{"url":"/dataset/sciq","name":"SciQ","full_name":"SciQ","description_markdown":"The SciQ dataset contains 13,679 crowdsourced science exam questions about Physics, Chemistry and Biology, among others. The questions are in multiple-choice format with 4 answer options each. For the majority of the questions, an additional paragraph with supporting evidence for the correct answer is provided.\r\n\r\nSource: [Allen Institute for AI](https://allenai.org/data/sciq)","description_withheld":null,"homepage":"https://allenai.org/data/sciq","introduced_date":"2017-07-19","introduced_date_note":null,"introduced_by":{"paper":"/paper/crowdsourcing-multiple-choice-science","title":"Crowdsourcing Multiple Choice Science Questions","first_author":"Johannes Welbl","url":null},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Text Generation","url":"/task/text-generation","datasets_with_task":"/datasets/task/text-generation"},{"name":"Reading Comprehension","url":"/task/reading-comprehension","datasets_with_task":"/datasets/task/reading-comprehension"},{"name":"Question Generation","url":"/task/question-generation","datasets_with_task":"/datasets/task/question-generation"},{"name":"Distractor Generation","url":"/task/distractor-generation","datasets_with_task":"/datasets/task/distractor-generation"}],"languages":[],"variants":["SciQ"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/Yogama/Employee","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/allenai/sciq","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/izumi-lab/sciq-ja-mbartm2m","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/sciq","frameworks":["tf","pytorch","jax"]}],"num_papers_in_archive":183,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/text-generation-on-sciq","task":"Text Generation","dataset_variant":"SciQ","rows":3,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"LLaMA-65B+CFG (zero-shot)","paper":"/paper/stay-on-topic-with-classifier-free-guidance","metrics":{"Accuracy":"96.6"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/stay-on-topic-with-classifier-free-guidance","title":"Stay on topic with Classifier-Free Guidance","date":"2023-06-30","rows_on_this_dataset":3,"code_links":0,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"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."}