{"url":"/sota/openapi-code-completion-on-openapi-code","task":{"name":"OpenAPI code completion","url":"/task/openapi-code-completion","note":null},"dataset":{"name":"OpenAPI completion refined","url":"/dataset/openapi-code-completion"},"category":"Computer Code","categories":["Computer Code"],"category_note":null,"description":"Code Completion in the [OpenAPI](https://spec.openapis.org/oas/latest.html) format which is a widely used machine and human-readable format for describing RESTful APIs in YAML or JSON.\r\n\r\nThe benchmark source code is available [on GitHub](https://github.com/BohdanPetryshyn/openapi-completion-benchmark).","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":["Correctness, avg., %","Correctness, max., %","Validness, avg., %","Validness, max., %"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Correctness, avg., %":null,"Correctness, max., %":null,"Validness, avg., %":null,"Validness, max., %":null}},"counts":{"rows":4,"rows_with_code":4,"rows_with_paper_page":4,"rows_dated":4,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"Code Llama 7B, fine-tuned with document splitting","metrics":{"Correctness, avg., %":"34","Correctness, max., %":"42","Validness, avg., %":"69.1","Validness, max., %":"76"},"uses_additional_data":false,"paper_date":"2024-05-24","paper":"/paper/optimizing-large-language-models-for-openapi","paper_url":"https://arxiv.org/abs/2405.15729v2","paper_title":"Optimizing Large Language Models for OpenAPI Code Completion","code":"https://github.com/BohdanPetryshyn/code-llama-fim-fine-tuning","n_code_links":2,"syntology":null},{"rank_in_archive_order":2,"model":"Code Llama 7B, fine-tuned at 4096 tokens","metrics":{"Correctness, avg., %":"32","Correctness, max., %":"45","Validness, avg., %":"63.1","Validness, max., %":"84"},"uses_additional_data":false,"paper_date":"2024-05-24","paper":"/paper/optimizing-large-language-models-for-openapi","paper_url":"https://arxiv.org/abs/2405.15729v2","paper_title":"Optimizing Large Language Models for OpenAPI Code Completion","code":"https://github.com/BohdanPetryshyn/code-llama-fim-fine-tuning","n_code_links":2,"syntology":null},{"rank_in_archive_order":3,"model":"Code Llama 7B","metrics":{"Correctness, avg., %":"31.1","Correctness, max., %":"36","Validness, avg., %":"60.7","Validness, max., %":"64"},"uses_additional_data":false,"paper_date":"2024-05-24","paper":"/paper/optimizing-large-language-models-for-openapi","paper_url":"https://arxiv.org/abs/2405.15729v2","paper_title":"Optimizing Large Language Models for OpenAPI Code Completion","code":"https://github.com/BohdanPetryshyn/code-llama-fim-fine-tuning","n_code_links":2,"syntology":null},{"rank_in_archive_order":4,"model":"GitHub Copilot","metrics":{"Correctness, avg., %":"29","Correctness, max., %":"29","Validness, avg., %":"68","Validness, max., %":"68"},"uses_additional_data":false,"paper_date":"2024-05-24","paper":"/paper/optimizing-large-language-models-for-openapi","paper_url":"https://arxiv.org/abs/2405.15729v2","paper_title":"Optimizing Large Language Models for OpenAPI Code Completion","code":"https://github.com/BohdanPetryshyn/code-llama-fim-fine-tuning","n_code_links":2,"syntology":null}],"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":0,"rows_with_any_sample_ran":0,"distinct_papers_with_graph_line":0,"distinct_papers_with_any_sample_ran":0,"samples_over_distinct_papers":{"n_ran":0,"n_unverified":0,"n_samples":0,"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":0,"n_unverified":0,"n_samples":0,"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"}}}