{"url":"/dataset/mathmc","name":"MathMC","full_name":null,"description_markdown":"Existing arithmetic benchmarks have a limited number of multiple-choice questions.  To address this gap, MathMC is created including 1,000 Chinese mathematical multiple-choice questions with detailed explanations and focusing on math problems typically encountered in grades 4 to 6.  It features a wide range of question types, including arithmetic, algebra, geometry, statistics, reasoning, and more, enhancing the diversity of current Chinese arithmetic datasets.","description_withheld":null,"homepage":"","introduced_date":"2024-10-10","introduced_date_note":null,"introduced_by":{"paper":"/paper/teaching-inspired-integrated-prompting","title":"Teaching-Inspired Integrated Prompting Framework: A Novel Approach for Enhancing Reasoning in Large Language Models","first_author":"Wenting Tan","url":null},"license":null,"modalities":[],"tasks":[{"name":"Mathematical Reasoning","url":"/task/mathematical-reasoning","datasets_with_task":"/datasets/task/mathematical-reasoning"},{"name":"Math Word Problem Solving","url":"/task/math-word-problem-solving","datasets_with_task":"/datasets/task/math-word-problem-solving"},{"name":"Arithmetic Reasoning","url":"/task/arithmetic-reasoning","datasets_with_task":"/datasets/task/arithmetic-reasoning"}],"languages":[{"name":"Chinese","url":"/datasets/language/chinese"}],"variants":["MathMC"],"data_loaders":[],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/arithmetic-reasoning-on-mathmc","task":"Arithmetic Reasoning","dataset_variant":"MathMC","rows":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"GPT-4 (Teaching-Inspired)","paper":"/paper/teaching-inspired-integrated-prompting","metrics":{"Accuracy":"92.2"},"code_links":[{"title":"sallytan13/teaching-inspired-prompting","url":"https://github.com/sallytan13/teaching-inspired-prompting"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/teaching-inspired-integrated-prompting","title":"Teaching-Inspired Integrated Prompting Framework: A Novel Approach for Enhancing Reasoning in Large Language Models","date":"2024-10-10","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":8,"samples_unverified":0,"pointer_only_for_licence":8,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":1,"samples_harvested":8,"samples_ran":8,"samples_unverified":0,"pointer_only_for_licence":8,"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."}