{"url":"/dataset/math-v","name":"MATH-V","full_name":null,"description_markdown":"Math-Vision (Math-V) dataset is a meticulously curated collection of 3,040 high-quality mathematical problems with visual contexts sourced from real math competitions. Spanning 16 distinct mathematical disciplines and graded across 5 levels of difficulty, our dataset provides a comprehensive and diverse set of challenges for evaluating the mathematical reasoning abilities of LMMs.\r\n\r\nThrough extensive experimentation, we unveil a notable performance gap between current LMMs and human performance on Math-Vision, underscoring the imperative for further advancements in LMMs. Moreover, our detailed categorization allows for a thorough error analysis of LMMs, offering valuable insights to guide future research and development.","description_withheld":null,"homepage":"https://mathvision-cuhk.github.io/","introduced_date":"2024-02-22","introduced_date_note":null,"introduced_by":{"paper":"/paper/measuring-multimodal-mathematical-reasoning","title":"Measuring Multimodal Mathematical Reasoning with MATH-Vision Dataset","first_author":"Ke Wang","url":null},"license":{"name":"mit","url":null},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Mathematical Reasoning","url":"/task/mathematical-reasoning","datasets_with_task":"/datasets/task/mathematical-reasoning"},{"name":"Multiple-choice","url":"/task/multiple-choice","datasets_with_task":"/datasets/task/multiple-choice"},{"name":"Multimodal Reasoning","url":"/task/multimodal-reasoning","datasets_with_task":"/datasets/task/multimodal-reasoning"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["MATH-V"],"data_loaders":[],"num_papers_in_archive":12,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/multimodal-reasoning-on-math-v","task":"Multimodal Reasoning","dataset_variant":"MATH-V","rows":4,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"GPT4V","paper":"/paper/measuring-multimodal-mathematical-reasoning","metrics":{"Accuracy":"22.76"},"code_links":[{"title":"mathllm/math-v","url":"https://github.com/mathllm/math-v"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/measuring-multimodal-mathematical-reasoning","title":"Measuring Multimodal Mathematical Reasoning with MATH-Vision Dataset","date":"2024-02-22","rows_on_this_dataset":4,"code_links":1,"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."}