{"url":"/sota/on-gpqa","task":{"name":null,"url":null,"note":"task not recorded in the archive for this table"},"dataset":{"name":"GPQA","url":"/dataset/gpqa"},"category":null,"categories":["Adversarial","Audio","Computer Code","Computer Vision","Medical","Methodology","Miscellaneous","Music","Natural Language Processing","Reasoning","Speech"],"category_note":"the archive's category list for this table covers most areas; treated as no area assigned","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"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Accuracy":"higher"}},"counts":{"rows":7,"rows_with_code":4,"rows_with_paper_page":4,"rows_dated":4,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"NVIDIA Llama Nemotron Ultra v1","metrics":{"Accuracy":"76.01"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":2,"model":"Openai-o1-preview","metrics":{"Accuracy":"72.3"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":3,"model":"Claude3.5-Sonnet","metrics":{"Accuracy":"65"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":4,"model":"Search-o1","metrics":{"Accuracy":"63.6"},"uses_additional_data":false,"paper_date":"2025-01-09","paper":"/paper/search-o1-agentic-search-enhanced-large","paper_url":"https://arxiv.org/abs/2501.05366v1","paper_title":"Search-o1: Agentic Search-Enhanced Large Reasoning Models","code":"https://github.com/sunnynexus/search-o1","n_code_links":2,"syntology":null},{"rank_in_archive_order":5,"model":"GPT4o+TextGrad","metrics":{"Accuracy":"55"},"uses_additional_data":false,"paper_date":"2024-06-11","paper":"/paper/textgrad-automatic-differentiation-via-text","paper_url":"https://arxiv.org/abs/2406.07496v1","paper_title":"TextGrad: Automatic \"Differentiation\" via Text","code":"https://github.com/zou-group/textgrad","n_code_links":2,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":6,"model":"GPT4o","metrics":{"Accuracy":"53.6"},"uses_additional_data":false,"paper_date":"2024-06-11","paper":"/paper/textgrad-automatic-differentiation-via-text","paper_url":"https://arxiv.org/abs/2406.07496v1","paper_title":"TextGrad: Automatic \"Differentiation\" via Text","code":"https://github.com/zou-group/textgrad","n_code_links":2,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":7,"model":"Qwen2.5-72B-Instruct","metrics":{"Accuracy":"49"},"uses_additional_data":false,"paper_date":"2024-12-19","paper":"/paper/qwen2-5-technical-report","paper_url":"https://arxiv.org/abs/2412.15115v2","paper_title":"Qwen2.5 Technical Report","code":"https://github.com/qwenlm/qwen1.5","n_code_links":6,"syntology":{"n_ran":1,"n_unverified":2,"n_samples":3,"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":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":1,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":3,"n_unverified":2,"n_samples":5,"n_pointer_only_licence":2,"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"}}}