Benchmark By Score Rank
Retrieval 3
MTEB Mandarin Chinesev1 · Retrieval · Mandarin Chinese Embeddings rank relevant documents for queries on MTEB Chinese v1 · Retrieval in Mandarin Chinese MTEB 24.5 #80 of 86+2 versions & slices v1 · Reranking · Mandarin Chinese Embeddings reorder candidate documents by relevance on MTEB Chinese v1 · Reranking in Mandarin Chinese MTEB 44.3 #64 of 71v1 · Classification · Mandarin Chinese Embeddings assign examples to categories on MTEB Chinese v1 · Classification in Mandarin Chinese MTEB 63.1 #38 of 55
Reranking 40
MTEB Dutchv1 · Reranking · Dutch Embeddings reorder candidate documents by relevance on MTEB Dutch v1 · Reranking in Dutch MTEB 80.6 #101 of 200+8 versions & slices v1 · Clustering · Dutch Embeddings group similar examples on MTEB Dutch v1 · Clustering in Dutch MTEB 29 #56 of 133v1 · Multilabel Classification · Dutch Embeddings assign multiple labels to each example on MTEB Dutch v1 · Multilabel Classification in Dutch MTEB 30.9 #80 of 133v1 · Pair Classification · Dutch Embeddings classify relationships between pairs on MTEB Dutch v1 · Pair Classification in Dutch MTEB 78.2 #33 of 133v1 · STS · Dutch Embeddings estimate semantic similarity between pairs on MTEB Dutch v1 · STS in Dutch MTEB 77.3 #43 of 133v1 · Classification · Dutch Embeddings assign examples to categories on MTEB Dutch v1 · Classification in Dutch MTEB 55.4 #60 of 131v1 · Retrieval · Dutch Embeddings rank relevant documents for queries on MTEB Dutch v1 · Retrieval in Dutch MTEB 37.7 #80 of 131v1 · Mean over tasks · Dutch Embeddings rank relevant documents for queries, assign examples to categories, assign multiple labels to each example, estimate semantic similarity between pairs, group similar examples, reorder candidate documents by relevance, classify relationships between pairs on MTEB Dutch v1 · mean over tasks in Dutch; tasks receive equal weight MTEB 45.8 #61 of 129v1 · Mean over task types · Dutch Embeddings rank relevant documents for queries, assign examples to categories, assign multiple labels to each example, estimate semantic similarity between pairs, group similar examples, reorder candidate documents by relevance, classify relationships between pairs on MTEB Dutch v1 · mean over task types in Dutch; task types receive equal weight MTEB 55.6 #63 of 129
MTEB Europev1 · Instruction Reranking · English Embeddings rerank documents according to instructions on MTEB Europe v1 · Instruction Reranking in English MTEB -1.3 #91 of 192+10 versions & slices v1 · Bitext Mining · multilingual (28 languages) Embeddings find translated sentence pairs on MTEB Europe v1 · Bitext Mining in 28 languages including Basque, Bulgarian, Croatian, Czech, Danish, Dutch, English, Estonian MTEB 77 #81 of 175v1 · Reranking · multilingual (12 languages) Embeddings reorder candidate documents by relevance on MTEB Europe v1 · Reranking in Bulgarian, Czech, Danish, Dutch, English, Finnish, French, German, Italian, Portuguese, Romanian, Swedish MTEB 50.2 #101 of 175v1 · Multilabel Classification · multilingual (23 languages) Embeddings assign multiple labels to each example on MTEB Europe v1 · Multilabel Classification in 23 languages including Bulgarian, Croatian, Czech, Danish, Dutch, English, Estonian, Finnish MTEB 5.7 #146 of 173v1 · Clustering · multilingual (29 languages) Embeddings group similar examples on MTEB Europe v1 · Clustering in 29 languages including Basque, Bulgarian, Croatian, Czech, Danish, Dutch, English, Estonian MTEB 34.4 #115 of 167v1 · Pair Classification · multilingual (11 languages) Embeddings classify relationships between pairs on MTEB Europe v1 · Pair Classification in Bulgarian, Czech, English, Finnish, French, German, Italian, Modern Greek (1453-), Polish, Spanish, Swedish MTEB 88.9 #33 of 154v1 · Retrieval · multilingual (25 languages) Embeddings rank relevant documents for queries on MTEB Europe v1 · Retrieval in 25 languages including Basque, Bulgarian, Croatian, Czech, Danish, Dutch, English, Estonian MTEB 37.6 #102 of 153v1 · Classification · multilingual (23 languages) Embeddings assign examples to categories on MTEB Europe v1 · Classification in 23 languages including Bulgarian, Czech, Danish, Dutch, English, Estonian, Finnish, French MTEB 52.7 #59 of 138v1 · STS · multilingual (8 languages) Embeddings estimate semantic similarity between pairs on MTEB Europe v1 · STS in Dutch, English, Finnish, French, German, Italian, Polish, Spanish MTEB 72.5 #37 of 105v1 · Mean over tasks · multilingual (29 languages) Embeddings assign examples to categories, rerank documents according to instructions, assign multiple labels to each example, estimate semantic similarity between pairs, classify relationships between pairs, group similar examples, rank relevant documents for queries, reorder candidate documents by relevance, find translated sentence pairs on MTEB Europe v1 · mean over tasks in 29 languages including Basque, Bulgarian, Croatian, Czech, Danish, Dutch, English, Estonian; tasks receive equal weight MTEB 51.7 #30 of 68v1 · Mean over task types · multilingual (29 languages) Embeddings assign examples to categories, rerank documents according to instructions, assign multiple labels to each example, estimate semantic similarity between pairs, classify relationships between pairs, group similar examples, rank relevant documents for queries, reorder candidate documents by relevance, find translated sentence pairs on MTEB Europe v1 · mean over task types in 29 languages including Basque, Bulgarian, Croatian, Czech, Danish, Dutch, English, Estonian; task types receive equal weight MTEB 46.4 #30 of 68
MTEB multilingualv2 · Instruction Reranking · English Embeddings rerank documents according to instructions on MTEB Multilingual v2 · Instruction Reranking in English MTEB -1.3 #91 of 192+10 versions & slices v2 · Retrieval · multilingual (120 languages) Embeddings rank relevant documents for queries on MTEB Multilingual v2 · Retrieval in 120 languages including Afrikaans, Amharic, Arabic, Armenian, Assamese, Bambara, Basque, Bengali MTEB 36.6 #116 of 176v2 · Bitext Mining · multilingual (1026 languages) Embeddings find translated sentence pairs on MTEB Multilingual v2 · Bitext Mining in 1026 languages including 'Auhelawa, Abau, Achi, Achinese, Achuar-Shiwiar, Adzera, Afrikaans, Agarabi MTEB 44.6 #82 of 173v2 · Multilabel Classification · multilingual (25 languages) Embeddings assign multiple labels to each example on MTEB Multilingual v2 · Multilabel Classification in 25 languages including Bulgarian, Croatian, Czech, Danish, Dutch, English, Estonian, Finnish MTEB 14.9 #137 of 173v2 · Reranking · multilingual (22 languages) Embeddings reorder candidate documents by relevance on MTEB Multilingual v2 · Reranking in 22 languages including Bengali, Bulgarian, Czech, Danish, Dutch, English, Finnish, French MTEB 51 #78 of 173v2 · Pair Classification · multilingual (24 languages) Embeddings classify relationships between pairs on MTEB Multilingual v2 · Pair Classification in 24 languages including Arabic, Armenian, Bulgarian, Chinese, Czech, English, Finnish, French MTEB 79 #44 of 166v2 · Clustering · multilingual (208 languages) Embeddings group similar examples on MTEB Multilingual v2 · Clustering in 208 languages including Achinese, Afrikaans, Akan, Albanian, Amharic, Armenian, Assamese, Asturian MTEB 38.3 #110 of 160v2 · Classification · multilingual (119 languages) Embeddings assign examples to categories on MTEB Multilingual v2 · Classification in 119 languages including Achinese, Afrikaans, Albanian, Algerian Arabic, Amharic, Arabic, Armenian, Assamese MTEB 51.7 #74 of 154v2 · STS · multilingual (35 languages) Embeddings estimate semantic similarity between pairs on MTEB Multilingual v2 · STS in 35 languages including Afrikaans, Algerian Arabic, Amharic, Arabic, Assamese, Bengali, Dutch, English MTEB 66.6 #61 of 120v2 · Mean over tasks · multilingual (1037 languages) Embeddings group similar examples, estimate semantic similarity between pairs, assign examples to categories, rank relevant documents for queries, assign multiple labels to each example, find translated sentence pairs, rerank documents according to instructions, reorder candidate documents by relevance, classify relationships between pairs on MTEB Multilingual v2 · mean over tasks in 1037 languages including 'Auhelawa, Abau, Achi, Achinese, Achuar-Shiwiar, Adzera, Afrikaans, Agarabi; tasks receive equal weight MTEB 48.7 #54 of 91v2 · Mean over task types · multilingual (1037 languages) Embeddings group similar examples, estimate semantic similarity between pairs, assign examples to categories, rank relevant documents for queries, assign multiple labels to each example, find translated sentence pairs, rerank documents according to instructions, reorder candidate documents by relevance, classify relationships between pairs on MTEB Multilingual v2 · mean over task types in 1037 languages including 'Auhelawa, Abau, Achi, Achinese, Achuar-Shiwiar, Adzera, Afrikaans, Agarabi; task types receive equal weight MTEB 42.4 #55 of 91
MTEB Persianv2 · Reranking · Persian Embeddings reorder candidate documents by relevance on MTEB Persian v2 · Reranking in Persian MTEB 55.8 #54 of 149+8 versions & slices v2 · Bitext Mining · Persian Embeddings find translated sentence pairs on MTEB Persian v2 · Bitext Mining in Persian MTEB 31.9 #38 of 44v2 · Clustering · Persian Embeddings group similar examples on MTEB Persian v2 · Clustering in Persian MTEB 58.1 #32 of 44v2 · STS · Persian Embeddings estimate semantic similarity between pairs on MTEB Persian v2 · STS in Persian MTEB 75 #28 of 43v2 · Pair Classification · Persian Embeddings classify relationships between pairs on MTEB Persian v2 · Pair Classification in Persian MTEB 78 #33 of 42v2 · Classification · Persian Embeddings assign examples to categories on MTEB Persian v2 · Classification in Persian MTEB 59.2 #33 of 35v2 · Mean over tasks · Persian Embeddings reorder candidate documents by relevance, classify relationships between pairs, group similar examples, assign examples to categories, rank relevant documents for queries, estimate semantic similarity between pairs, find translated sentence pairs on MTEB Persian v2 · mean over tasks in Persian; tasks receive equal weight MTEB 51.3 #27 of 33v2 · Mean over task types · Persian Embeddings reorder candidate documents by relevance, classify relationships between pairs, group similar examples, assign examples to categories, rank relevant documents for queries, estimate semantic similarity between pairs, find translated sentence pairs on MTEB Persian v2 · mean over task types in Persian; task types receive equal weight MTEB 55.6 #27 of 33v2 · Retrieval · Persian Embeddings rank relevant documents for queries on MTEB Persian v2 · Retrieval in Persian MTEB 31 #26 of 33
Other 108
MTEB Englishv2 · Pair Classification · English Embeddings classify relationships between pairs in English MTEB 80 #186 of 238+6 versions & slices v2 · Reranking · English Embeddings reorder candidate documents by relevance in English MTEB 45.4 #143 of 223v2 · Classification · English Embeddings assign examples to categories in English MTEB 69.2 #180 of 222v2 · Summarization · English Embeddings match summaries to their source meaning in English MTEB 26.9 #164 of 209v2 · Clustering · English Embeddings group similar examples in English MTEB 41.7 #153 of 207v2 · STS · English Embeddings estimate semantic similarity between pairs in English MTEB 78.7 #130 of 200v2 · Retrieval · English Embeddings rank relevant documents for queries in English MTEB 35.9 #155 of 200
MTEB Medicalv1 · Clustering · English Embeddings group similar examples on MTEB Medical v1 · Clustering in English MTEB 35.1 #121 of 220+4 versions & slices v1 · Reranking · Mandarin Chinese Embeddings reorder candidate documents by relevance on MTEB Medical v1 · Reranking in Mandarin Chinese MTEB 48.6 #94 of 202v1 · Retrieval · multilingual (10 languages) Embeddings rank relevant documents for queries on MTEB Medical v1 · Retrieval in Arabic, Chinese, English, French, Korean, Mandarin Chinese, Polish, Russian, Spanish, Vietnamese MTEB 37.5 #91 of 140v1 · Mean over tasks · multilingual (10 languages) Embeddings rank relevant documents for queries, group similar examples, reorder candidate documents by relevance on MTEB Medical v1 · mean over tasks in Arabic, Chinese, English, French, Korean, Mandarin Chinese, Polish, Russian, Spanish, Vietnamese; tasks receive equal weight MTEB 38 #81 of 138v1 · Mean over task types · multilingual (10 languages) Embeddings rank relevant documents for queries, group similar examples, reorder candidate documents by relevance on MTEB Medical v1 · mean over task types in Arabic, Chinese, English, French, Korean, Mandarin Chinese, Polish, Russian, Spanish, Vietnamese; task types receive equal weight MTEB 40.4 #49 of 138
RTEB French betaMean over tasks · multilingual (2 languages) Embeddings rank relevant documents for queries on RTEB French Beta · mean over tasks in English, French; tasks receive equal weight MTEB 22.3 #120 of 215
RTEB German betaMean over tasks · German Embeddings rank relevant documents for queries on RTEB German Beta · mean over tasks in German; tasks receive equal weight MTEB 13.3 #160 of 212
RTEB Law betaMean over tasks · multilingual (4 languages) Embeddings rank relevant documents for queries on RTEB Law Beta · mean over tasks in English, French, German, Japanese; tasks receive equal weight MTEB 25.6 #172 of 209
MTEB Scandinavianv1 · Bitext Mining · multilingual (3 languages) Embeddings find translated sentence pairs on MTEB Scandinavian v1 · Bitext Mining in Danish, Norwegian Bokmål, Norwegian Nynorsk MTEB 51 #176 of 206+5 versions & slices v1 · Clustering · multilingual (2 languages) Embeddings group similar examples on MTEB Scandinavian v1 · Clustering in Norwegian Bokmål, Swedish MTEB 34.5 #87 of 175v1 · Classification · multilingual (6 languages) Embeddings assign examples to categories on MTEB Scandinavian v1 · Classification in Danish, Faroese, Icelandic, Norwegian Bokmål, Norwegian Nynorsk, Swedish MTEB 55.8 #63 of 158v1 · Retrieval · multilingual (3 languages) Embeddings rank relevant documents for queries on MTEB Scandinavian v1 · Retrieval in Danish, Norwegian Bokmål, Swedish MTEB 43.5 #72 of 144v1 · Mean over tasks · multilingual (6 languages) Embeddings assign examples to categories, rank relevant documents for queries, group similar examples, find translated sentence pairs on MTEB Scandinavian v1 · mean over tasks in Danish, Faroese, Icelandic, Norwegian Bokmål, Norwegian Nynorsk, Swedish; tasks receive equal weight MTEB 47.8 #55 of 135v1 · Mean over task types · multilingual (6 languages) Embeddings assign examples to categories, rank relevant documents for queries, group similar examples, find translated sentence pairs on MTEB Scandinavian v1 · mean over task types in Danish, Faroese, Icelandic, Norwegian Bokmål, Norwegian Nynorsk, Swedish; task types receive equal weight MTEB 46.2 #72 of 135
BEIRMean over tasks · English Embeddings rank relevant documents for queries on BEIR · mean over tasks in English; tasks receive equal weight MTEB 33.4 #162 of 196+2 versions & slices Mean over task types · English Embeddings rank relevant documents for queries on BEIR · mean over task types in English; task types receive equal weight MTEB 33.4 #162 of 196Retrieval · English Embeddings rank relevant documents for queries on BEIR · Retrieval in English MTEB 33.4 #162 of 196
MTEB Russianv1.1 · Pair Classification · Russian Embeddings classify relationships between pairs on MTEB Russian v1.1 · Pair Classification in Russian MTEB 58.6 #48 of 194+8 versions & slices v1.1 · Multilabel Classification · Russian Embeddings assign multiple labels to each example on MTEB Russian v1.1 · Multilabel Classification in Russian MTEB 31.3 #74 of 162v1.1 · Clustering · Russian Embeddings group similar examples on MTEB Russian v1.1 · Clustering in Russian MTEB 47.8 #76 of 158v1.1 · Reranking · Russian Embeddings reorder candidate documents by relevance on MTEB Russian v1.1 · Reranking in Russian MTEB 46.3 #65 of 153v1.1 · Classification · Russian Embeddings assign examples to categories on MTEB Russian v1.1 · Classification in Russian MTEB 53.9 #75 of 146v1.1 · STS · Russian Embeddings estimate semantic similarity between pairs on MTEB Russian v1.1 · STS in Russian MTEB 66.2 #61 of 139v1.1 · Retrieval · Russian Embeddings rank relevant documents for queries on MTEB Russian v1.1 · Retrieval in Russian MTEB 34.1 #47 of 109v1.1 · Mean over tasks · Russian Embeddings assign examples to categories, group similar examples, reorder candidate documents by relevance, assign multiple labels to each example, estimate semantic similarity between pairs, rank relevant documents for queries, classify relationships between pairs on MTEB Russian v1.1 · mean over tasks in Russian; tasks receive equal weight MTEB 49.7 #46 of 106v1.1 · Mean over task types · Russian Embeddings assign examples to categories, group similar examples, reorder candidate documents by relevance, assign multiple labels to each example, estimate semantic similarity between pairs, rank relevant documents for queries, classify relationships between pairs on MTEB Russian v1.1 · mean over task types in Russian; task types receive equal weight MTEB 48.3 #46 of 106
MTEB Portuguesev1 · Multilabel Classification · Portuguese Embeddings assign multiple labels to each example on MTEB Portuguese v1 · Multilabel Classification in Portuguese MTEB 20.1 #74 of 193+6 versions & slices v1 · Classification · Portuguese Embeddings assign examples to categories on MTEB Portuguese v1 · Classification in Portuguese MTEB 54.8 #37 of 49v1 · STS · Portuguese Embeddings estimate semantic similarity between pairs on MTEB Portuguese v1 · STS in Portuguese MTEB 76.6 #27 of 44v1 · Reranking · Portuguese Embeddings reorder candidate documents by relevance on MTEB Portuguese v1 · Reranking in Portuguese MTEB 80.9 #24 of 33v1 · Mean over tasks · Portuguese Embeddings reorder candidate documents by relevance, assign examples to categories, estimate semantic similarity between pairs, assign multiple labels to each example, rank relevant documents for queries on MTEB Portuguese v1 · mean over tasks in Portuguese; tasks receive equal weight MTEB 62.2 #16 of 22v1 · Mean over task types · Portuguese Embeddings reorder candidate documents by relevance, assign examples to categories, estimate semantic similarity between pairs, assign multiple labels to each example, rank relevant documents for queries on MTEB Portuguese v1 · mean over task types in Portuguese; task types receive equal weight MTEB 57.1 #16 of 22v1 · Retrieval · Portuguese Embeddings rank relevant documents for queries on MTEB Portuguese v1 · Retrieval in Portuguese MTEB 52.9 #17 of 22
FollowIRMean over tasks · English Embeddings rerank documents according to instructions on FollowIR · mean over tasks in English; tasks receive equal weight MTEB -1.3 #91 of 192+2 versions & slices Mean over task types · English Embeddings rerank documents according to instructions on FollowIR · mean over task types in English; task types receive equal weight MTEB -1.3 #91 of 192Instruction Reranking · English Embeddings rerank documents according to instructions on FollowIR · Instruction Reranking in English MTEB -1.3 #91 of 192
MTEB Indicv1 · STS · multilingual (13 languages) Embeddings estimate semantic similarity between pairs on MTEB Indic v1 · STS in Assamese, Bengali, English, Gujarati, Hindi, Kannada, Malayalam, Marathi, Odia, Panjabi, Tamil, Telugu, Urdu MTEB 19.8 #80 of 192+8 versions & slices v1 · Clustering · multilingual (21 languages) Embeddings group similar examples on MTEB Indic v1 · Clustering in Assamese, Awadhi, Bengali, Bhojpuri, Chhattisgarhi, Gujarati, Hindi, Kannada, Kashmiri, Maithili, Malayalam, Manipuri, Marathi, Nepali (individual language), Odia, Panjabi, Sanskrit, Sindhi, Tamil, Telugu, Urdu MTEB 16.7 #88 of 187v1 · Reranking · multilingual (2 languages) Embeddings reorder candidate documents by relevance on MTEB Indic v1 · Reranking in Bengali, Hindi MTEB 59.3 #99 of 183v1 · Pair Classification · Hindi Embeddings classify relationships between pairs on MTEB Indic v1 · Pair Classification in Hindi MTEB 77.8 #23 of 179v1 · Bitext Mining · multilingual (20 languages) Embeddings find translated sentence pairs on MTEB Indic v1 · Bitext Mining in Assamese, Bengali, Dogri (macrolanguage), Goan Konkani, Gujarati, Hindi, Kannada, Kashmiri, Maithili, Malayalam, Manipuri, Marathi, Nepali (individual language), Odia, Panjabi, Sanskrit, Sindhi, Tamil, Telugu, Urdu MTEB 15.3 #63 of 162v1 · Retrieval · multilingual (14 languages) Embeddings rank relevant documents for queries on MTEB Indic v1 · Retrieval in Assamese, Bengali, Gujarati, Hindi, Kannada, Malayalam, Marathi, Nepali (individual language), Odia, Panjabi, Sindhi, Tamil, Telugu, Urdu MTEB 48.8 #66 of 153v1 · Classification · multilingual (8 languages) Embeddings assign examples to categories on MTEB Indic v1 · Classification in Bengali, Gujarati, Hindi, Malayalam, Nepali (macrolanguage), Panjabi, Sanskrit, Urdu MTEB 57.8 #56 of 141v1 · Mean over tasks · multilingual (25 languages) Embeddings assign examples to categories, find translated sentence pairs, estimate semantic similarity between pairs, reorder candidate documents by relevance, rank relevant documents for queries, classify relationships between pairs, group similar examples on MTEB Indic v1 · mean over tasks in 25 languages including Assamese, Awadhi, Bengali, Bhojpuri, Chhattisgarhi, Dogri (macrolanguage), English, Goan Konkani; tasks receive equal weight MTEB 49.8 #52 of 125v1 · Mean over task types · multilingual (25 languages) Embeddings assign examples to categories, find translated sentence pairs, estimate semantic similarity between pairs, reorder candidate documents by relevance, rank relevant documents for queries, classify relationships between pairs, group similar examples on MTEB Indic v1 · mean over task types in 25 languages including Assamese, Awadhi, Bengali, Bhojpuri, Chhattisgarhi, Dogri (macrolanguage), English, Goan Konkani; task types receive equal weight MTEB 42.2 #52 of 125
MTEB Thaiv1 · Clustering · Thai Embeddings group similar examples on MTEB Thai v1 · Clustering in Thai MTEB 43 #56 of 192+3 versions & slices v1 · Pair Classification · Thai Embeddings classify relationships between pairs on MTEB Thai v1 · Pair Classification in Thai MTEB 80.4 #17 of 182v1 · Classification · Thai Embeddings assign examples to categories on MTEB Thai v1 · Classification in Thai MTEB 61.8 #24 of 35v1 · Reranking · Thai Embeddings reorder candidate documents by relevance on MTEB Thai v1 · Reranking in Thai MTEB 63.8 #13 of 33
MTEB Frenchv1 · Pair Classification · French Embeddings classify relationships between pairs on MTEB French v1 · Pair Classification in French MTEB 56.7 #111 of 188+8 versions & slices v1 · Summarization · French Embeddings match summaries to their source meaning on MTEB French v1 · Summarization in French MTEB 29.2 #119 of 158v1 · Reranking · French Embeddings reorder candidate documents by relevance on MTEB French v1 · Reranking in French MTEB 67.5 #82 of 144v1 · Retrieval · multilingual (2 languages) Embeddings rank relevant documents for queries on MTEB French v1 · Retrieval in English, French MTEB 37.8 #72 of 138v1 · Classification · French Embeddings assign examples to categories on MTEB French v1 · Classification in French MTEB 61.4 #53 of 134v1 · Clustering · French Embeddings group similar examples on MTEB French v1 · Clustering in French MTEB 38.3 #77 of 120v1 · STS · French Embeddings estimate semantic similarity between pairs on MTEB French v1 · STS in French MTEB 75.7 #37 of 112v1 · Mean over tasks · multilingual (2 languages) Embeddings estimate semantic similarity between pairs, rank relevant documents for queries, assign examples to categories, group similar examples, reorder candidate documents by relevance, classify relationships between pairs, match summaries to their source meaning on MTEB French v1 · mean over tasks in English, French; tasks receive equal weight MTEB 50.9 #40 of 102v1 · Mean over task types · multilingual (2 languages) Embeddings estimate semantic similarity between pairs, rank relevant documents for queries, assign examples to categories, group similar examples, reorder candidate documents by relevance, classify relationships between pairs, match summaries to their source meaning on MTEB French v1 · mean over task types in English, French; task types receive equal weight MTEB 52.4 #40 of 102
MTEB Germanv1 · Pair Classification · German Embeddings classify relationships between pairs on MTEB German v1 · Pair Classification in German MTEB 50.5 #78 of 175+7 versions & slices v1 · Classification · German Embeddings assign examples to categories on MTEB German v1 · Classification in German MTEB 57.6 #67 of 168v1 · Clustering · German Embeddings group similar examples on MTEB German v1 · Clustering in German MTEB 26.5 #70 of 167v1 · Reranking · German Embeddings reorder candidate documents by relevance on MTEB German v1 · Reranking in German MTEB 36.5 #58 of 148v1 · STS · German Embeddings estimate semantic similarity between pairs on MTEB German v1 · STS in German MTEB 62.7 #51 of 137v1 · Retrieval · German Embeddings rank relevant documents for queries on MTEB German v1 · Retrieval in German MTEB 37.5 #63 of 127v1 · Mean over tasks · German Embeddings assign examples to categories, classify relationships between pairs, estimate semantic similarity between pairs, group similar examples, rank relevant documents for queries, reorder candidate documents by relevance on MTEB German v1 · mean over tasks in German; tasks receive equal weight MTEB 45.5 #42 of 114v1 · Mean over task types · German Embeddings assign examples to categories, classify relationships between pairs, estimate semantic similarity between pairs, group similar examples, rank relevant documents for queries, reorder candidate documents by relevance on MTEB German v1 · mean over task types in German; task types receive equal weight MTEB 45.2 #40 of 114
MTEB Spanishv1 · Pair Classification · Spanish Embeddings classify relationships between pairs on MTEB Spanish v1 · Pair Classification in Spanish MTEB 68 #46 of 171+7 versions & slices v1 · Reranking · Spanish Embeddings reorder candidate documents by relevance on MTEB Spanish v1 · Reranking in Spanish MTEB 46 #57 of 148v1 · Clustering · Spanish Embeddings group similar examples on MTEB Spanish v1 · Clustering in Spanish MTEB 36.3 #98 of 127v1 · Classification · Spanish Embeddings assign examples to categories on MTEB Spanish v1 · Classification in Spanish MTEB 39.6 #101 of 101v1 · STS · multilingual (2 languages) Embeddings estimate semantic similarity between pairs on MTEB Spanish v1 · STS in English, Spanish MTEB 74.3 #36 of 88v1 · Retrieval · multilingual (2 languages) Embeddings rank relevant documents for queries on MTEB Spanish v1 · Retrieval in English, Spanish MTEB 22.1 #28 of 28v1 · Mean over tasks · multilingual (2 languages) Embeddings estimate semantic similarity between pairs, group similar examples, rank relevant documents for queries, classify relationships between pairs, reorder candidate documents by relevance, assign examples to categories on MTEB Spanish v1 · mean over tasks in English, Spanish; tasks receive equal weight MTEB 46.3 #26 of 27v1 · Mean over task types · multilingual (2 languages) Embeddings estimate semantic similarity between pairs, group similar examples, rank relevant documents for queries, classify relationships between pairs, reorder candidate documents by relevance, assign examples to categories on MTEB Spanish v1 · mean over task types in English, Spanish; task types receive equal weight MTEB 47.7 #27 of 27
JMTEBv2 · STS · Japanese Embeddings estimate semantic similarity between pairs on jMTEB v2 · STS in Japanese MTEB 73.5 #73 of 168+1 versions & slices v2 · Clustering · Japanese Embeddings group similar examples on jMTEB v2 · Clustering in Japanese MTEB 41.5 #66 of 161
LongEmbedMean over tasks · English Embeddings rank relevant documents for queries on LongEmbed · mean over tasks in English; tasks receive equal weight MTEB 20.9 #146 of 168+2 versions & slices Mean over task types · English Embeddings rank relevant documents for queries on LongEmbed · mean over task types in English; task types receive equal weight MTEB 20.9 #146 of 168Retrieval · English Embeddings rank relevant documents for queries on LongEmbed · Retrieval in English MTEB 20.9 #146 of 168
MTEB Lawv1 · Mean over tasks · multilingual (3 languages) Embeddings rank relevant documents for queries on MTEB Law v1 · mean over tasks in Chinese, English, German; tasks receive equal weight MTEB 34.4 #130 of 167+2 versions & slices v1 · Mean over task types · multilingual (3 languages) Embeddings rank relevant documents for queries on MTEB Law v1 · mean over task types in Chinese, English, German; task types receive equal weight MTEB 34.4 #130 of 167v1 · Retrieval · multilingual (3 languages) Embeddings rank relevant documents for queries on MTEB Law v1 · Retrieval in Chinese, English, German MTEB 34.4 #130 of 167
MTEB Polishv1 · Pair Classification · Polish Embeddings classify relationships between pairs on MTEB Polish v1 · Pair Classification in Polish MTEB 83.4 #36 of 159+5 versions & slices v1 · Classification · Polish Embeddings assign examples to categories on MTEB Polish v1 · Classification in Polish MTEB 52.2 #59 of 144v1 · STS · Polish Embeddings estimate semantic similarity between pairs on MTEB Polish v1 · STS in Polish MTEB 63.8 #48 of 132v1 · Clustering · Polish Embeddings group similar examples on MTEB Polish v1 · Clustering in Polish MTEB 37.3 #33 of 121v1 · Mean over tasks · Polish Embeddings assign examples to categories, group similar examples, estimate semantic similarity between pairs, classify relationships between pairs on MTEB Polish v1 · mean over tasks in Polish; tasks receive equal weight MTEB 59 #35 of 103v1 · Mean over task types · Polish Embeddings assign examples to categories, group similar examples, estimate semantic similarity between pairs, classify relationships between pairs on MTEB Polish v1 · mean over task types in Polish; task types receive equal weight MTEB 59.2 #33 of 103
MTEB Koreanv2 · Classification · Korean Embeddings assign examples to categories on MTEB Korean v2 · Classification in Korean MTEB 39.7 #65 of 156+7 versions & slices v2 · Reranking · Korean Embeddings reorder candidate documents by relevance on MTEB Korean v2 · Reranking in Korean MTEB 35.6 #57 of 155v2 · STS · Korean Embeddings estimate semantic similarity between pairs on MTEB Korean v2 · STS in Korean MTEB 72.4 #44 of 108v2 · Clustering · Korean Embeddings group similar examples on MTEB Korean v2 · Clustering in Korean MTEB 33.8 #35 of 40v2 · Pair Classification · Korean Embeddings classify relationships between pairs on MTEB Korean v2 · Pair Classification in Korean MTEB 64.9 #13 of 40v2 · Retrieval · multilingual (2 languages) Embeddings rank relevant documents for queries on MTEB Korean v2 · Retrieval in English, Korean MTEB 37.9 #35 of 39v2 · Mean over tasks · multilingual (2 languages) Embeddings rank relevant documents for queries, group similar examples, estimate semantic similarity between pairs, assign examples to categories, classify relationships between pairs, reorder candidate documents by relevance on MTEB Korean v2 · mean over tasks in English, Korean; tasks receive equal weight MTEB 46.5 #27 of 31v2 · Mean over task types · multilingual (2 languages) Embeddings rank relevant documents for queries, group similar examples, estimate semantic similarity between pairs, assign examples to categories, classify relationships between pairs, reorder candidate documents by relevance on MTEB Korean v2 · mean over task types in English, Korean; task types receive equal weight MTEB 47.4 #27 of 31
RTEB Finnish betaMean over tasks · English Embeddings rank relevant documents for queries on RTEB Finnish Beta · mean over tasks in English; tasks receive equal weight MTEB 29.8 #81 of 93
RTEB Health betaMean over tasks · multilingual (4 languages) Embeddings rank relevant documents for queries on RTEB Health Beta · mean over tasks in English, French, German, Spanish; tasks receive equal weight MTEB 28.9 #75 of 93
BEIR-NLMean over tasks · Dutch Embeddings rank relevant documents for queries on BEIR NL · mean over tasks in Dutch; tasks receive equal weight MTEB 25.8 #12 of 15+2 versions & slices Mean over task types · Dutch Embeddings rank relevant documents for queries on BEIR NL · mean over task types in Dutch; task types receive equal weight MTEB 25.8 #12 of 15Retrieval · Dutch Embeddings rank relevant documents for queries on BEIR NL · Retrieval in Dutch MTEB 25.8 #12 of 15
No benchmark matches
OpenQwen 3 Embedding 8Bunstated+55%—$0.01Languages: not verified+1iBetterMultilingual E5 Large InstructunstatedOpen+36%—$0.01Memory (4-bit): 0.1 GB → 0.3 GB
Harrier OSS v1 0.6BunstatedOpen+44%——Memory (4-bit): 0.1 GB → 0.4 GB