{"url":"/dataset/headqa","name":"HeadQA","full_name":null,"description_markdown":"HeadQA is a multi-choice question answering testbed to encourage research on complex reasoning. The questions come from exams to access a specialized position in the Spanish healthcare system, and are challenging even for highly specialized humans. \r\n\r\nSource: [HEAD-QA: A Healthcare Dataset for Complex Reasoning](/paper/head-qa-a-healthcare-dataset-for-complex)\r\nImage Source: [https://arxiv.org/pdf/1906.04701v1.pdf](https://arxiv.org/pdf/1906.04701v1.pdf)","description_withheld":null,"homepage":"https://github.com/aghie/head-qa","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/head-qa-a-healthcare-dataset-for-complex","title":"HEAD-QA: A Healthcare Dataset for Complex Reasoning","first_author":"David Vilares","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"},{"name":"Text Generation","url":"/task/text-generation","datasets_with_task":"/datasets/task/text-generation"},{"name":"Natural Language Inference","url":"/task/natural-language-inference","datasets_with_task":"/datasets/task/natural-language-inference"},{"name":"Information Retrieval","url":"/task/information-retrieval","datasets_with_task":"/datasets/task/information-retrieval"}],"languages":[{"name":"Spanish","url":"/datasets/language/spanish"}],"variants":["HeadQA"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/dvilares/head_qa","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/head_qa","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/aghie/head-qa","url":"https://github.com/aghie/head-qa","frameworks":[]}],"num_papers_in_archive":23,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/text-generation-on-headqa","task":"Text Generation","dataset_variant":"HeadQA","rows":0,"metrics":["acc"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[],"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."}