Mihaiii/Wartortle
- 50.1 sentence-transformers/all-mpnet-base-v2
- 50.1 thenlper/gte-large
- 50.0 cnmoro/static-nomic-384-pten-v2-st
- 50.0 ibm-granite/granite-embedding-125m-english
- 50.0 sdadas/mmlw-e5-large
- 50.0 ai-forever/ru-en-RoSBERTa
- 50.0 ibm-granite/granite-embedding-311m-multilingual-r2
- 50.0 malenia1/ternary-weight-embedding
- 50.0 nomic-ai/nomic-embed-text-v1.5
- 50.0 sentence-transformers/paraphrase-multilingual-mpnet-base-v2
- 50.0 nomic-ai/nomic-embed-text-v1
- 50.0 Snowflake/snowflake-arctic-embed-xs
- 50.0 consciousAI/cai-lunaris-text-embeddings
- 50.0 nomic-ai/nomic-embed-text-v1-unsupervised
- 50.0 Snowflake/snowflake-arctic-embed-m-v1.5
- 50.0 Cohere/Cohere-embed-english-v3.0
- 50.0 minishlab/M2V_base_glove_subword
- 50.0 Snowflake/snowflake-arctic-embed-l
- 50.0 minishlab/potion-base-4M
- 50.0 Omartificial-Intelligence-Space/Arabic-MiniLM-L12-v2-all-nli-triplet
- 50.0 rasgaard/m2v-dfm-large
- 50.0 andersborges/model2vecdk-stem
- 50.0 intfloat/e5-large
- 50.0 intfloat/e5-small
- 50.0 minishlab/potion-base-8M
- 50.0 Cohere/Cohere-embed-english-light-v3.0
- 50.0 avsolatorio/GIST-large-Embedding-v0
- 50.0 minishlab/potion-base-2M
- 49.9 intfloat/e5-base
- 1 microsoft/harrier-oss-v1-27b 91.1%
- 2 tencent/KaLM-Embedding-Gemma3-12B-2511 86.3%
- 3 codefuse-ai/F2LLM-v2-14B 84.7%
- 4 codefuse-ai/F2LLM-v2-8B 80.8%
- 5 codefuse-ai/F2LLM-v2-4B 78.6%
- 6 codefuse-ai/F2LLM-v2-1.7B 76.5%
- 7 microsoft/harrier-oss-v1-0.6b 72.9%
- 8 codefuse-ai/F2LLM-v2-0.6B 68.6%
- 9 nvidia/llama-embed-nemotron-8b 65.9%
- 10 codefuse-ai/F2LLM-v2-330M 64.3%
- 11 KennethEnevoldsen/dfm-sentence-encoder-large 63.5%
- 12 FacebookAI/xlm-roberta-large 62.8%
- 13 microsoft/harrier-oss-v1-270m 62.2%
- 14 FacebookAI/xlm-roberta-base 60.4%
- 15
Qwen3-Embedding-8B 57.4%
- 16 Octen/Octen-Embedding-8B 56.5%
- 17 Alibaba-NLP/gte-Qwen2-7B-instruct 55.7%
- 18 Alibaba-NLP/gte-Qwen1.5-7B-instruct 55.6%
- 19 Salesforce/SFR-Embedding-2_R 53.3%
- 20 Haon-Chen/speed-embedding-7b-instruct 53.2%
- 21 BidirLM/BidirLM-1.7B-Embedding 53.1%
- 22 emillykkejensen/mmBERTscandi-base-embedding 52.9%
- 23 Jaume/gemma-2b-embeddings 52.8%
- 24 BidirLM/BidirLM-Omni-2.5B-Embedding 52.8%
- 25 McGill-NLP/LLM2Vec-Mistral-7B-Instruct-v2-mntp-unsup-simcse 52.5%
- 26 BidirLM/BidirLM-1B-Embedding 52.3%
- 27 nicher92/saga-embed_v1 52.1%
- 28 GritLM/GritLM-7B 52.1%
- 29 Bytedance/Seed1.6-embedding-1215 52%
- 30 google/gemini-embedding-001 51.9%
- 31 google/text-multilingual-embedding-002 51.8%
- 32 KennethEnevoldsen/dfm-sentence-encoder-medium 51.8%
- 33 McGill-NLP/LLM2Vec-Mistral-7B-Instruct-v2-mntp-supervised 51.6%
- 34 GritLM/GritLM-8x7B 51.4%
- 35
Qwen3-Embedding-4B 51.3%
- 36 BidirLM/BidirLM-270M-Embedding 51.3%
- 37 BidirLM/BidirLM-0.6B-Embedding 51.2%
- 38 NbAiLab/nb-sbert-base 51.2%
- 39 ai-sage/Giga-Embeddings-instruct-3B-0826 51.1%
- 40 Linq-AI-Research/Linq-Embed-Mistral 51.1%
- 41 intfloat/multilingual-e5-large 51.1%
- 42 mongodb/voyage-3.5 (output_dtype=int8) 51.1%
- 43 intfloat/e5-mistral-7b-instruct 51.1%
- 44 mongodb/voyage-multilingual-2 51.1%
- 45 codefuse-ai/F2LLM-v2-160M 51%
- 46 mongodb/voyage-finance-2 51%
- 47 ai-sage/Giga-Embeddings-instruct-10B-A1.8B-0826 51%
- 48 Salesforce/SFR-Embedding-Mistral 51%
- 49 intfloat/multilingual-e5-base 50.9%
- 50 mongodb/voyage-3-lite 50.9%
- 51 Cohere/Cohere-embed-multilingual-v3.0 50.9%
- 52 google/embeddinggemma-300m 50.8%
- 53 openai/text-embedding-3-large 50.8%
- 54 nvidia/NV-Embed-v2 50.7%
- 55 OrdalieTech/Solon-embeddings-large-0.1 50.7%
- 56 izhx/udever-bloom-7b1 50.6%
- 57 mongodb/voyage-3 50.6%
- 58 nomic-ai/nomic-embed-text-v2-moe 50.6%
- 59 openai/text-embedding-3-large (embed_dim=512) 50.6%
- 60 emillykkejensen/Qwen3-Embedding-Scandi-0.6B 50.6%
- 61 Snowflake/snowflake-arctic-embed-l-v2.0 50.6%
- 62 mongodb/voyage-3.5 50.6%
- 63 mongodb/voyage-code-3 50.6%
- 64 sentence-transformers/LaBSE 50.6%
- 65 zeroentropy/zembed-1 50.5%
- 66 Lajavaness/bilingual-embedding-base 50.5%
- 67
Qwen3-Embedding-0.6B 50.5%
- 68 omarelshehy/arabic-english-sts-matryoshka 50.5%
- 69 mongodb/voyage-3.5 (output_dtype=binary) 50.5%
- 70 BAAI/bge-m3 50.4%
- 71 bigscience/sgpt-bloom-7b1-msmarco 50.4%
- 72 mongodb/voyage-multimodal-3 50.4%
- 73 openai/text-embedding-3-small 50.4%
- 74 cointegrated/LaBSE-en-ru 50.4%
- 75 HIT-TMG/KaLM-embedding-multilingual-mini-v1 50.4%
- 76 intfloat/multilingual-e5-small 50.4%
- 77 HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1 50.4%
- 78 izhx/udever-bloom-3b 50.4%
- 79 mongodb/voyage-large-2-instruct 50.4%
- 80 openai/text-embedding-3-small (embed_dim=512) 50.4%
- 81 Alibaba-NLP/gte-Qwen2-1.5B-instruct 50.4%
- 82 nvidia/NV-Embed-v1 50.4%
- 83 deepfile/embedder-100p 50.4%
- 84 intfloat/multilingual-e5-large-instruct 50.4%
- 85 izhx/udever-bloom-1b1 50.4%
- 86 deepvk/USER-bge-m3 50.4%
- 87 ICT-TIME-and-Querit/ICT-TIME-and-Querit-embedding-v1 50.4%
- 88 manu/bge-m3-custom-fr 50.4%
- 89 mongodb/voyage-law-2 50.4%
- 90 NovaSearch/stella_en_1.5B_v5 50.3%
- 91 ICT-TIME-and-Querit/BOOM_4B_v1 50.3%
- 92 Lajavaness/bilingual-embedding-small 50.3%
- 93 mongodb/voyage-code-2 50.3%
- 94 ai-forever/sbert_large_mt_nlu_ru 50.3%
- 95 Cohere/Cohere-embed-multilingual-light-v3.0 50.3%
- 96 izhx/udever-bloom-560m 50.3%
- 97 brahmairesearch/slx-v0.1 50.3%
- 98 sentence-transformers/all-MiniLM-L6-v2 50.3%
- 99 cointegrated/rubert-tiny2 50.3%
- 100 DeepPavlov/rubert-base-cased 50.3%
- 101 cointegrated/rubert-tiny 50.3%
- 102 hotchpotch/bekko-embedding-v1-a25m 50.3%
- 103 Lajavaness/bilingual-embedding-large 50.3%
- 104 deepvk/deberta-v1-base 50.2%
- 105 deepvk/USER-base 50.2%
- 106 jinaai/jina-embeddings-v5-omni-small 50.2%
- 107 jinaai/jina-embeddings-v5-text-small 50.2%
- 108 emillykkejensen/EmbeddingGemma-Scandi-300m 50.2%
- 109 KFST/XLMRoberta-en-da-sv-nb 50.2%
- 110 silma-ai/silma-embeddding-matryoshka-v0.1 50.2%
- 111 Snowflake/snowflake-arctic-embed-m 50.2%
- 112 Omartificial-Intelligence-Space/Arabic-all-nli-triplet-Matryoshka 50.2%
- 113 codefuse-ai/F2LLM-v2-80M 50.2%
- 114 DeepPavlov/rubert-base-cased-sentence 50.2%
- 115 ibm-granite/granite-embedding-107m-multilingual 50.2%
- 116 jinaai/jina-embedding-s-en-v1 50.2%
- 117 manu/sentence_croissant_alpha_v0.2 50.2%
- 118 Mira190/Euler-Legal-Embedding-V1 50.2%
- 119 jinaai/jina-embeddings-v2-small-en 50.2%
- 120 WhereIsAI/UAE-Large-V1 50.2%
- 121 ai-forever/sbert_large_nlu_ru 50.2%
- 122 dwzhu/e5-base-4k 50.2%
- 123 Hum-Works/lodestone-base-4096-v1 50.2%
- 124 ibm-granite/granite-embedding-278m-multilingual 50.2%
- 125 jinaai/jina-embeddings-v3 50.2%
- 126 avsolatorio/GIST-Embedding-v0 50.2%
- 127 infgrad/stella-base-en-v2 50.2%
- 128 intfloat/e5-small-v2 50.2%
- 129 Mihaiii/gte-micro-v4 50.2%
- 130 Omartificial-Intelligence-Space/Arabert-all-nli-triplet-Matryoshka 50.2%
- 131 Snowflake/snowflake-arctic-embed-m-v2.0 50.2%
- 132 avsolatorio/GIST-all-MiniLM-L6-v2 50.1%
- 133 intfloat/e5-base-v2 50.1%
- 134 intfloat/e5-large-v2 50.1%
- 135 jinaai/jina-embeddings-v2-base-en 50.1%
- 136 Mihaiii/Bulbasaur 50.1%
- 137 abhinand/MedEmbed-small-v0.1 50.1%
- 138 BAAI/bge-base-en-v1.5 50.1%
- 139 mixedbread-ai/mxbai-embed-large-v1 50.1%
- 140 sdadas/mmlw-e5-small 50.1%
- 141 sergeyzh/LaBSE-ru-turbo 50.1%
- 142 avsolatorio/GIST-small-Embedding-v0 50.1%
- 143 Gameselo/STS-multilingual-mpnet-base-v2 50.1%
- 144 mongodb/voyage-2 50.1%
- 145 mongodb/voyage-large-2 50.1%
- 146 Omartificial-Intelligence-Space/Arabic-mpnet-base-all-nli-triplet 50.1%
- 147 sentence-transformers/all-MiniLM-L12-v2 50.1%
- 148 Snowflake/snowflake-arctic-embed-s 50.1%
- 149 manu/sentence_croissant_alpha_v0.4 50.1%
- 150 nomic-ai/nomic-embed-text-v1-ablated 50.1%
- 151 sdadas/mmlw-e5-base 50.1%
- 152 sentence-transformers/static-similarity-mrl-multilingual-v1 50.1%
- 153 DeepPavlov/distilrubert-small-cased-conversational 50.1%
- 154 jinaai/jina-embeddings-v5-omni-nano 50.1%
- 155 jinaai/jina-embeddings-v5-text-nano 50.1%
- 156 Mihaiii/Squirtle 50.1%
- 157 minishlab/M2V_base_glove 50.1%
- 158 NovaSearch/stella_en_400M_v5 50.1%
- 159 Omartificial-Intelligence-Space/Arabic-labse-Matryoshka 50.1%
- 160 sdadas/mmlw-roberta-base 50.1%
- 161 sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 50.1%
- 162 Snowflake/snowflake-arctic-embed-m-long 50.1%
- 163 BAAI/bge-large-en-v1.5 50.1%
- 164 BAAI/bge-small-en-v1.5 50.1%
- 165 hotchpotch/bekko-embedding-v1-a8m 50.1%
- 166 ibm-granite/granite-embedding-30m-english 50.1%
- 167 jinaai/jina-embedding-b-en-v1 50.1%
- 168 Omartificial-Intelligence-Space/Marbert-all-nli-triplet-Matryoshka 50.1%
- 169 sdadas/mmlw-roberta-large 50.1%
- 170 shibing624/text2vec-base-multilingual 50.1%
- 171 Alibaba-NLP/gte-multilingual-base 50.1%
- 172 Mihaiii/gte-micro 50.1%
- 173 thenlper/gte-small 50.1%
- 174 aari1995/German_Semantic_STS_V2 50.1%
- 175 avsolatorio/NoInstruct-small-Embedding-v0 50.1%
- 176 hotchpotch/bekko-static-embedding-v1 50.1%
- 177 ibm-granite/granite-embedding-97m-multilingual-r2 50.1%
- 178 manu/sentence_croissant_alpha_v0.3 50.1%
- 179 thenlper/gte-base 50.1%
- 180
EmbeddingGemma 2 50.1%
- 181 Mihaiii/Ivysaur 50.1%
- 182 minishlab/M2V_base_output 50.1%
- 183 minishlab/potion-multilingual-128M 50.1%
- 184 sergeyzh/rubert-tiny-turbo 50.1%
- 185 andersborges/model2vecdk 50.1%
- 186 Mihaiii/Venusaur 50.1%
- 187 Mihaiii/Wartortle 50.1%
- 188 sentence-transformers/all-mpnet-base-v2 50.1%
- 189 thenlper/gte-large 50.1%
- 190 cnmoro/static-nomic-384-pten-v2-st 50%
- 191 ibm-granite/granite-embedding-125m-english 50%
- 192 sdadas/mmlw-e5-large 50%
- 193 ai-forever/ru-en-RoSBERTa 50%
- 194 ibm-granite/granite-embedding-311m-multilingual-r2 50%
- 195 malenia1/ternary-weight-embedding 50%
- 196 nomic-ai/nomic-embed-text-v1.5 50%
- 197 sentence-transformers/paraphrase-multilingual-mpnet-base-v2 50%
- 198 nomic-ai/nomic-embed-text-v1 50%
- 199 Snowflake/snowflake-arctic-embed-xs 50%
- 200 consciousAI/cai-lunaris-text-embeddings 50%
- 201 nomic-ai/nomic-embed-text-v1-unsupervised 50%
- 202 Snowflake/snowflake-arctic-embed-m-v1.5 50%
- 203 Cohere/Cohere-embed-english-v3.0 50%
- 204 minishlab/M2V_base_glove_subword 50%
- 205 Snowflake/snowflake-arctic-embed-l 50%
- 206 minishlab/potion-base-4M 50%
- 207 Omartificial-Intelligence-Space/Arabic-MiniLM-L12-v2-all-nli-triplet 50%
- 208 rasgaard/m2v-dfm-large 50%
- 209 andersborges/model2vecdk-stem 50%
- 210 intfloat/e5-large 50%
- 211 intfloat/e5-small 50%
- 212 minishlab/potion-base-8M 50%
- 213 Cohere/Cohere-embed-english-light-v3.0 50%
- 214 avsolatorio/GIST-large-Embedding-v0 50%
- 215 minishlab/potion-base-2M 50%
- 216 intfloat/e5-base 49.9%
Source: MTEB’s leaderboard
- 1
Qwen3-Embedding-8B 57.4%
- 2
Qwen3-Embedding-4B 51.3%
- 3
Qwen3-Embedding-0.6B 50.5%
- 4
EmbeddingGemma 2 50.1%
Source: MTEB’s leaderboard
| # | Entry | Score | Setting | Date | Link | Source |
|---|---|---|---|---|---|---|
| 1 | microsoft/harrier-oss-v1-27b open weights, 27B | 91.1% | huggingface.co | Official leaderboard | ||
| 2 | tencent/KaLM-Embedding-Gemma3-12B-2511 open weights, 11.8B | 86.3% | huggingface.co | Official leaderboard | ||
| 3 | codefuse-ai/F2LLM-v2-14B open weights, 14B | 84.7% | huggingface.co | Official leaderboard | ||
| 4 | codefuse-ai/F2LLM-v2-8B open weights, 7.6B | 80.8% | huggingface.co | Official leaderboard | ||
| 5 | codefuse-ai/F2LLM-v2-4B open weights, 4B | 78.6% | huggingface.co | Official leaderboard | ||
| 6 | codefuse-ai/F2LLM-v2-1.7B open weights, 1.7B | 76.5% | huggingface.co | Official leaderboard | ||
| 7 | microsoft/harrier-oss-v1-0.6b open weights, 0.6B | 72.9% | huggingface.co | Official leaderboard | ||
| 8 | codefuse-ai/F2LLM-v2-0.6B open weights, 0.6B | 68.6% | huggingface.co | Official leaderboard | ||
| 9 | nvidia/llama-embed-nemotron-8b open weights, 7.5B | 65.9% | huggingface.co | Official leaderboard | ||
| 10 | codefuse-ai/F2LLM-v2-330M open weights, 0.3B | 64.3% | huggingface.co | Official leaderboard | ||
| 11 | KennethEnevoldsen/dfm-sentence-encoder-large open weights, 0.4B | 63.5% | huggingface.co | Official leaderboard | ||
| 12 | FacebookAI/xlm-roberta-large open weights, 0.6B | 62.8% | huggingface.co | Official leaderboard | ||
| 13 | microsoft/harrier-oss-v1-270m open weights, 0.3B | 62.2% | huggingface.co | Official leaderboard | ||
| 14 | FacebookAI/xlm-roberta-base open weights, 0.3B | 60.4% | huggingface.co | Official leaderboard | ||
| 15 | | 57.4% | Jun 2025 | huggingface.co | Official leaderboard | |
| 16 | Octen/Octen-Embedding-8B open weights, 7.6B | 56.5% | huggingface.co | Official leaderboard | ||
| 17 | Alibaba-NLP/gte-Qwen2-7B-instruct open weights, 7.1B | 55.7% | huggingface.co | Official leaderboard | ||
| 18 | Alibaba-NLP/gte-Qwen1.5-7B-instruct open weights, 7.1B | 55.6% | huggingface.co | Official leaderboard | ||
| 19 | Salesforce/SFR-Embedding-2_R open weights, 7.1B | 53.3% | huggingface.co | Official leaderboard | ||
| 20 | Haon-Chen/speed-embedding-7b-instruct open weights, 7.1B | 53.2% | huggingface.co | Official leaderboard | ||
| 21 | BidirLM/BidirLM-1.7B-Embedding open weights, 1.7B | 53.1% | huggingface.co | Official leaderboard | ||
| 22 | emillykkejensen/mmBERTscandi-base-embedding open weights, 0.3B | 52.9% | huggingface.co | Official leaderboard | ||
| 23 | Jaume/gemma-2b-embeddings open weights, 2.5B | 52.8% | huggingface.co | Official leaderboard | ||
| 24 | BidirLM/BidirLM-Omni-2.5B-Embedding open weights, 2.4B | 52.8% | huggingface.co | Official leaderboard | ||
| 25 | McGill-NLP/LLM2Vec-Mistral-7B-Instruct-v2-mntp-unsup-simcse open weights, 7.2B | 52.5% | huggingface.co | Official leaderboard | ||
| 26 | BidirLM/BidirLM-1B-Embedding open weights, 1B | 52.3% | huggingface.co | Official leaderboard | ||
| 27 | nicher92/saga-embed_v1 open weights, 0.4B | 52.1% | huggingface.co | Official leaderboard | ||
| 28 | GritLM/GritLM-7B open weights, 7.2B | 52.1% | huggingface.co | Official leaderboard | ||
| 29 | Bytedance/Seed1.6-embedding-1215 closed weights | 52% | console.volcengine.com | Official leaderboard | ||
| 30 | google/gemini-embedding-001 closed weights | 51.9% | ai.google.dev | Official leaderboard | ||
| 31 | google/text-multilingual-embedding-002 closed weights | 51.8% | cloud.google.com | Official leaderboard | ||
| 32 | KennethEnevoldsen/dfm-sentence-encoder-medium open weights, 0.1B | 51.8% | huggingface.co | Official leaderboard | ||
| 33 | McGill-NLP/LLM2Vec-Mistral-7B-Instruct-v2-mntp-supervised open weights, 7.2B | 51.6% | huggingface.co | Official leaderboard | ||
| 34 | GritLM/GritLM-8x7B open weights, 57.9B | 51.4% | huggingface.co | Official leaderboard | ||
| 35 | | 51.3% | Jun 2025 | huggingface.co | Official leaderboard | |
| 36 | BidirLM/BidirLM-270M-Embedding open weights, 0.3B | 51.3% | huggingface.co | Official leaderboard | ||
| 37 | BidirLM/BidirLM-0.6B-Embedding open weights, 0.6B | 51.2% | huggingface.co | Official leaderboard | ||
| 38 | NbAiLab/nb-sbert-base open weights, 0.2B | 51.2% | huggingface.co | Official leaderboard | ||
| 39 | ai-sage/Giga-Embeddings-instruct-3B-0826 open weights, 3.2B | 51.1% | huggingface.co | Official leaderboard | ||
| 40 | Linq-AI-Research/Linq-Embed-Mistral open weights, 7.1B | 51.1% | huggingface.co | Official leaderboard | ||
| 41 | intfloat/multilingual-e5-large open weights, 0.6B | 51.1% | huggingface.co | Official leaderboard | ||
| 42 | mongodb/voyage-3.5 (output_dtype=int8) closed weights | 51.1% | blog.voyageai.com | Official leaderboard | ||
| 43 | intfloat/e5-mistral-7b-instruct open weights, 7.1B | 51.1% | huggingface.co | Official leaderboard | ||
| 44 | mongodb/voyage-multilingual-2 closed weights | 51.1% | blog.voyageai.com | Official leaderboard | ||
| 45 | codefuse-ai/F2LLM-v2-160M open weights, 0.2B | 51% | huggingface.co | Official leaderboard | ||
| 46 | mongodb/voyage-finance-2 closed weights | 51% | blog.voyageai.com | Official leaderboard | ||
| 47 | ai-sage/Giga-Embeddings-instruct-10B-A1.8B-0826 open weights, 10.5B | 51% | huggingface.co | Official leaderboard | ||
| 48 | Salesforce/SFR-Embedding-Mistral open weights, 7.1B | 51% | huggingface.co | Official leaderboard | ||
| 49 | intfloat/multilingual-e5-base open weights, 0.3B | 50.9% | huggingface.co | Official leaderboard | ||
| 50 | mongodb/voyage-3-lite closed weights | 50.9% | blog.voyageai.com | Official leaderboard | ||
| 51 | Cohere/Cohere-embed-multilingual-v3.0 closed weights | 50.9% | cohere.com | Official leaderboard | ||
| 52 | google/embeddinggemma-300m open weights, 0.3B | 50.8% | ai.google.dev | Official leaderboard | ||
| 53 | openai/text-embedding-3-large closed weights | 50.8% | openai.com | Official leaderboard | ||
| 54 | nvidia/NV-Embed-v2 open weights, 7.9B | 50.7% | huggingface.co | Official leaderboard | ||
| 55 | OrdalieTech/Solon-embeddings-large-0.1 open weights, 0.6B | 50.7% | huggingface.co | Official leaderboard | ||
| 56 | izhx/udever-bloom-7b1 open weights | 50.6% | huggingface.co | Official leaderboard | ||
| 57 | mongodb/voyage-3 closed weights | 50.6% | blog.voyageai.com | Official leaderboard | ||
| 58 | nomic-ai/nomic-embed-text-v2-moe open weights, 0.5B | 50.6% | huggingface.co | Official leaderboard | ||
| 59 | openai/text-embedding-3-large (embed_dim=512) closed weights | 50.6% | openai.com | Official leaderboard | ||
| 60 | emillykkejensen/Qwen3-Embedding-Scandi-0.6B open weights, 0.6B | 50.6% | huggingface.co | Official leaderboard | ||
| 61 | Snowflake/snowflake-arctic-embed-l-v2.0 open weights, 0.6B | 50.6% | huggingface.co | Official leaderboard | ||
| 62 | mongodb/voyage-3.5 closed weights | 50.6% | blog.voyageai.com | Official leaderboard | ||
| 63 | mongodb/voyage-code-3 closed weights | 50.6% | blog.voyageai.com | Official leaderboard | ||
| 64 | sentence-transformers/LaBSE open weights, 0.5B | 50.6% | huggingface.co | Official leaderboard | ||
| 65 | zeroentropy/zembed-1 open weights, 4B | 50.5% | huggingface.co | Official leaderboard | ||
| 66 | Lajavaness/bilingual-embedding-base open weights, 0.3B | 50.5% | huggingface.co | Official leaderboard | ||
| 67 | | 50.5% | Jun 2025 | huggingface.co | Official leaderboard | |
| 68 | omarelshehy/arabic-english-sts-matryoshka open weights, 0.6B | 50.5% | huggingface.co | Official leaderboard | ||
| 69 | mongodb/voyage-3.5 (output_dtype=binary) closed weights | 50.5% | blog.voyageai.com | Official leaderboard | ||
| 70 | BAAI/bge-m3 open weights, 0.6B | 50.4% | huggingface.co | Official leaderboard | ||
| 71 | bigscience/sgpt-bloom-7b1-msmarco open weights, 7.1B | 50.4% | huggingface.co | Official leaderboard | ||
| 72 | mongodb/voyage-multimodal-3 closed weights | 50.4% | huggingface.co | Official leaderboard | ||
| 73 | openai/text-embedding-3-small closed weights | 50.4% | openai.com | Official leaderboard | ||
| 74 | cointegrated/LaBSE-en-ru open weights, 0.1B | 50.4% | huggingface.co | Official leaderboard | ||
| 75 | HIT-TMG/KaLM-embedding-multilingual-mini-v1 open weights, 0.5B | 50.4% | huggingface.co | Official leaderboard | ||
| 76 | intfloat/multilingual-e5-small open weights, 0.1B | 50.4% | huggingface.co | Official leaderboard | ||
| 77 | HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1 open weights, 0.5B | 50.4% | huggingface.co | Official leaderboard | ||
| 78 | izhx/udever-bloom-3b open weights, 3B | 50.4% | huggingface.co | Official leaderboard | ||
| 79 | mongodb/voyage-large-2-instruct closed weights | 50.4% | blog.voyageai.com | Official leaderboard | ||
| 80 | openai/text-embedding-3-small (embed_dim=512) closed weights | 50.4% | openai.com | Official leaderboard | ||
| 81 | Alibaba-NLP/gte-Qwen2-1.5B-instruct open weights, 1.5B | 50.4% | huggingface.co | Official leaderboard | ||
| 82 | nvidia/NV-Embed-v1 open weights, 7.9B | 50.4% | huggingface.co | Official leaderboard | ||
| 83 | deepfile/embedder-100p open weights, 0.3B | 50.4% | huggingface.co | Official leaderboard | ||
| 84 | intfloat/multilingual-e5-large-instruct open weights, 0.6B | 50.4% | huggingface.co | Official leaderboard | ||
| 85 | izhx/udever-bloom-1b1 open weights, 1.1B | 50.4% | huggingface.co | Official leaderboard | ||
| 86 | deepvk/USER-bge-m3 open weights, 0.4B | 50.4% | huggingface.co | Official leaderboard | ||
| 87 | ICT-TIME-and-Querit/ICT-TIME-and-Querit-embedding-v1 open weights, 4B | 50.4% | huggingface.co | Official leaderboard | ||
| 88 | manu/bge-m3-custom-fr open weights, 0.6B | 50.4% | huggingface.co | Official leaderboard | ||
| 89 | mongodb/voyage-law-2 closed weights | 50.4% | blog.voyageai.com | Official leaderboard | ||
| 90 | NovaSearch/stella_en_1.5B_v5 open weights, 1.5B | 50.3% | huggingface.co | Official leaderboard | ||
| 91 | ICT-TIME-and-Querit/BOOM_4B_v1 open weights, 4B | 50.3% | huggingface.co | Official leaderboard | ||
| 92 | Lajavaness/bilingual-embedding-small open weights, 0.1B | 50.3% | huggingface.co | Official leaderboard | ||
| 93 | mongodb/voyage-code-2 closed weights | 50.3% | blog.voyageai.com | Official leaderboard | ||
| 94 | ai-forever/sbert_large_mt_nlu_ru open weights, 0.4B | 50.3% | huggingface.co | Official leaderboard | ||
| 95 | Cohere/Cohere-embed-multilingual-light-v3.0 closed weights | 50.3% | cohere.com | Official leaderboard | ||
| 96 | izhx/udever-bloom-560m open weights, 0.6B | 50.3% | huggingface.co | Official leaderboard | ||
| 97 | brahmairesearch/slx-v0.1 open weights, 0B | 50.3% | huggingface.co | Official leaderboard | ||
| 98 | sentence-transformers/all-MiniLM-L6-v2 open weights, 0B | 50.3% | huggingface.co | Official leaderboard | ||
| 99 | cointegrated/rubert-tiny2 open weights, 0B | 50.3% | huggingface.co | Official leaderboard | ||
| 100 | DeepPavlov/rubert-base-cased open weights, 1.3B | 50.3% | huggingface.co | Official leaderboard | ||
| 101 | cointegrated/rubert-tiny open weights, 0B | 50.3% | huggingface.co | Official leaderboard | ||
| 102 | hotchpotch/bekko-embedding-v1-a25m open weights, 0.1B | 50.3% | huggingface.co | Official leaderboard | ||
| 103 | Lajavaness/bilingual-embedding-large open weights, 0.6B | 50.3% | huggingface.co | Official leaderboard | ||
| 104 | deepvk/deberta-v1-base open weights, 0.1B | 50.2% | huggingface.co | Official leaderboard | ||
| 105 | deepvk/USER-base open weights, 0.4B | 50.2% | huggingface.co | Official leaderboard | ||
| 106 | jinaai/jina-embeddings-v5-omni-small open weights, 1.6B | 50.2% | huggingface.co | Official leaderboard | ||
| 107 | jinaai/jina-embeddings-v5-text-small open weights, 0.6B | 50.2% | huggingface.co | Official leaderboard | ||
| 108 | emillykkejensen/EmbeddingGemma-Scandi-300m open weights, 0.3B | 50.2% | huggingface.co | Official leaderboard | ||
| 109 | KFST/XLMRoberta-en-da-sv-nb open weights, 0.3B | 50.2% | huggingface.co | Official leaderboard | ||
| 110 | silma-ai/silma-embeddding-matryoshka-v0.1 open weights, 0.1B | 50.2% | huggingface.co | Official leaderboard | ||
| 111 | Snowflake/snowflake-arctic-embed-m open weights, 0.1B | 50.2% | huggingface.co | Official leaderboard | ||
| 112 | Omartificial-Intelligence-Space/Arabic-all-nli-triplet-Matryoshka open weights, 0.3B | 50.2% | huggingface.co | Official leaderboard | ||
| 113 | codefuse-ai/F2LLM-v2-80M open weights, 0.1B | 50.2% | huggingface.co | Official leaderboard | ||
| 114 | DeepPavlov/rubert-base-cased-sentence open weights, 0.1B | 50.2% | huggingface.co | Official leaderboard | ||
| 115 | ibm-granite/granite-embedding-107m-multilingual open weights, 0.1B | 50.2% | huggingface.co | Official leaderboard | ||
| 116 | jinaai/jina-embedding-s-en-v1 open weights, 0B | 50.2% | huggingface.co | Official leaderboard | ||
| 117 | manu/sentence_croissant_alpha_v0.2 open weights, 1.3B | 50.2% | huggingface.co | Official leaderboard | ||
| 118 | Mira190/Euler-Legal-Embedding-V1 open weights, 7.6B | 50.2% | huggingface.co | Official leaderboard | ||
| 119 | jinaai/jina-embeddings-v2-small-en open weights, 0B | 50.2% | huggingface.co | Official leaderboard | ||
| 120 | WhereIsAI/UAE-Large-V1 open weights, 0.3B | 50.2% | huggingface.co | Official leaderboard | ||
| 121 | ai-forever/sbert_large_nlu_ru open weights, 0.4B | 50.2% | huggingface.co | Official leaderboard | ||
| 122 | dwzhu/e5-base-4k open weights, 0.1B | 50.2% | huggingface.co | Official leaderboard | ||
| 123 | Hum-Works/lodestone-base-4096-v1 open weights, 0.1B | 50.2% | huggingface.co | Official leaderboard | ||
| 124 | ibm-granite/granite-embedding-278m-multilingual open weights, 0.3B | 50.2% | huggingface.co | Official leaderboard | ||
| 125 | jinaai/jina-embeddings-v3 open weights, 0.6B | 50.2% | huggingface.co | Official leaderboard | ||
| 126 | avsolatorio/GIST-Embedding-v0 open weights, 0.1B | 50.2% | huggingface.co | Official leaderboard | ||
| 127 | infgrad/stella-base-en-v2 open weights, 0.1B | 50.2% | huggingface.co | Official leaderboard | ||
| 128 | intfloat/e5-small-v2 open weights, 0B | 50.2% | huggingface.co | Official leaderboard | ||
| 129 | Mihaiii/gte-micro-v4 open weights, 0B | 50.2% | huggingface.co | Official leaderboard | ||
| 130 | Omartificial-Intelligence-Space/Arabert-all-nli-triplet-Matryoshka open weights, 0.1B | 50.2% | huggingface.co | Official leaderboard | ||
| 131 | Snowflake/snowflake-arctic-embed-m-v2.0 open weights, 0.3B | 50.2% | huggingface.co | Official leaderboard | ||
| 132 | avsolatorio/GIST-all-MiniLM-L6-v2 open weights, 0B | 50.1% | huggingface.co | Official leaderboard | ||
| 133 | intfloat/e5-base-v2 open weights, 0.1B | 50.1% | huggingface.co | Official leaderboard | ||
| 134 | intfloat/e5-large-v2 open weights, 0.3B | 50.1% | huggingface.co | Official leaderboard | ||
| 135 | jinaai/jina-embeddings-v2-base-en open weights, 0.1B | 50.1% | huggingface.co | Official leaderboard | ||
| 136 | Mihaiii/Bulbasaur open weights, 0B | 50.1% | huggingface.co | Official leaderboard | ||
| 137 | abhinand/MedEmbed-small-v0.1 open weights, 0B | 50.1% | huggingface.co | Official leaderboard | ||
| 138 | BAAI/bge-base-en-v1.5 open weights, 0.1B | 50.1% | huggingface.co | Official leaderboard | ||
| 139 | mixedbread-ai/mxbai-embed-large-v1 open weights, 0.3B | 50.1% | huggingface.co | Official leaderboard | ||
| 140 | sdadas/mmlw-e5-small open weights, 0.1B | 50.1% | huggingface.co | Official leaderboard | ||
| 141 | sergeyzh/LaBSE-ru-turbo open weights, 0.1B | 50.1% | huggingface.co | Official leaderboard | ||
| 142 | avsolatorio/GIST-small-Embedding-v0 open weights, 0B | 50.1% | huggingface.co | Official leaderboard | ||
| 143 | Gameselo/STS-multilingual-mpnet-base-v2 open weights, 0.3B | 50.1% | huggingface.co | Official leaderboard | ||
| 144 | mongodb/voyage-2 closed weights | 50.1% | blog.voyageai.com | Official leaderboard | ||
| 145 | mongodb/voyage-large-2 closed weights | 50.1% | blog.voyageai.com | Official leaderboard | ||
| 146 | Omartificial-Intelligence-Space/Arabic-mpnet-base-all-nli-triplet open weights, 0.1B | 50.1% | huggingface.co | Official leaderboard | ||
| 147 | sentence-transformers/all-MiniLM-L12-v2 open weights, 0B | 50.1% | huggingface.co | Official leaderboard | ||
| 148 | Snowflake/snowflake-arctic-embed-s open weights, 0B | 50.1% | huggingface.co | Official leaderboard | ||
| 149 | manu/sentence_croissant_alpha_v0.4 open weights, 1.3B | 50.1% | huggingface.co | Official leaderboard | ||
| 150 | nomic-ai/nomic-embed-text-v1-ablated open weights, 0.1B | 50.1% | huggingface.co | Official leaderboard | ||
| 151 | sdadas/mmlw-e5-base open weights, 0.3B | 50.1% | huggingface.co | Official leaderboard | ||
| 152 | sentence-transformers/static-similarity-mrl-multilingual-v1 open weights, 0.1B | 50.1% | huggingface.co | Official leaderboard | ||
| 153 | DeepPavlov/distilrubert-small-cased-conversational open weights, 0.1B | 50.1% | huggingface.co | Official leaderboard | ||
| 154 | jinaai/jina-embeddings-v5-omni-nano open weights, 1B | 50.1% | huggingface.co | Official leaderboard | ||
| 155 | jinaai/jina-embeddings-v5-text-nano open weights, 0.2B | 50.1% | huggingface.co | Official leaderboard | ||
| 156 | Mihaiii/Squirtle open weights, 0B | 50.1% | huggingface.co | Official leaderboard | ||
| 157 | minishlab/M2V_base_glove open weights, 0.1B | 50.1% | huggingface.co | Official leaderboard | ||
| 158 | NovaSearch/stella_en_400M_v5 open weights, 0.4B | 50.1% | huggingface.co | Official leaderboard | ||
| 159 | Omartificial-Intelligence-Space/Arabic-labse-Matryoshka open weights, 0.5B | 50.1% | huggingface.co | Official leaderboard | ||
| 160 | sdadas/mmlw-roberta-base open weights, 0.1B | 50.1% | huggingface.co | Official leaderboard | ||
| 161 | sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 open weights, 0.1B | 50.1% | huggingface.co | Official leaderboard | ||
| 162 | Snowflake/snowflake-arctic-embed-m-long open weights, 0.1B | 50.1% | huggingface.co | Official leaderboard | ||
| 163 | BAAI/bge-large-en-v1.5 open weights, 0.3B | 50.1% | huggingface.co | Official leaderboard | ||
| 164 | BAAI/bge-small-en-v1.5 open weights, 0B | 50.1% | huggingface.co | Official leaderboard | ||
| 165 | hotchpotch/bekko-embedding-v1-a8m open weights, 0.1B | 50.1% | huggingface.co | Official leaderboard | ||
| 166 | ibm-granite/granite-embedding-30m-english open weights, 0B | 50.1% | huggingface.co | Official leaderboard | ||
| 167 | jinaai/jina-embedding-b-en-v1 open weights, 0.1B | 50.1% | huggingface.co | Official leaderboard | ||
| 168 | Omartificial-Intelligence-Space/Marbert-all-nli-triplet-Matryoshka open weights, 0.2B | 50.1% | huggingface.co | Official leaderboard | ||
| 169 | sdadas/mmlw-roberta-large open weights, 0.4B | 50.1% | huggingface.co | Official leaderboard | ||
| 170 | shibing624/text2vec-base-multilingual open weights, 0.1B | 50.1% | huggingface.co | Official leaderboard | ||
| 171 | Alibaba-NLP/gte-multilingual-base open weights, 0.3B | 50.1% | huggingface.co | Official leaderboard | ||
| 172 | Mihaiii/gte-micro open weights, 0B | 50.1% | huggingface.co | Official leaderboard | ||
| 173 | thenlper/gte-small open weights, 0B | 50.1% | huggingface.co | Official leaderboard | ||
| 174 | aari1995/German_Semantic_STS_V2 open weights, 0.3B | 50.1% | huggingface.co | Official leaderboard | ||
| 175 | avsolatorio/NoInstruct-small-Embedding-v0 open weights, 0B | 50.1% | huggingface.co | Official leaderboard | ||
| 176 | hotchpotch/bekko-static-embedding-v1 open weights, 0.2B | 50.1% | huggingface.co | Official leaderboard | ||
| 177 | ibm-granite/granite-embedding-97m-multilingual-r2 open weights, 0.1B | 50.1% | huggingface.co | Official leaderboard | ||
| 178 | manu/sentence_croissant_alpha_v0.3 open weights, 1.3B | 50.1% | huggingface.co | Official leaderboard | ||
| 179 | thenlper/gte-base open weights, 0.1B | 50.1% | huggingface.co | Official leaderboard | ||
| 180 | | 50.1% | Oct 2026 | huggingface.co | Official leaderboard | |
| 181 | Mihaiii/Ivysaur open weights, 0B | 50.1% | huggingface.co | Official leaderboard | ||
| 182 | minishlab/M2V_base_output open weights, 0B | 50.1% | huggingface.co | Official leaderboard | ||
| 183 | minishlab/potion-multilingual-128M open weights, 0.1B | 50.1% | huggingface.co | Official leaderboard | ||
| 184 | sergeyzh/rubert-tiny-turbo open weights, 0B | 50.1% | huggingface.co | Official leaderboard | ||
| 185 | andersborges/model2vecdk open weights, 0B | 50.1% | huggingface.co | Official leaderboard | ||
| 186 | Mihaiii/Venusaur open weights, 0B | 50.1% | huggingface.co | Official leaderboard | ||
| 187 | Mihaiii/Wartortle open weights, 0B | 50.1% | huggingface.co | Official leaderboard | ||
| 188 | sentence-transformers/all-mpnet-base-v2 open weights, 0.1B | 50.1% | huggingface.co | Official leaderboard | ||
| 189 | thenlper/gte-large open weights, 0.3B | 50.1% | huggingface.co | Official leaderboard | ||
| 190 | cnmoro/static-nomic-384-pten-v2-st open weights, 0.1B | 50% | huggingface.co | Official leaderboard | ||
| 191 | ibm-granite/granite-embedding-125m-english open weights, 0.1B | 50% | huggingface.co | Official leaderboard | ||
| 192 | sdadas/mmlw-e5-large open weights, 0.6B | 50% | huggingface.co | Official leaderboard | ||
| 193 | ai-forever/ru-en-RoSBERTa open weights, 0.4B | 50% | huggingface.co | Official leaderboard | ||
| 194 | ibm-granite/granite-embedding-311m-multilingual-r2 open weights, 0.3B | 50% | huggingface.co | Official leaderboard | ||
| 195 | malenia1/ternary-weight-embedding open weights, 0.1B | 50% | huggingface.co | Official leaderboard | ||
| 196 | nomic-ai/nomic-embed-text-v1.5 open weights, 0.1B | 50% | huggingface.co | Official leaderboard | ||
| 197 | sentence-transformers/paraphrase-multilingual-mpnet-base-v2 open weights, 0.3B | 50% | huggingface.co | Official leaderboard | ||
| 198 | nomic-ai/nomic-embed-text-v1 open weights, 0.1B | 50% | huggingface.co | Official leaderboard | ||
| 199 | Snowflake/snowflake-arctic-embed-xs open weights, 0B | 50% | huggingface.co | Official leaderboard | ||
| 200 | consciousAI/cai-lunaris-text-embeddings open weights, 0.3B | 50% | huggingface.co | Official leaderboard | ||
| 201 | nomic-ai/nomic-embed-text-v1-unsupervised open weights, 0.1B | 50% | huggingface.co | Official leaderboard | ||
| 202 | Snowflake/snowflake-arctic-embed-m-v1.5 open weights, 0.1B | 50% | huggingface.co | Official leaderboard | ||
| 203 | Cohere/Cohere-embed-english-v3.0 closed weights | 50% | cohere.com | Official leaderboard | ||
| 204 | minishlab/M2V_base_glove_subword open weights, 0.1B | 50% | huggingface.co | Official leaderboard | ||
| 205 | Snowflake/snowflake-arctic-embed-l open weights, 0.3B | 50% | huggingface.co | Official leaderboard | ||
| 206 | minishlab/potion-base-4M open weights, 0B | 50% | huggingface.co | Official leaderboard | ||
| 207 | Omartificial-Intelligence-Space/Arabic-MiniLM-L12-v2-all-nli-triplet open weights, 0.1B | 50% | huggingface.co | Official leaderboard | ||
| 208 | rasgaard/m2v-dfm-large open weights, 0B | 50% | huggingface.co | Official leaderboard | ||
| 209 | andersborges/model2vecdk-stem open weights, 0B | 50% | huggingface.co | Official leaderboard | ||
| 210 | intfloat/e5-large open weights, 0.3B | 50% | huggingface.co | Official leaderboard | ||
| 211 | intfloat/e5-small open weights, 0B | 50% | huggingface.co | Official leaderboard | ||
| 212 | minishlab/potion-base-8M open weights, 0B | 50% | huggingface.co | Official leaderboard | ||
| 213 | Cohere/Cohere-embed-english-light-v3.0 closed weights | 50% | cohere.com | Official leaderboard | ||
| 214 | avsolatorio/GIST-large-Embedding-v0 open weights, 0.3B | 50% | huggingface.co | Official leaderboard | ||
| 215 | minishlab/potion-base-2M open weights, 0B | 50% | huggingface.co | Official leaderboard | ||
| 216 | intfloat/e5-base open weights, 0.1B | 49.9% | huggingface.co | Official leaderboard |
| # | Model | Score | Setting | Date | Link | Source |
|---|---|---|---|---|---|---|
| 1 | | 57.4% | Jun 2025 | huggingface.co | Official leaderboard | |
| 2 | | 51.3% | Jun 2025 | huggingface.co | Official leaderboard | |
| 3 | | 50.5% | Jun 2025 | huggingface.co | Official leaderboard | |
| 4 | | 50.1% | Oct 2026 | huggingface.co | Official leaderboard |
Rankings by part
We read 4 parts from MTEB’s leaderboard, each ranking models on one part of the test, such as Danish, Norwegian Bokmål and Norwegian Nynorsk. Qwen3-Embedding-8B leads every one of them. Arrows show how far a model moved from its overall rank among the models we track.
Danish
4 models we track have a score here.
- 1
Qwen3-Embedding-8B 0.59%
- 2
Qwen3-Embedding-4B 0.52%
- 3
Qwen3-Embedding-0.6B 0.51%
- 4
EmbeddingGemma 2 0.50%
Norwegian Bokmål
4 models we track have a score here.
- 1
Qwen3-Embedding-8B 0.57%
- 2
Qwen3-Embedding-4B 0.51%
- 3
Qwen3-Embedding-0.6B 0.51%
- 4
EmbeddingGemma 2 0.50%
Norwegian Nynorsk
4 models we track have a score here.
- 1
Qwen3-Embedding-8B 0.53%
- 2
Qwen3-Embedding-4B 0.51%
- 3
EmbeddingGemma 2 ↑1 0.50%
- 4
Qwen3-Embedding-0.6B ↓1 0.50%
Swedish
4 models we track have a score here.
- 1
Qwen3-Embedding-8B 0.61%
- 2
Qwen3-Embedding-4B 0.52%
- 3
Qwen3-Embedding-0.6B 0.51%
- 4
EmbeddingGemma 2 0.50%
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 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 10 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 4 pass 1 note
- Pass Independent runs Scores from the benchmark’s paper (216 entries).
- Pass Models scored 4 models we track, plus 212 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.
- Pass Headroom The best is 57.4%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on MTEB: 4 rows for models we track and 212 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.