{"url":"/sota/code-search-on-codesearchnet","task":{"name":"Code Search","url":"/task/code-search","note":null},"dataset":{"name":"CodeSearchNet","url":"/dataset/codesearchnet"},"category":"Computer Code","categories":["Computer Code"],"category_note":null,"description":"The goal of **Code Search** is to retrieve code fragments from a large code corpus that most closely match a developer’s intent, which is expressed in natural language.\r\n\r\n\r\n<span class=\"description-source\">Source: [When Deep Learning Met Code Search ](https://arxiv.org/abs/1905.03813)</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":["Overall","Go","Ruby","Python","Java","JS","PHP"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Overall":null,"Go":null,"Ruby":null,"Python":null,"Java":null,"JS":null,"PHP":null}},"counts":{"rows":6,"rows_with_code":6,"rows_with_paper_page":6,"rows_dated":6,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"cpt-code M","metrics":{"Go":"97.5","JS":"86.5","Java":"94.4","Overall":"93.5","PHP":"97.2","Python":"99.9","Ruby":"85.5"},"uses_additional_data":false,"paper_date":"2022-01-24","paper":"/paper/text-and-code-embeddings-by-contrastive-pre","paper_url":"https://arxiv.org/abs/2201.10005v1","paper_title":"Text and Code Embeddings by Contrastive Pre-Training","code":"https://github.com/openmatch/coco-dr","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"cpt-code S","metrics":{"Go":"97.7","JS":"86.0","Java":"94.0","Overall":"93.4","PHP":"96.7","Python":"99.8","Ruby":"86.3"},"uses_additional_data":false,"paper_date":"2022-01-24","paper":"/paper/text-and-code-embeddings-by-contrastive-pre","paper_url":"https://arxiv.org/abs/2201.10005v1","paper_title":"Text and Code Embeddings by Contrastive Pre-Training","code":"https://github.com/openmatch/coco-dr","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"CodeT5+ 770M","metrics":{"Go":"92.7","JS":"71.3","Java":"76.2","Overall":"77.4","PHP":"70.1","Python":"75.8","Ruby":"78.0"},"uses_additional_data":false,"paper_date":"2023-05-13","paper":"/paper/codet5-open-code-large-language-models-for","paper_url":"https://arxiv.org/abs/2305.07922v2","paper_title":"CodeT5+: Open Code Large Language Models for Code Understanding and Generation","code":"https://github.com/salesforce/codet5","n_code_links":2,"syntology":{"n_ran":3,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":4,"model":"GraphCodeBERT","metrics":{"Go":"84.1","JS":"71.1","Java":"75.7","Overall":"77.4","PHP":"72.5 ","Python":"87.9","Ruby":"73.2"},"uses_additional_data":false,"paper_date":"2020-09-17","paper":"/paper/graphcodebert-pre-training-code","paper_url":"https://arxiv.org/abs/2009.08366v4","paper_title":"GraphCodeBERT: Pre-training Code Representations with Data Flow","code":"https://github.com/microsoft/CodeBERT","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"CodeT5+ 220M","metrics":{"Go":"92.4","JS":"70..8","Java":"76.1","Overall":"77.1","PHP":"69.8","Python":"75.6","Ruby":"77.7"},"uses_additional_data":false,"paper_date":"2023-05-13","paper":"/paper/codet5-open-code-large-language-models-for","paper_url":"https://arxiv.org/abs/2305.07922v2","paper_title":"CodeT5+: Open Code Large Language Models for Code Understanding and Generation","code":"https://github.com/salesforce/codet5","n_code_links":2,"syntology":{"n_ran":3,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":6,"model":"CodeBERT","metrics":{"Go":"69.3","JS":"74.8","Java":"86.8","Overall":"76.0","PHP":"70.6","Python":"84.0","Ruby":"70.6"},"uses_additional_data":false,"paper_date":"2020-02-19","paper":"/paper/codebert-a-pre-trained-model-for-programming","paper_url":"https://arxiv.org/abs/2002.08155v4","paper_title":"CodeBERT: A Pre-Trained Model for Programming and Natural Languages","code":"https://github.com/salesforce/codet5","n_code_links":9,"syntology":{"n_ran":2,"n_unverified":18,"n_samples":20,"n_pointer_only_licence":4}}],"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":3,"rows_with_any_sample_ran":3,"distinct_papers_with_graph_line":2,"distinct_papers_with_any_sample_ran":2,"samples_over_distinct_papers":{"n_ran":5,"n_unverified":19,"n_samples":24,"n_pointer_only_licence":4,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":8,"n_unverified":20,"n_samples":28,"n_pointer_only_licence":4,"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"}}}