{"url":"/sota/code-completion-on-codexglue-py150","task":{"name":"Code Completion","url":"/task/code-completion","note":null},"dataset":{"name":"CodeXGLUE - PY150","url":"/dataset/codexglue"},"category":"Computer Code","categories":["Computer Code"],"category_note":null,"description":null,"description_from":null,"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 (token-level)","EM (line-level)","Edit Sim (line-level)"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Accuracy (token-level)":"higher","EM (line-level)":null,"Edit Sim (line-level)":null}},"counts":{"rows":3,"rows_with_code":3,"rows_with_paper_page":3,"rows_dated":3,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"CodeGPT-adapted","metrics":{"Accuracy (token-level)":"75.11","EM (line-level)":"39.65","Edit Sim (line-level)":"69.84"},"uses_additional_data":false,"paper_date":"2021-02-09","paper":"/paper/codexglue-a-machine-learning-benchmark","paper_url":"https://arxiv.org/abs/2102.04664v2","paper_title":"CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation","code":"https://github.com/microsoft/CodeXGLUE","n_code_links":7,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":2,"model":"CodeT5+ 770M","metrics":{"EM (line-level)":"44.86","Edit Sim (line-level)":"74.22"},"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":3,"model":"CodeT5+ 220M","metrics":{"EM (line-level)":"43.42","Edit Sim (line-level)":"73.69"},"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}}],"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":4,"n_unverified":1,"n_samples":5,"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":7,"n_unverified":2,"n_samples":9,"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"}}}