{"url":"/dataset/strategyqa","name":"StrategyQA","full_name":null,"description_markdown":"**StrategyQA** is a question answering benchmark where the required reasoning steps are implicit in the question, and should be inferred using a strategy.\r\nIt includes 2,780 examples, each consisting of a strategy question, its decomposition, and evidence paragraphs.\r\nQuestions in StrategyQA are short, topic-diverse, and cover a wide range of strategies.","description_withheld":null,"homepage":"https://allenai.org/data/strategyqa","introduced_date":"2021-01-06","introduced_date_note":null,"introduced_by":{"paper":"/paper/did-aristotle-use-a-laptop-a-question","title":"Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies","first_author":"Mor Geva","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Question Answering","url":"/task/question-answering","datasets_with_task":"/datasets/task/question-answering"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["StrategyQA"],"data_loaders":[],"num_papers_in_archive":291,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/question-answering-on-strategyqa","task":"Question Answering","dataset_variant":"StrategyQA","rows":12,"metrics":["Accuracy","EM"],"first_row_in_archive_order":{"model":"PaLM 2 (few-shot, CoT, SC)","paper":"/paper/palm-2-technical-report-1","metrics":{"Accuracy":"90.4"},"code_links":[{"title":"eternityyw/tram-benchmark","url":"https://github.com/eternityyw/tram-benchmark"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/chain-of-action-faithful-and-multimodal","title":"Chain-of-Action: Faithful and Multimodal Question Answering through Large Language Models","date":"2024-03-26","rows_on_this_dataset":4,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":10,"samples_ran":8,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/palm-2-technical-report-1","title":"PaLM 2 Technical Report","date":"2023-05-17","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/search-in-the-chain-towards-the-accurate","title":"Search-in-the-Chain: Interactively Enhancing Large Language Models with Search for Knowledge-intensive Tasks","date":"2023-04-28","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/rethinking-with-retrieval-faithful-large","title":"Rethinking with Retrieval: Faithful Large Language Model Inference","date":"2022-12-31","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/transcending-scaling-laws-with-0-1-extra","title":"Transcending Scaling Laws with 0.1% Extra Compute","date":"2022-10-20","rows_on_this_dataset":3,"code_links":0,"syntology":null},{"paper":"/paper/least-to-most-prompting-enables-complex","title":"Least-to-Most Prompting Enables Complex Reasoning in Large Language Models","date":"2022-05-21","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":1,"samples_harvested":10,"samples_ran":8,"samples_unverified":2,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}