{"url":"/sota/math-word-problem-solving-on-paramawps","task":{"name":"Math Word Problem Solving","url":"/task/math-word-problem-solving","note":null},"dataset":{"name":"ParaMAWPS","url":"/dataset/paramawps"},"category":"Reasoning","categories":["Reasoning"],"category_note":null,"description":"A math word problem is a mathematical exercise (such as in a textbook, worksheet, or exam) where significant background information on the problem is presented in ordinary language rather than in mathematical notation. As most word problems involve a narrative of some sort, they are sometimes referred to as story problems and may vary in the amount of technical language used.","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":6,"rows_with_code":6,"rows_with_paper_page":6,"rows_dated":6,"rows_using_additional_data":1},"rows":[{"rank_in_archive_order":1,"model":"DeBERTa (VM)","metrics":{"Accuracy (%)":"79.1"},"uses_additional_data":true,"paper_date":"2023-06-24","paper":"/paper/math-word-problem-solving-by-generating","paper_url":"https://arxiv.org/abs/2306.13899v1","paper_title":"Math Word Problem Solving by Generating Linguistic Variants of Problem Statements","code":"https://github.com/starscream-11813/variational-mathematical-reasoning","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"DeBERTa","metrics":{"Accuracy (%)":"74.1"},"uses_additional_data":false,"paper_date":"2020-06-05","paper":"/paper/deberta-decoding-enhanced-bert-with","paper_url":"https://arxiv.org/abs/2006.03654v6","paper_title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","code":"https://github.com/huggingface/transformers","n_code_links":14,"syntology":{"n_ran":4,"n_unverified":9,"n_samples":13,"n_pointer_only_licence":3}},{"rank_in_archive_order":3,"model":"GPT-3.5 Turbo (175B)","metrics":{"Accuracy (%)":"73.0"},"uses_additional_data":false,"paper_date":"2023-06-24","paper":"/paper/math-word-problem-solving-by-generating","paper_url":"https://arxiv.org/abs/2306.13899v1","paper_title":"Math Word Problem Solving by Generating Linguistic Variants of Problem Statements","code":"https://github.com/starscream-11813/variational-mathematical-reasoning","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"GPT-J (6B)","metrics":{"Accuracy (%)":"5.9"},"uses_additional_data":false,"paper_date":"2023-06-24","paper":"/paper/math-word-problem-solving-by-generating","paper_url":"https://arxiv.org/abs/2306.13899v1","paper_title":"Math Word Problem Solving by Generating Linguistic Variants of Problem Statements","code":"https://github.com/starscream-11813/variational-mathematical-reasoning","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"GPT-3 text-curie-001 (13B)","metrics":{"Accuracy (%)":"4.20"},"uses_additional_data":false,"paper_date":"2023-06-24","paper":"/paper/math-word-problem-solving-by-generating","paper_url":"https://arxiv.org/abs/2306.13899v1","paper_title":"Math Word Problem Solving by Generating Linguistic Variants of Problem Statements","code":"https://github.com/starscream-11813/variational-mathematical-reasoning","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"GPT-3 text-babbage-001 (6.7B)","metrics":{"Accuracy (%)":"3.21"},"uses_additional_data":false,"paper_date":"2023-06-24","paper":"/paper/math-word-problem-solving-by-generating","paper_url":"https://arxiv.org/abs/2306.13899v1","paper_title":"Math Word Problem Solving by Generating Linguistic Variants of Problem Statements","code":"https://github.com/starscream-11813/variational-mathematical-reasoning","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":1,"rows_with_any_sample_ran":1,"distinct_papers_with_graph_line":1,"distinct_papers_with_any_sample_ran":1,"samples_over_distinct_papers":{"n_ran":4,"n_unverified":9,"n_samples":13,"n_pointer_only_licence":3,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":4,"n_unverified":9,"n_samples":13,"n_pointer_only_licence":3,"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"}}}