{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"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":{"order":"date (newest first), then slug","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"shown":2,"of":2,"counts":{"papers_with_a_benchmark_row":2,"with_a_code_link":2,"where_syntology_ran_a_sample":1,"not_listed_spam_title":0,"listed":2,"listed_where_code_ran":1,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":1,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"paper":"/paper/angle-optimized-text-embeddings","slug":"angle-optimized-text-embeddings","title":"AnglE-optimized Text Embeddings","date":"2023-09-22","arxiv_id":"2309.12871","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/mteb-massive-text-embedding-benchmark","slug":"mteb-massive-text-embedding-benchmark","title":"MTEB: Massive Text Embedding Benchmark","date":"2022-10-13","arxiv_id":"2210.07316","rows_on_this_dataset":148,"code_links":5,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":13,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":3,"samples_unverified":3,"pointer_only_for_licence":0,"official":{"repos":["embeddings-benchmark/mteb"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/mteb-massive-text-embedding-benchmark#ran","syntology_url":"https://syntology.ai/paper/2210.07316","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.07316"}}}}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/angle-optimized-text-embeddings","slug":"angle-optimized-text-embeddings","title":"AnglE-optimized Text Embeddings","date":"2023-09-22","arxiv_id":"2309.12871","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/mteb-massive-text-embedding-benchmark","slug":"mteb-massive-text-embedding-benchmark","title":"MTEB: Massive Text Embedding Benchmark","date":"2022-10-13","arxiv_id":"2210.07316","rows_on_this_dataset":148,"code_links":5,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":13,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":3,"samples_unverified":3,"pointer_only_for_licence":0,"official":{"repos":["embeddings-benchmark/mteb"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/mteb-massive-text-embedding-benchmark#ran","syntology_url":"https://syntology.ai/paper/2210.07316","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.07316"}}}}],"papers_where_code_ran":1,"papers_where_code_ran_first_page":"/dataset/mteb/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/dataset/mteb/papers/ran/1","json":"/dataset/mteb/papers/ran/1.json","rows":1}],"row_route":"each paper's syntology object carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers","syntology_totals":{"read_at":"2026-10-05T00:36:11+00:00","papers_with_samples":1,"samples_harvested":13,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":3,"samples_unverified":3,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":1,"papers_with_a_run_with_no_instrument_failure":1,"papers_where_every_run_was_an_instrument_failure":0,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"key_notes":{"samples_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","samples_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":4,"papers_placed":0,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[{"leaderboard":"/sota/text-classification-on-mteb","since_archive":"/sota/text-classification-on-mteb#since-judged","papers_judged":4,"placed":0},{"leaderboard":"/sota/text-clustering-on-mteb","since_archive":"/sota/text-clustering-on-mteb#since-judged","papers_judged":2,"placed":0},{"leaderboard":"/sota/text-retrieval-on-mteb","since_archive":"/sota/text-retrieval-on-mteb#since-judged","papers_judged":2,"placed":0}]},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"8b185d3477a6a23e9d48a37fe99f466af7b8c07c1f3f56e1e94b09759dfea817","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}