Benchmark By Score Rank
Reranking 17
MAEB v1 audio-onlyAudio Reranking · No linguistic content Embeddings reorder candidate audio clips by relevance on Maeb v1 Audio Only · Audio Reranking in No linguistic content MTEB 74.8 #13 of 27+6 versions & slices Audio Clustering · multilingual (6 languages) Embeddings group similar audio clips on Maeb v1 Audio Only · Audio Clustering in English, French, German, No linguistic content, Polish, Spanish MTEB 6.2 #9 of 26Audio Pair Classification · English Embeddings classify relationships between audio clips on Maeb v1 Audio Only · Audio Pair Classification in English MTEB 66.7 #3 of 26Any-to-any Retrieval · multilingual (4 languages) Embeddings retrieve matching examples across modalities on Maeb v1 Audio Only · Any-to-any Retrieval in English, French, German, Spanish MTEB 66.9 #19 of 25Mean over tasks · multilingual (102 languages) Embeddings classify audio clips, retrieve matching examples across modalities, group similar audio clips, classify relationships between audio clips, reorder candidate audio clips by relevance on Maeb v1 Audio Only · mean over tasks in 102 languages including Afrikaans, Amharic, Armenian, Assamese, Asturian, Belarusian, Bengali, Bosnian; tasks receive equal weight MTEB 53.6 #1 of 23Mean over task types · multilingual (102 languages) Embeddings classify audio clips, retrieve matching examples across modalities, group similar audio clips, classify relationships between audio clips, reorder candidate audio clips by relevance on Maeb v1 Audio Only · mean over task types in 102 languages including Afrikaans, Amharic, Armenian, Assamese, Asturian, Belarusian, Bengali, Bosnian; task types receive equal weight MTEB 54.9 #10 of 23Audio Classification · multilingual (102 languages) Embeddings classify audio clips on Maeb v1 Audio Only · Audio Classification in 102 languages including Afrikaans, Amharic, Armenian, Assamese, Asturian, Belarusian, Bengali, Bosnian MTEB 59.8 #1 of 23
MAEBv1 · Audio Reranking · No linguistic content Embeddings reorder candidate audio clips by relevance on Maeb v1 · Audio Reranking in No linguistic content MTEB 74.8 #13 of 27+8 versions & slices v1 · Audio Zero-shot Classification · English Embeddings classify audio using unseen labels on Maeb v1 · Audio Zero-shot Classification in English MTEB 65.8 #2 of 27v1 · Audio Clustering · multilingual (6 languages) Embeddings group similar audio clips on Maeb v1 · Audio Clustering in English, French, German, No linguistic content, Polish, Spanish MTEB 6.2 #9 of 26v1 · Audio Multilabel Classification · English Embeddings assign multiple labels to audio clips on Maeb v1 · Audio Multilabel Classification in English MTEB 60.9 #15 of 26v1 · Audio Pair Classification · English Embeddings classify relationships between audio clips on Maeb v1 · Audio Pair Classification in English MTEB 66.7 #3 of 26v1 · Any-to-any Retrieval · multilingual (150 languages) Embeddings retrieve matching examples across modalities on Maeb v1 · Any-to-any Retrieval in 150 languages including Abkhazian, Afrikaans, Albanian, Amharic, Arabic, Armenian, Assamese, Asturian MTEB 47.5 #8 of 24v1 · Mean over tasks · multilingual (159 languages) Embeddings classify audio clips, classify audio using unseen labels, retrieve matching examples across modalities, classify relationships between audio clips, reorder candidate audio clips by relevance, assign multiple labels to audio clips, group similar audio clips on Maeb v1 · mean over tasks in 159 languages including Abkhazian, Afrikaans, Albanian, Amharic, Arabic, Armenian, Assamese, Asturian; tasks receive equal weight MTEB 52.4 #3 of 23v1 · Mean over task types · multilingual (159 languages) Embeddings classify audio clips, classify audio using unseen labels, retrieve matching examples across modalities, classify relationships between audio clips, reorder candidate audio clips by relevance, assign multiple labels to audio clips, group similar audio clips on Maeb v1 · mean over task types in 159 languages including Abkhazian, Afrikaans, Albanian, Amharic, Arabic, Armenian, Assamese, Asturian; task types receive equal weight MTEB 54.5 #6 of 23v1 · Audio Classification · multilingual (102 languages) Embeddings classify audio clips on Maeb v1 · Audio Classification in 102 languages including Afrikaans, Amharic, Armenian, Assamese, Asturian, Belarusian, Bengali, Bosnian MTEB 59.8 #1 of 23
MTEB Dutchv1 · Reranking · Dutch Embeddings reorder candidate documents by relevance on MTEB Dutch v1 · Reranking in Dutch MTEB 86 #4 of 4
Other 68 Leads on 2
MIEB liteDocument Understanding · English Embeddings match queries to document content on MIEB Lite · Document Understanding in English MTEB 65.1 #52 of 89+11 versions & slices Visual semantic similarity (multilingual) · multilingual (13 languages) Embeddings estimate visual semantic similarity on MIEB Lite · Visual STS (multilingual) in Arabic, Dutch, English, French, German, Italian, Korean, Mandarin Chinese, Polish, Portuguese, Russian, Spanish, Turkish MTEB 45.7 #12 of 56Visual semantic similarity (English) · English Embeddings estimate visual semantic similarity on MIEB Lite · Visual STS (English) in English MTEB 67.9 #27 of 54Image Classification · English Embeddings classify images on MIEB Lite · Image Classification in English MTEB 73.8 #15 of 53Image Clustering · English Embeddings group similar images on MIEB Lite · Image Clustering in English MTEB 66.2 #37 of 53Any-to-any Multilingual Retrieval · multilingual (40 languages) Embeddings retrieve matching examples across languages and modalities on MIEB Lite · Any-to-any Multilingual Retrieval in 40 languages including Arabic, Bengali, Bulgarian, Chinese, Croatian, Cusco Quechua, Czech, Danish MTEB 57 #7 of 48Vision Centric QA · English Embeddings match visual content to questions on MIEB Lite · Vision Centric QA in English MTEB 55.4 #13 of 48Mean over tasks · multilingual (41 languages) Embeddings match visual content to questions, retrieve matching examples across modalities, match queries to document content, assign unseen category labels to examples, distinguish changes in how objects and attributes are combined, classify images, retrieve matching examples across languages and modalities, group similar images, estimate visual semantic similarity, estimate visual semantic similarity on MIEB Lite · mean over tasks in 41 languages including Arabic, Bengali, Bulgarian, Chinese, Croatian, Cusco Quechua, Czech, Danish; tasks receive equal weight MTEB 56 #10 of 47Mean over task types · multilingual (41 languages) Embeddings match visual content to questions, retrieve matching examples across modalities, match queries to document content, assign unseen category labels to examples, distinguish changes in how objects and attributes are combined, classify images, retrieve matching examples across languages and modalities, group similar images, estimate visual semantic similarity, estimate visual semantic similarity on MIEB Lite · mean over task types in 41 languages including Arabic, Bengali, Bulgarian, Chinese, Croatian, Cusco Quechua, Czech, Danish; task types receive equal weight MTEB 56 #10 of 47Any-to-any Retrieval · English Embeddings retrieve matching examples across modalities on MIEB Lite · Any-to-any Retrieval in English MTEB 31.3 #15 of 47Compositionality · English Embeddings distinguish changes in how objects and attributes are combined on MIEB Lite · Compositionality in English MTEB 46 #3 of 47Zero-shot Classification · English Embeddings assign unseen category labels to examples on MIEB Lite · Zero-shot Classification in English MTEB 51.3 #31 of 47
MIEB multilingualVisual semantic similarity (multilingual) · multilingual (13 languages) Embeddings estimate visual semantic similarity on MIEB Multilingual · Visual STS (multilingual) in Arabic, Dutch, English, French, German, Italian, Korean, Mandarin Chinese, Polish, Portuguese, Russian, Spanish, Turkish MTEB 45.7 #12 of 56
MVEB text videov1 · Video Clustering · English Embeddings group similar videos on MVEB Text Video v1 · Video Clustering in English MTEB 21.6 #3 of 27+4 versions & slices v1 · Video Pair Classification · English Embeddings classify relationships between video pairs on MVEB Text Video v1 · Video Pair Classification in English MTEB 85.7 #7 of 27v1 · Video Centric QA · English Embeddings match video content to questions on MVEB Text Video v1 · Video Centric QA in English MTEB 26.9 #6 of 25v1 · Video Classification · multilingual (16 languages) Embeddings classify videos on MVEB Text Video v1 · Video Classification in Bosnian, Breton, Chinese, English, Finnish, French, German, Hindi, Italian, Japanese, Korean, Persian, Portuguese, Russian, Spanish, Telugu MTEB 48.5 #6 of 25v1 · Video Zero-shot Classification · English Embeddings classify videos using unseen labels on MVEB Text Video v1 · Video Zero-shot Classification in English MTEB 53.4 #12 of 25
MVEBv1 · Video Centric QA · English Embeddings match video content to questions on MVEB v1 · Video Centric QA in English MTEB 55.8 #7 of 26+7 versions & slices v1 · Any-to-any Retrieval · English Embeddings retrieve matching examples across modalities on MVEB v1 · Any-to-any Retrieval in English MTEB 45.5 #11 of 17v1 · Video Zero-shot Classification · English Embeddings classify videos using unseen labels on MVEB v1 · Video Zero-shot Classification in English MTEB 53.9 #4 of 17v1 · Mean over tasks · multilingual (16 languages) Embeddings retrieve matching examples across modalities, classify videos using unseen labels, classify relationships between video pairs, classify videos, group similar videos, match video content to questions on MVEB v1 · mean over tasks in Bosnian, Breton, Chinese, English, Finnish, French, German, Hindi, Italian, Japanese, Korean, Persian, Portuguese, Russian, Spanish, Telugu; tasks receive equal weight MTEB 51.2 #10 of 16v1 · Mean over task types · multilingual (16 languages) Embeddings retrieve matching examples across modalities, classify videos using unseen labels, classify relationships between video pairs, classify videos, group similar videos, match video content to questions on MVEB v1 · mean over task types in Bosnian, Breton, Chinese, English, Finnish, French, German, Hindi, Italian, Japanese, Korean, Persian, Portuguese, Russian, Spanish, Telugu; task types receive equal weight MTEB 52.1 #3 of 16v1 · Video Classification · multilingual (16 languages) Embeddings classify videos on MVEB v1 · Video Classification in Bosnian, Breton, Chinese, English, Finnish, French, German, Hindi, Italian, Japanese, Korean, Persian, Portuguese, Russian, Spanish, Telugu MTEB 61.2 #1 of 16v1 · Video Clustering · English Embeddings group similar videos on MVEB v1 · Video Clustering in English MTEB 17.1 #13 of 16v1 · Video Pair Classification · English Embeddings classify relationships between video pairs on MVEB v1 · Video Pair Classification in English MTEB 78.7 #4 of 16
MVEB videov1 · Mean over tasks · multilingual (16 languages) Embeddings classify videos, classify relationships between video pairs on MVEB Video v1 · mean over tasks in Bosnian, Breton, Chinese, English, Finnish, French, German, Hindi, Italian, Japanese, Korean, Persian, Portuguese, Russian, Spanish, Telugu; tasks receive equal weight MTEB 58 #6 of 25+3 versions & slices v1 · Mean over task types · multilingual (16 languages) Embeddings classify videos, classify relationships between video pairs on MVEB Video v1 · mean over task types in Bosnian, Breton, Chinese, English, Finnish, French, German, Hindi, Italian, Japanese, Korean, Persian, Portuguese, Russian, Spanish, Telugu; task types receive equal weight MTEB 62 #6 of 25v1 · Video Classification · multilingual (16 languages) Embeddings classify videos on MVEB Video v1 · Video Classification in Bosnian, Breton, Chinese, English, Finnish, French, German, Hindi, Italian, Japanese, Korean, Persian, Portuguese, Russian, Spanish, Telugu MTEB 50.1 #7 of 25v1 · Video Pair Classification · English Embeddings classify relationships between video pairs on MVEB Video v1 · Video Pair Classification in English MTEB 73.8 #5 of 25
MTEB Englishv2 · Pair Classification · English Embeddings classify relationships between pairs in English MTEB 86.2 #2 of 13+6 versions & slices v2 · Classification · English Embeddings assign examples to categories in English MTEB 82.2 #7 of 13v2 · Reranking · English Embeddings reorder candidate documents by relevance in English MTEB 47.8 #5 of 13v2 · STS · English Embeddings estimate semantic similarity between pairs in English MTEB 84.6 #5 of 12v2 · Retrieval · English Embeddings rank relevant documents for queries in English MTEB 55.1 #5 of 12v2 · Clustering · English Embeddings group similar examples in English MTEB 51.5 #5 of 11v2 · Summarization · English Embeddings match summaries to their source meaning in English MTEB 30.1 #7 of 11
MTEB Medicalv1 · Clustering · English Embeddings group similar examples on MTEB Medical v1 · Clustering in English MTEB 40.1 #5 of 11
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 74.9 #4 of 6
MTEB Europev1 · 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 90 #4 of 5+4 versions & slices v1 · 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 47.1 #3 of 4v1 · Instruction Reranking · English Embeddings rerank documents according to instructions on MTEB Europe v1 · Instruction Reranking in English MTEB 1 #2 of 4v1 · 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 19 #3 of 4v1 · 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 59.8 #3 of 4
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 48.8 #1 of 5+3 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 51.2 #1 of 4v1 · Pair Classification · Hindi Embeddings classify relationships between pairs on MTEB Indic v1 · Pair Classification in Hindi MTEB 74 #4 of 4v1 · Reranking · multilingual (2 languages) Embeddings reorder candidate documents by relevance on MTEB Indic v1 · Reranking in Bengali, Hindi MTEB 83.4 #4 of 4
MTEB multilingualv2 · 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 72.3 #2 of 5+10 versions & slices v2 · Mean over tasks · multilingual (1037 languages) Embeddings assign examples to categories, group similar examples, estimate semantic similarity between pairs, classify relationships between pairs, rank relevant documents for queries, find translated sentence pairs, rerank documents according to instructions, assign multiple labels to each example, reorder candidate documents by relevance 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 63.5 #3 of 4v2 · Mean over task types · multilingual (1037 languages) Embeddings assign examples to categories, group similar examples, estimate semantic similarity between pairs, classify relationships between pairs, rank relevant documents for queries, find translated sentence pairs, rerank documents according to instructions, assign multiple labels to each example, reorder candidate documents by relevance 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 55.5 #3 of 4v2 · 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 65.9 #3 of 4v2 · 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 51.5 #3 of 4v2 · Instruction Reranking · English Embeddings rerank documents according to instructions on MTEB Multilingual v2 · Instruction Reranking in English MTEB 1 #2 of 4v2 · 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 26.5 #3 of 4v2 · 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 80.7 #3 of 4v2 · 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 64.7 #2 of 4v2 · 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 61 #3 of 4v2 · 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 75.7 #3 of 4
FollowIRMean over tasks · English Embeddings rerank documents according to instructions on FollowIR · mean over tasks in English; tasks receive equal weight MTEB 1 #2 of 4+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 #2 of 4Instruction Reranking · English Embeddings rerank documents according to instructions on FollowIR · Instruction Reranking in English MTEB 1 #2 of 4
MTEB Frenchv1 · Pair Classification · French Embeddings classify relationships between pairs on MTEB French v1 · Pair Classification in French MTEB 60.7 #3 of 4
MTEB Portuguesev1 · Multilabel Classification · Portuguese Embeddings assign multiple labels to each example on MTEB Portuguese v1 · Multilabel Classification in Portuguese MTEB 28.6 #2 of 4
MTEB Russianv1.1 · Pair Classification · Russian Embeddings classify relationships between pairs on MTEB Russian v1.1 · Pair Classification in Russian MTEB 58.3 #3 of 4
MTEB Spanishv1 · Pair Classification · Spanish Embeddings classify relationships between pairs on MTEB Spanish v1 · Pair Classification in Spanish MTEB 68.7 #3 of 4
MTEB Thaiv1 · Clustering · Thai Embeddings group similar examples on MTEB Thai v1 · Clustering in Thai MTEB 61.3 #1 of 4+1 versions & slices v1 · Pair Classification · Thai Embeddings classify relationships between pairs on MTEB Thai v1 · Pair Classification in Thai MTEB 76.2 #3 of 4
No benchmark matches
BetterEmbeddingGemma 2unstatedOpen+68%—$0.02Max input: 33K tokens → 8K tokens+1LOpenLCO Embedding Omni 7Bunstated+80%——Languages: not verified+1
BetterJina Embeddings v5 Omni NanounstatedOpen+18%—$0.02Max input: 33K tokens → 8K tokens+1