{"url":"/task/mathematical-question-answering","name":"Mathematical Question Answering","slug":"mathematical-question-answering","description_markdown":"Building systems that automatically answer mathematical questions.","categories":[{"name":"Knowledge Base","url":"/area/knowledge-base"},{"name":"Reasoning","url":"/area/reasoning"},{"name":"Time Series","url":"/area/time-series"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":11,"papers_with_code":9,"benchmarks":2,"benchmark_tables_in_archive":2,"benchmark_tables_shown":2,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":11,"subtasks":1,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/mathematical-question-answering-on-geometry3k","slug":"mathematical-question-answering-on-geometry3k","dataset":"Geometry3K","dataset_url":"/dataset/geometry3k","rows_in_archive":8,"metrics":["Accuracy (%)"],"first_row_in_archive_order":{"model":"Human Expert","paper_title":"Inter-GPS: Interpretable Geometry Problem Solving with Formal Language and Symbolic Reasoning","paper_url":"/paper/inter-gps-interpretable-geometry-problem","paper_date":"2021-05-10","arxiv_id":"2105.04165","code_links":[{"title":"lupantech/InterGPS","url":"https://github.com/lupantech/InterGPS"}],"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":0}}},{"leaderboard":"/sota/mathematical-question-answering-on-geos","slug":"mathematical-question-answering-on-geos","dataset":"GeoS","dataset_url":"/dataset/geos","rows_in_archive":2,"metrics":["Accuracy (%)"],"first_row_in_archive_order":{"model":"Inter-GPS","paper_title":"Inter-GPS: Interpretable Geometry Problem Solving with Formal Language and Symbolic Reasoning","paper_url":"/paper/inter-gps-interpretable-geometry-problem","paper_date":"2021-05-10","arxiv_id":"2105.04165","code_links":[{"title":"lupantech/InterGPS","url":"https://github.com/lupantech/InterGPS"}],"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":0}}}],"datasets":[{"url":"/dataset/geoqa","name":"GeoQA","full_name":"Geometric Question Answering","num_papers_in_archive":46},{"url":"/dataset/geometry3k","name":"Geometry3K","full_name":"","num_papers_in_archive":45},{"url":"/dataset/iconqa","name":"IconQA","full_name":"Icon Question Answering","num_papers_in_archive":42},{"url":"/dataset/geos","name":"GeoS","full_name":"","num_papers_in_archive":24},{"url":"/dataset/mathematics","name":"Mathematics Dataset","full_name":"","num_papers_in_archive":19},{"url":"/dataset/mathbench","name":"MathBench","full_name":"MathBench: Evaluating the Theory and Application Proficiency of LLMs with a Hierarchical Mathematics Benchmark","num_papers_in_archive":16},{"url":"/dataset/smart-101","name":"SMART-101","full_name":"Simple Multimodal Algorithmic Reasoning Task Dataset","num_papers_in_archive":6},{"url":"/dataset/dart-math-hard","name":"DART-Math-Hard","full_name":"","num_papers_in_archive":2},{"url":"/dataset/eedi-dataset","name":"Eedi Dataset","full_name":"","num_papers_in_archive":2},{"url":"/dataset/paramawps","name":"ParaMAWPS","full_name":"Paraphrased Math Word Problem Solving Repository","num_papers_in_archive":2},{"url":"/dataset/dart-math-uniform","name":"DART-Math-Uniform","full_name":"","num_papers_in_archive":1}],"subtasks":[{"url":"/task/math-word-problem-solving","name":"Math Word Problem Solving"}],"parent_tasks":[{"url":"/task/question-answering","name":"Question Answering"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":9,"of":9,"tagged_in_all":11,"items":[{"url":"/paper/analysing-mathematical-reasoning-abilities-of-1","title":"Analysing Mathematical Reasoning Abilities of Neural Models","date":"2019-04-02","arxiv_id":"1904.01557","repositories_listed":7,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/mathchat-benchmarking-mathematical-reasoning","title":"MathChat: Benchmarking Mathematical Reasoning and Instruction Following in Multi-Turn Interactions","date":"2024-05-29","arxiv_id":"2405.19444","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/gold-geometry-problem-solver-with-natural","title":"GOLD: Geometry Problem Solver with Natural Language Description","date":"2024-05-01","arxiv_id":"2405.00494","repositories_listed":1,"syntology":null},{"url":"/paper/speak-like-a-native-prompting-large-language","title":"AlignedCoT: Prompting Large Language Models via Native-Speaking Demonstrations","date":"2023-11-22","arxiv_id":"2311.13538","repositories_listed":1,"syntology":null},{"url":"/paper/mining-mathematical-documents-for-question","title":"Mining Mathematical Documents for Question Answering via Unsupervised Formula Labeling","date":"2022-11-12","arxiv_id":"2211.06664","repositories_listed":1,"syntology":null},{"url":"/paper/plane-geometry-diagram-parsing","title":"Plane Geometry Diagram Parsing","date":"2022-05-19","arxiv_id":"2205.09363","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/iconqa-a-new-benchmark-for-abstract-diagram","title":"IconQA: A New Benchmark for Abstract Diagram Understanding and Visual Language Reasoning","date":"2021-10-25","arxiv_id":"2110.13214","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_unverified":2,"n_pointer_only":10}},{"url":"/paper/inter-gps-interpretable-geometry-problem","title":"Inter-GPS: Interpretable Geometry Problem Solving with Formal Language and Symbolic Reasoning","date":"2021-05-10","arxiv_id":"2105.04165","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/solving-geometry-problems-combining-text-and","title":"Solving Geometry Problems: Combining Text and Diagram Interpretation","date":"2015-09-01","arxiv_id":null,"repositories_listed":1,"syntology":null}],"syntology_records":5,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}