{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/dataset/gpqa","name":"GPQA","full_name":null,"description_markdown":"**GPQA** stands for **Graduate-Level Google-Proof Q&A Benchmark**. It's a challenging dataset designed to evaluate the capabilities of **Large Language Models (LLMs)** and scalable oversight mechanisms. Let me provide more details about it:\r\n\r\n- **Description**: GPQA consists of **448 multiple-choice questions** meticulously crafted by domain experts in **biology, physics, and chemistry**. These questions are intentionally designed to be **high-quality and extremely difficult**.\r\n- **Expert Accuracy**: Even experts who hold or are pursuing **PhDs in the corresponding domains** achieve only **65% accuracy** on these questions (or **74%** when excluding clear mistakes identified in retrospect).\r\n- **Google-Proof**: The questions are \"Google-proof,\" meaning that even with **unrestricted access to the web**, highly skilled non-expert validators only reach an accuracy of **34%** despite spending over 30 minutes searching for answers.\r\n- **AI Systems Difficulty**: State-of-the-art AI systems, including our strongest **GPT-4 based baseline**, achieve only **39% accuracy** on this challenging dataset.\r\n\r\nThe difficulty of GPQA for both skilled non-experts and cutting-edge AI systems makes it an excellent resource for conducting **realistic scalable oversight experiments**. These experiments aim to explore ways for human experts to reliably obtain truthful information from AI systems that surpass human capabilities¹³.\r\n\r\nIn summary, GPQA serves as a valuable benchmark for assessing the robustness and limitations of language models, especially when faced with complex and nuanced questions. Its difficulty level encourages research into effective oversight methods, bridging the gap between AI and human expertise.\r\n\r\n(1) [2311.12022] GPQA: A Graduate-Level Google-Proof Q&A Benchmark - arXiv.org. https://arxiv.org/abs/2311.12022.\r\n(2) GPQA: A Graduate-Level Google-Proof Q&A Benchmark — Klu. https://klu.ai/glossary/gpqa-eval.\r\n(3) GPA Dataset (Spring 2010 through Spring 2020) - Data Science Discovery. https://discovery.cs.illinois.edu/dataset/gpa/.\r\n(4) GPQA: A Graduate-Level Google-Proof Q&A Benchmark - GitHub. https://github.com/idavidrein/gpqa.\r\n(5) Data Sets - OpenIntro. https://www.openintro.org/data/index.php?data=satgpa.\r\n(6) undefined. https://doi.org/10.48550/arXiv.2311.12022.\r\n(7) undefined. https://arxiv.org/abs/2311.12022%29.","description_withheld":null,"homepage":"https://github.com/idavidrein/gpqa","introduced_date":"2023-11-20","introduced_date_note":null,"introduced_by":{"paper":"/paper/gpqa-a-graduate-level-google-proof-q-a","title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","first_author":"David Rein","url":null},"license":null,"modalities":[],"tasks":[{"name":"task","url":null,"datasets_with_task":"/datasets/task/task"}],"languages":[],"variants":["GPQA"],"data_loaders":[{"repo":"https://github.com/RUCAIBox/LLMBox","url":"https://github.com/RUCAIBox/LLMBox","frameworks":["pytorch"]}],"num_papers_in_archive":270,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/on-gpqa","task":"","dataset_variant":"GPQA","rows":7,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"NVIDIA Llama Nemotron Ultra v1","paper":null,"metrics":{"Accuracy":"76.01"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers":{"order":"date (newest first), then slug","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"shown":3,"of":3,"counts":{"papers_with_a_benchmark_row":3,"with_a_code_link":3,"where_syntology_ran_a_sample":2,"not_listed_spam_title":0,"listed":3,"listed_where_code_ran":2,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":0,"every_run_a_failure_of_syntologys_instrument":2,"listed_with_a_run_with_no_instrument_failure":0,"listed_every_run_a_failure_of_syntologys_instrument":2,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"paper":"/paper/search-o1-agentic-search-enhanced-large","slug":"search-o1-agentic-search-enhanced-large","title":"Search-o1: Agentic Search-Enhanced Large Reasoning Models","date":"2025-01-09","arxiv_id":"2501.05366","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/qwen2-5-technical-report","slug":"qwen2-5-technical-report","title":"Qwen2.5 Technical Report","date":"2024-12-19","arxiv_id":"2412.15115","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["qwenlm/qwen2.5"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/qwen2-5-technical-report#ran","syntology_url":"https://syntology.ai/paper/2412.15115","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.15115"}}}},{"paper":"/paper/textgrad-automatic-differentiation-via-text","slug":"textgrad-automatic-differentiation-via-text","title":"TextGrad: Automatic \"Differentiation\" via Text","date":"2024-06-11","arxiv_id":"2406.07496","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["zou-group/textgrad"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/textgrad-automatic-differentiation-via-text#ran","syntology_url":"https://syntology.ai/paper/2406.07496","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.07496"}}}}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/search-o1-agentic-search-enhanced-large","slug":"search-o1-agentic-search-enhanced-large","title":"Search-o1: Agentic Search-Enhanced Large Reasoning Models","date":"2025-01-09","arxiv_id":"2501.05366","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/qwen2-5-technical-report","slug":"qwen2-5-technical-report","title":"Qwen2.5 Technical Report","date":"2024-12-19","arxiv_id":"2412.15115","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["qwenlm/qwen2.5"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/qwen2-5-technical-report#ran","syntology_url":"https://syntology.ai/paper/2412.15115","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.15115"}}}},{"paper":"/paper/textgrad-automatic-differentiation-via-text","slug":"textgrad-automatic-differentiation-via-text","title":"TextGrad: Automatic \"Differentiation\" via Text","date":"2024-06-11","arxiv_id":"2406.07496","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["zou-group/textgrad"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/textgrad-automatic-differentiation-via-text#ran","syntology_url":"https://syntology.ai/paper/2406.07496","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.07496"}}}}],"papers_where_code_ran":2,"papers_where_code_ran_first_page":"/dataset/gpqa/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/dataset/gpqa/papers/ran/1","json":"/dataset/gpqa/papers/ran/1.json","rows":2}],"row_route":"each paper's syntology object carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers","syntology_totals":{"read_at":"2026-10-05T00:36:11+00:00","papers_with_samples":2,"samples_harvested":4,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":2,"samples_unverified":2,"pointer_only_for_licence":1,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":2,"papers_with_a_run_with_no_instrument_failure":0,"papers_where_every_run_was_an_instrument_failure":2,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"key_notes":{"samples_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","samples_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":65,"papers_placed":1,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[{"leaderboard":"/sota/on-gpqa","since_archive":"/sota/on-gpqa#since-judged","papers_judged":65,"placed":1}]},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"be5b3ac8fd2bd8ce858f618145533f5f4c34adc901ee8eeba05b2c053f89c4c1","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}