{"url":"/sota/multimodal-reasoning-on-math-v","task":{"name":"Multimodal Reasoning","url":"/task/multimodal-reasoning","note":null},"dataset":{"name":"MATH-V","url":"/dataset/math-v"},"category":"Computer Vision","categories":["Computer Vision","Reasoning"],"category_note":null,"description":"Reasoning over multimodal inputs.","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["Accuracy"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Accuracy":"higher"}},"counts":{"rows":4,"rows_with_code":4,"rows_with_paper_page":4,"rows_dated":4,"rows_using_additional_data":4},"rows":[{"rank_in_archive_order":1,"model":"GPT4V","metrics":{"Accuracy":"22.76"},"uses_additional_data":true,"paper_date":"2024-02-22","paper":"/paper/measuring-multimodal-mathematical-reasoning","paper_url":"https://arxiv.org/abs/2402.14804v1","paper_title":"Measuring Multimodal Mathematical Reasoning with MATH-Vision Dataset","code":"https://github.com/mathllm/math-v","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"Gemini Pro","metrics":{"Accuracy":"17.66"},"uses_additional_data":true,"paper_date":"2024-02-22","paper":"/paper/measuring-multimodal-mathematical-reasoning","paper_url":"https://arxiv.org/abs/2402.14804v1","paper_title":"Measuring Multimodal Mathematical Reasoning with MATH-Vision Dataset","code":"https://github.com/mathllm/math-v","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"Qwen-VL-Max","metrics":{"Accuracy":"15.59"},"uses_additional_data":true,"paper_date":"2024-02-22","paper":"/paper/measuring-multimodal-mathematical-reasoning","paper_url":"https://arxiv.org/abs/2402.14804v1","paper_title":"Measuring Multimodal Mathematical Reasoning with MATH-Vision Dataset","code":"https://github.com/mathllm/math-v","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"InternLM-XComposer2-VL","metrics":{"Accuracy":"14.54"},"uses_additional_data":true,"paper_date":"2024-02-22","paper":"/paper/measuring-multimodal-mathematical-reasoning","paper_url":"https://arxiv.org/abs/2402.14804v1","paper_title":"Measuring Multimodal Mathematical Reasoning with MATH-Vision Dataset","code":"https://github.com/mathllm/math-v","n_code_links":1,"syntology":null}],"since_archive":{"present":false,"note":"No Syntology-extracted rows are published in this build."},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":0,"rows_with_any_sample_ran":0,"distinct_papers_with_graph_line":0,"distinct_papers_with_any_sample_ran":0,"samples_over_distinct_papers":{"n_ran":0,"n_unverified":0,"n_samples":0,"n_pointer_only_licence":0,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":0,"n_unverified":0,"n_samples":0,"n_pointer_only_licence":0,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}