{"url":"/sota/text-classification-on-mteb","task":{"name":"Text Classification","url":"/task/text-classification","note":null},"dataset":{"name":"MTEB","url":"/dataset/mteb"},"category":"Natural Language Processing","categories":["Natural Language Processing"],"category_note":null,"description":"**Text Classification** is the task of assigning a sentence or document an appropriate category. The categories depend on the chosen dataset and can range from topics. \r\n\r\nText Classification problems include emotion classification, news classification, citation intent classification, among others. Benchmark datasets for evaluating text classification capabilities include GLUE, AGNews,  among others. \r\n\r\nIn recent years, deep learning techniques like XLNet and RoBERTa have attained some of the biggest performance jumps for text classification problems. \r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [Text Classification Algorithms: A Survey](https://arxiv.org/pdf/1904.08067v4.pdf) )</span>","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["Accuracy"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Accuracy":"higher"}},"counts":{"rows":31,"rows_with_code":31,"rows_with_paper_page":31,"rows_dated":31,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"ST5-XXL","metrics":{"Accuracy":"73.42"},"uses_additional_data":false,"paper_date":"2022-10-13","paper":"/paper/mteb-massive-text-embedding-benchmark","paper_url":"https://arxiv.org/abs/2210.07316v3","paper_title":"MTEB: Massive Text Embedding Benchmark","code":"https://github.com/embeddings-benchmark/mteb","n_code_links":5,"syntology":{"n_ran":3,"n_unverified":10,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":2,"model":"ST5-XL","metrics":{"Accuracy":"72.84"},"uses_additional_data":false,"paper_date":"2022-10-13","paper":"/paper/mteb-massive-text-embedding-benchmark","paper_url":"https://arxiv.org/abs/2210.07316v3","paper_title":"MTEB: Massive Text Embedding Benchmark","code":"https://github.com/embeddings-benchmark/mteb","n_code_links":5,"syntology":{"n_ran":3,"n_unverified":10,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"ST5-Large","metrics":{"Accuracy":"72.31"},"uses_additional_data":false,"paper_date":"2022-10-13","paper":"/paper/mteb-massive-text-embedding-benchmark","paper_url":"https://arxiv.org/abs/2210.07316v3","paper_title":"MTEB: Massive Text Embedding Benchmark","code":"https://github.com/embeddings-benchmark/mteb","n_code_links":5,"syntology":{"n_ran":3,"n_unverified":10,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":4,"model":"Ada Similarity","metrics":{"Accuracy":"70.44"},"uses_additional_data":false,"paper_date":"2022-10-13","paper":"/paper/mteb-massive-text-embedding-benchmark","paper_url":"https://arxiv.org/abs/2210.07316v3","paper_title":"MTEB: Massive Text Embedding Benchmark","code":"https://github.com/embeddings-benchmark/mteb","n_code_links":5,"syntology":{"n_ran":3,"n_unverified":10,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":5,"model":"SGPT-5.8B-nli","metrics":{"Accuracy":"70.14"},"uses_additional_data":false,"paper_date":"2022-10-13","paper":"/paper/mteb-massive-text-embedding-benchmark","paper_url":"https://arxiv.org/abs/2210.07316v3","paper_title":"MTEB: Massive Text Embedding Benchmark","code":"https://github.com/embeddings-benchmark/mteb","n_code_links":5,"syntology":{"n_ran":3,"n_unverified":10,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":6,"model":"ST5-Base","metrics":{"Accuracy":"69.81"},"uses_additional_data":false,"paper_date":"2022-10-13","paper":"/paper/mteb-massive-text-embedding-benchmark","paper_url":"https://arxiv.org/abs/2210.07316v3","paper_title":"MTEB: Massive Text Embedding Benchmark","code":"https://github.com/embeddings-benchmark/mteb","n_code_links":5,"syntology":{"n_ran":3,"n_unverified":10,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":7,"model":"SGPT-5.8B-msmarco","metrics":{"Accuracy":"68.13"},"uses_additional_data":false,"paper_date":"2022-10-13","paper":"/paper/mteb-massive-text-embedding-benchmark","paper_url":"https://arxiv.org/abs/2210.07316v3","paper_title":"MTEB: Massive Text Embedding Benchmark","code":"https://github.com/embeddings-benchmark/mteb","n_code_links":5,"syntology":{"n_ran":3,"n_unverified":10,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":8,"model":"MPNet-multilingual","metrics":{"Accuracy":"67.91"},"uses_additional_data":false,"paper_date":"2022-10-13","paper":"/paper/mteb-massive-text-embedding-benchmark","paper_url":"https://arxiv.org/abs/2210.07316v3","paper_title":"MTEB: Massive Text Embedding Benchmark","code":"https://github.com/embeddings-benchmark/mteb","n_code_links":5,"syntology":{"n_ran":3,"n_unverified":10,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":9,"model":"GTR-XXL","metrics":{"Accuracy":"67.41"},"uses_additional_data":false,"paper_date":"2022-10-13","paper":"/paper/mteb-massive-text-embedding-benchmark","paper_url":"https://arxiv.org/abs/2210.07316v3","paper_title":"MTEB: Massive Text Embedding Benchmark","code":"https://github.com/embeddings-benchmark/mteb","n_code_links":5,"syntology":{"n_ran":3,"n_unverified":10,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":10,"model":"SimCSE-BERT-sup","metrics":{"Accuracy":"67.32"},"uses_additional_data":false,"paper_date":"2022-10-13","paper":"/paper/mteb-massive-text-embedding-benchmark","paper_url":"https://arxiv.org/abs/2210.07316v3","paper_title":"MTEB: Massive Text Embedding Benchmark","code":"https://github.com/embeddings-benchmark/mteb","n_code_links":5,"syntology":{"n_ran":3,"n_unverified":10,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":11,"model":"GTR-Large","metrics":{"Accuracy":"67.14"},"uses_additional_data":false,"paper_date":"2022-10-13","paper":"/paper/mteb-massive-text-embedding-benchmark","paper_url":"https://arxiv.org/abs/2210.07316v3","paper_title":"MTEB: Massive Text Embedding Benchmark","code":"https://github.com/embeddings-benchmark/mteb","n_code_links":5,"syntology":{"n_ran":3,"n_unverified":10,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":12,"model":"SGPT-2.7B-msmarco","metrics":{"Accuracy":"67.13"},"uses_additional_data":false,"paper_date":"2022-10-13","paper":"/paper/mteb-massive-text-embedding-benchmark","paper_url":"https://arxiv.org/abs/2210.07316v3","paper_title":"MTEB: Massive Text Embedding Benchmark","code":"https://github.com/embeddings-benchmark/mteb","n_code_links":5,"syntology":{"n_ran":3,"n_unverified":10,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":13,"model":"GTR-XL","metrics":{"Accuracy":"67.11"},"uses_additional_data":false,"paper_date":"2022-10-13","paper":"/paper/mteb-massive-text-embedding-benchmark","paper_url":"https://arxiv.org/abs/2210.07316v3","paper_title":"MTEB: Massive Text Embedding Benchmark","code":"https://github.com/embeddings-benchmark/mteb","n_code_links":5,"syntology":{"n_ran":3,"n_unverified":10,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":14,"model":"Contriever","metrics":{"Accuracy":"66.68"},"uses_additional_data":false,"paper_date":"2022-10-13","paper":"/paper/mteb-massive-text-embedding-benchmark","paper_url":"https://arxiv.org/abs/2210.07316v3","paper_title":"MTEB: Massive Text Embedding Benchmark","code":"https://github.com/embeddings-benchmark/mteb","n_code_links":5,"syntology":{"n_ran":3,"n_unverified":10,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":15,"model":"SGPT-1.3B-msmarco","metrics":{"Accuracy":"66.52"},"uses_additional_data":false,"paper_date":"2022-10-13","paper":"/paper/mteb-massive-text-embedding-benchmark","paper_url":"https://arxiv.org/abs/2210.07316v3","paper_title":"MTEB: Massive Text Embedding Benchmark","code":"https://github.com/embeddings-benchmark/mteb","n_code_links":5,"syntology":{"n_ran":3,"n_unverified":10,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":16,"model":"SGPT-BLOOM-7.1B-msmarco","metrics":{"Accuracy":"66.19"},"uses_additional_data":false,"paper_date":"2022-10-13","paper":"/paper/mteb-massive-text-embedding-benchmark","paper_url":"https://arxiv.org/abs/2210.07316v3","paper_title":"MTEB: Massive Text Embedding Benchmark","code":"https://github.com/embeddings-benchmark/mteb","n_code_links":5,"syntology":{"n_ran":3,"n_unverified":10,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":17,"model":"GTR-Base","metrics":{"Accuracy":"65.25"},"uses_additional_data":false,"paper_date":"2022-10-13","paper":"/paper/mteb-massive-text-embedding-benchmark","paper_url":"https://arxiv.org/abs/2210.07316v3","paper_title":"MTEB: Massive Text Embedding Benchmark","code":"https://github.com/embeddings-benchmark/mteb","n_code_links":5,"syntology":{"n_ran":3,"n_unverified":10,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":18,"model":"MPNet","metrics":{"Accuracy":"65.07"},"uses_additional_data":false,"paper_date":"2022-10-13","paper":"/paper/mteb-massive-text-embedding-benchmark","paper_url":"https://arxiv.org/abs/2210.07316v3","paper_title":"MTEB: Massive Text Embedding Benchmark","code":"https://github.com/embeddings-benchmark/mteb","n_code_links":5,"syntology":{"n_ran":3,"n_unverified":10,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":19,"model":"coCondenser-msmarco","metrics":{"Accuracy":"64.71"},"uses_additional_data":false,"paper_date":"2022-10-13","paper":"/paper/mteb-massive-text-embedding-benchmark","paper_url":"https://arxiv.org/abs/2210.07316v3","paper_title":"MTEB: Massive Text Embedding Benchmark","code":"https://github.com/embeddings-benchmark/mteb","n_code_links":5,"syntology":{"n_ran":3,"n_unverified":10,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":20,"model":"MiniLM-L12-multilingual","metrics":{"Accuracy":"64.3"},"uses_additional_data":false,"paper_date":"2022-10-13","paper":"/paper/mteb-massive-text-embedding-benchmark","paper_url":"https://arxiv.org/abs/2210.07316v3","paper_title":"MTEB: Massive Text Embedding Benchmark","code":"https://github.com/embeddings-benchmark/mteb","n_code_links":5,"syntology":{"n_ran":3,"n_unverified":10,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":21,"model":"MiniLM-L12","metrics":{"Accuracy":"63.21"},"uses_additional_data":false,"paper_date":"2022-10-13","paper":"/paper/mteb-massive-text-embedding-benchmark","paper_url":"https://arxiv.org/abs/2210.07316v3","paper_title":"MTEB: Massive Text Embedding Benchmark","code":"https://github.com/embeddings-benchmark/mteb","n_code_links":5,"syntology":{"n_ran":3,"n_unverified":10,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":22,"model":"MiniLM-L6","metrics":{"Accuracy":"63.06"},"uses_additional_data":false,"paper_date":"2022-10-13","paper":"/paper/mteb-massive-text-embedding-benchmark","paper_url":"https://arxiv.org/abs/2210.07316v3","paper_title":"MTEB: Massive Text Embedding Benchmark","code":"https://github.com/embeddings-benchmark/mteb","n_code_links":5,"syntology":{"n_ran":3,"n_unverified":10,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":23,"model":"LaBSE","metrics":{"Accuracy":"62.71"},"uses_additional_data":false,"paper_date":"2022-10-13","paper":"/paper/mteb-massive-text-embedding-benchmark","paper_url":"https://arxiv.org/abs/2210.07316v3","paper_title":"MTEB: Massive Text Embedding Benchmark","code":"https://github.com/embeddings-benchmark/mteb","n_code_links":5,"syntology":{"n_ran":3,"n_unverified":10,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":24,"model":"SimCSE-BERT-unsup","metrics":{"Accuracy":"62.5"},"uses_additional_data":false,"paper_date":"2022-10-13","paper":"/paper/mteb-massive-text-embedding-benchmark","paper_url":"https://arxiv.org/abs/2210.07316v3","paper_title":"MTEB: Massive Text Embedding Benchmark","code":"https://github.com/embeddings-benchmark/mteb","n_code_links":5,"syntology":{"n_ran":3,"n_unverified":10,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":25,"model":"BERT","metrics":{"Accuracy":"61.66"},"uses_additional_data":false,"paper_date":"2022-10-13","paper":"/paper/mteb-massive-text-embedding-benchmark","paper_url":"https://arxiv.org/abs/2210.07316v3","paper_title":"MTEB: Massive Text Embedding Benchmark","code":"https://github.com/embeddings-benchmark/mteb","n_code_links":5,"syntology":{"n_ran":3,"n_unverified":10,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":26,"model":"SGPT-125M-nli","metrics":{"Accuracy":"61.46"},"uses_additional_data":false,"paper_date":"2022-10-13","paper":"/paper/mteb-massive-text-embedding-benchmark","paper_url":"https://arxiv.org/abs/2210.07316v3","paper_title":"MTEB: Massive Text Embedding Benchmark","code":"https://github.com/embeddings-benchmark/mteb","n_code_links":5,"syntology":{"n_ran":3,"n_unverified":10,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":27,"model":"SGPT-125M-msmarco","metrics":{"Accuracy":"60.72"},"uses_additional_data":false,"paper_date":"2022-10-13","paper":"/paper/mteb-massive-text-embedding-benchmark","paper_url":"https://arxiv.org/abs/2210.07316v3","paper_title":"MTEB: Massive Text Embedding Benchmark","code":"https://github.com/embeddings-benchmark/mteb","n_code_links":5,"syntology":{"n_ran":3,"n_unverified":10,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":28,"model":"Komninos","metrics":{"Accuracy":"57.65"},"uses_additional_data":false,"paper_date":"2022-10-13","paper":"/paper/mteb-massive-text-embedding-benchmark","paper_url":"https://arxiv.org/abs/2210.07316v3","paper_title":"MTEB: Massive Text Embedding Benchmark","code":"https://github.com/embeddings-benchmark/mteb","n_code_links":5,"syntology":{"n_ran":3,"n_unverified":10,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":29,"model":"Glove","metrics":{"Accuracy":"57.29"},"uses_additional_data":false,"paper_date":"2022-10-13","paper":"/paper/mteb-massive-text-embedding-benchmark","paper_url":"https://arxiv.org/abs/2210.07316v3","paper_title":"MTEB: Massive Text Embedding Benchmark","code":"https://github.com/embeddings-benchmark/mteb","n_code_links":5,"syntology":{"n_ran":3,"n_unverified":10,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":30,"model":"LASER2","metrics":{"Accuracy":"53.65"},"uses_additional_data":false,"paper_date":"2022-10-13","paper":"/paper/mteb-massive-text-embedding-benchmark","paper_url":"https://arxiv.org/abs/2210.07316v3","paper_title":"MTEB: Massive Text Embedding Benchmark","code":"https://github.com/embeddings-benchmark/mteb","n_code_links":5,"syntology":{"n_ran":3,"n_unverified":10,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":31,"model":"SPECTER","metrics":{"Accuracy":"52.37"},"uses_additional_data":false,"paper_date":"2022-10-13","paper":"/paper/mteb-massive-text-embedding-benchmark","paper_url":"https://arxiv.org/abs/2210.07316v3","paper_title":"MTEB: Massive Text Embedding Benchmark","code":"https://github.com/embeddings-benchmark/mteb","n_code_links":5,"syntology":{"n_ran":3,"n_unverified":10,"n_samples":13,"n_pointer_only_licence":0}}],"since_archive":{"present":false,"note":"No Syntology-extracted rows are published in this build."},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":31,"rows_with_any_sample_ran":31,"distinct_papers_with_graph_line":1,"distinct_papers_with_any_sample_ran":1,"samples_over_distinct_papers":{"n_ran":3,"n_unverified":10,"n_samples":13,"n_pointer_only_licence":0,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":93,"n_unverified":310,"n_samples":403,"n_pointer_only_licence":0,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}