{"url":"/dataset/mteb","name":"MTEB","full_name":"Massive Text Embedding Benchmark","description_markdown":"**MTEB** is a benchmark that spans 8 embedding tasks covering a total of 56 datasets and 112 languages. The 8 task types are Bitext mining, Classification, Clustering, Pair Classification, Reranking, Retrieval, Semantic Textual Similarity and Summarisation. The 56 datasets contain varying text lengths and they are grouped into three categories: Sentence to sentence, Paragraph to paragraph, and Sentence to paragraph.\r\n\r\nCheck the latest leaderboards at [HuggingFace](https://huggingface.co/spaces/mteb/leaderboard).","description_withheld":null,"homepage":"https://github.com/embeddings-benchmark/mteb","introduced_date":"2022-10-13","introduced_date_note":null,"introduced_by":{"paper":"/paper/mteb-massive-text-embedding-benchmark","title":"MTEB: Massive Text Embedding Benchmark","first_author":"Niklas Muennighoff","url":null},"license":{"name":"Apache-2.0 license","url":"https://github.com/embeddings-benchmark/mteb/blob/main/LICENSE"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Text Classification","url":"/task/text-classification","datasets_with_task":"/datasets/task/text-classification"},{"name":"Text Summarization","url":"/task/text-summarization","datasets_with_task":"/datasets/task/text-summarization"},{"name":"Information Retrieval","url":"/task/information-retrieval","datasets_with_task":"/datasets/task/information-retrieval"},{"name":"Semantic Textual Similarity","url":"/task/semantic-textual-similarity","datasets_with_task":"/datasets/task/semantic-textual-similarity"},{"name":"Text Clustering","url":"/task/text-clustering","datasets_with_task":"/datasets/task/text-clustering"},{"name":"Text Retrieval","url":"/task/text-retrieval","datasets_with_task":"/datasets/task/text-retrieval"},{"name":"Text Reranking","url":"/task/text-reranking","datasets_with_task":"/datasets/task/text-reranking"},{"name":"Text Pair Classification","url":"/task/text-pair-classification","datasets_with_task":"/datasets/task/text-pair-classification"},{"name":"STS","url":"/task/sts","datasets_with_task":"/datasets/task/sts"}],"languages":[],"variants":["MTEB"],"data_loaders":[],"num_papers_in_archive":155,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/text-classification-on-mteb","task":"Text Classification","dataset_variant":"MTEB","rows":31,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"ST5-XXL","paper":"/paper/mteb-massive-text-embedding-benchmark","metrics":{"Accuracy":"73.42"},"code_links":[{"title":"embeddings-benchmark/mteb","url":"https://github.com/embeddings-benchmark/mteb"},{"title":"lyon-nlp/mteb-french","url":"https://github.com/lyon-nlp/mteb-french"},{"title":"climsocana/tecb-de","url":"https://github.com/climsocana/tecb-de"},{"title":"wadoodabdul/clinical_ner_benchmark","url":"https://github.com/wadoodabdul/clinical_ner_benchmark"},{"title":"basf/chemteb","url":"https://github.com/basf/chemteb"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/text-clustering-on-mteb","task":"Text Clustering","dataset_variant":"MTEB","rows":31,"metrics":["V-Measure"],"first_row_in_archive_order":{"model":"ST5-XXL","paper":"/paper/mteb-massive-text-embedding-benchmark","metrics":{"V-Measure":"43.71"},"code_links":[{"title":"embeddings-benchmark/mteb","url":"https://github.com/embeddings-benchmark/mteb"},{"title":"lyon-nlp/mteb-french","url":"https://github.com/lyon-nlp/mteb-french"},{"title":"climsocana/tecb-de","url":"https://github.com/climsocana/tecb-de"},{"title":"wadoodabdul/clinical_ner_benchmark","url":"https://github.com/wadoodabdul/clinical_ner_benchmark"},{"title":"basf/chemteb","url":"https://github.com/basf/chemteb"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/semantic-textual-similarity-on-mteb","task":"Semantic Textual Similarity","dataset_variant":"MTEB","rows":30,"metrics":["Spearman Correlation"],"first_row_in_archive_order":{"model":"AnglE-UAE","paper":"/paper/angle-optimized-text-embeddings","metrics":{"Spearman Correlation":"84.54"},"code_links":[{"title":"SeanLee97/AnglE","url":"https://github.com/SeanLee97/AnglE"},{"title":"4ai/bellm","url":"https://github.com/4ai/bellm"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/text-retrieval-on-mteb","task":"Text Retrieval","dataset_variant":"MTEB","rows":30,"metrics":["nDCG@10"],"first_row_in_archive_order":{"model":"SGPT-5.8B-msmarco","paper":"/paper/mteb-massive-text-embedding-benchmark","metrics":{"nDCG@10":"50.25"},"code_links":[{"title":"embeddings-benchmark/mteb","url":"https://github.com/embeddings-benchmark/mteb"},{"title":"lyon-nlp/mteb-french","url":"https://github.com/lyon-nlp/mteb-french"},{"title":"climsocana/tecb-de","url":"https://github.com/climsocana/tecb-de"},{"title":"wadoodabdul/clinical_ner_benchmark","url":"https://github.com/wadoodabdul/clinical_ner_benchmark"},{"title":"basf/chemteb","url":"https://github.com/basf/chemteb"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/text-summarization-on-mteb","task":"Text Summarization","dataset_variant":"MTEB","rows":26,"metrics":["Spearman Correlation"],"first_row_in_archive_order":{"model":"MPNet-multilingual","paper":"/paper/mteb-massive-text-embedding-benchmark","metrics":{"Spearman Correlation":"31.57"},"code_links":[{"title":"embeddings-benchmark/mteb","url":"https://github.com/embeddings-benchmark/mteb"},{"title":"lyon-nlp/mteb-french","url":"https://github.com/lyon-nlp/mteb-french"},{"title":"climsocana/tecb-de","url":"https://github.com/climsocana/tecb-de"},{"title":"wadoodabdul/clinical_ner_benchmark","url":"https://github.com/wadoodabdul/clinical_ner_benchmark"},{"title":"basf/chemteb","url":"https://github.com/basf/chemteb"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/information-retrieval-on-mteb","task":"Information Retrieval","dataset_variant":"MTEB","rows":1,"metrics":["nDCG@10"],"first_row_in_archive_order":{"model":"SGPT-5.8B-msmarco","paper":"/paper/mteb-massive-text-embedding-benchmark","metrics":{"nDCG@10":"50.25"},"code_links":[{"title":"embeddings-benchmark/mteb","url":"https://github.com/embeddings-benchmark/mteb"},{"title":"lyon-nlp/mteb-french","url":"https://github.com/lyon-nlp/mteb-french"},{"title":"climsocana/tecb-de","url":"https://github.com/climsocana/tecb-de"},{"title":"wadoodabdul/clinical_ner_benchmark","url":"https://github.com/wadoodabdul/clinical_ner_benchmark"},{"title":"basf/chemteb","url":"https://github.com/basf/chemteb"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/angle-optimized-text-embeddings","title":"AnglE-optimized Text Embeddings","date":"2023-09-22","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/mteb-massive-text-embedding-benchmark","title":"MTEB: Massive Text Embedding Benchmark","date":"2022-10-13","rows_on_this_dataset":148,"code_links":5,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":13,"samples_ran":3,"samples_unverified":10,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":1,"samples_harvested":13,"samples_ran":3,"samples_unverified":10,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}