{"url":"/task/mteb-benchmark","name":"MTEB Benchmark","slug":"mteb-benchmark","description_markdown":null,"categories":[],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":13,"papers_with_code":7,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":1,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/humaneval","name":"HumanEval","full_name":"","num_papers_in_archive":1201}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":7,"of":7,"tagged_in_all":13,"items":[{"url":"/paper/jina-embeddings-2-8192-token-general-purpose","title":"Jina Embeddings 2: 8192-Token General-Purpose Text Embeddings for Long Documents","date":"2023-10-30","arxiv_id":"2310.19923","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/c-pack-packaged-resources-to-advance-general","title":"C-Pack: Packed Resources For General Chinese Embeddings","date":"2023-09-14","arxiv_id":"2309.07597","repositories_listed":2,"syntology":null},{"url":"/paper/neobert-a-next-generation-bert","title":"NeoBERT: A Next-Generation BERT","date":"2025-02-26","arxiv_id":"2502.19587","repositories_listed":1,"syntology":null},{"url":"/paper/kalm-embedding-superior-training-data-brings","title":"KaLM-Embedding: Superior Training Data Brings A Stronger Embedding Model","date":"2025-01-02","arxiv_id":"2501.01028","repositories_listed":1,"syntology":null},{"url":"/paper/geneol-harnessing-the-generative-power-of","title":"GenEOL: Harnessing the Generative Power of LLMs for Training-Free Sentence Embeddings","date":"2024-10-18","arxiv_id":"2410.14635","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_unverified":2,"n_pointer_only":3}},{"url":"/paper/a-bi-metric-framework-for-fast-similarity","title":"A Bi-metric Framework for Fast Similarity Search","date":"2024-06-05","arxiv_id":"2406.02891","repositories_listed":1,"syntology":null},{"url":"/paper/text-embeddings-by-weakly-supervised","title":"Text Embeddings by Weakly-Supervised Contrastive Pre-training","date":"2022-12-07","arxiv_id":"2212.03533","repositories_listed":1,"syntology":null}],"syntology_records":2,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-25T09:33:49+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}