{"url":"/sota/code-translation-on-codexglue-codetrans","task":{"name":"Code Translation","url":"/task/code-translation","note":null},"dataset":{"name":"CodeXGLUE - CodeTrans","url":"/dataset/codexglue"},"category":"Natural Language Processing","categories":["Computer Code","Natural Language Processing","Reasoning"],"category_note":null,"description":"Code translation is the process of converting code written in one programming language to another programming language while maintaining the same functionality. This process is also known as code conversion, source-to-source translation, or transpilation. Code translation is often performed when developers want to take advantage of new programming languages, improve code performance, or maintain legacy systems. Some common examples include translating code from Python to Java, or from JavaScript to TypeScript.","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 (C#→Java)","Accuracy (Java→C#)","BLEU (C#→Java)","BLEU (Java→C#)","CodeBLEU (C#→Java)","CodeBLEU (Java→C#)"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Accuracy (C#→Java)":"higher","Accuracy (Java→C#)":"higher","BLEU (C#→Java)":"higher","BLEU (Java→C#)":"higher","CodeBLEU (C#→Java)":null,"CodeBLEU (Java→C#)":null}},"counts":{"rows":2,"rows_with_code":2,"rows_with_paper_page":2,"rows_dated":2,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"CodeT5","metrics":{"Accuracy (C#→Java)":"66.90","Accuracy (Java→C#)":"65.90","BLEU (C#→Java)":"79.87","BLEU (Java→C#)":"84.03"},"uses_additional_data":false,"paper_date":"2021-09-02","paper":"/paper/codet5-identifier-aware-unified-pre-trained","paper_url":"https://arxiv.org/abs/2109.00859v1","paper_title":"CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation","code":"https://github.com/salesforce/codet5","n_code_links":5,"syntology":{"n_ran":1,"n_unverified":10,"n_samples":11,"n_pointer_only_licence":0}},{"rank_in_archive_order":2,"model":"CodeBERT","metrics":{"Accuracy (C#→Java)":"58","Accuracy (Java→C#)":"59","BLEU (C#→Java)":"72.14","BLEU (Java→C#)":"79.92","CodeBLEU (C#→Java)":"79.41","CodeBLEU (Java→C#)":"85.1"},"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}}],"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":2,"rows_with_any_sample_ran":2,"distinct_papers_with_graph_line":2,"distinct_papers_with_any_sample_ran":2,"samples_over_distinct_papers":{"n_ran":2,"n_unverified":10,"n_samples":12,"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":2,"n_unverified":10,"n_samples":12,"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"}}}