{"url":"/dataset/gsm-plus","name":"GSM-Plus","full_name":null,"description_markdown":"By perturbing the widely used GSM8K dataset, an adversarial dataset for grade-school math called GSM-Plus is created. Motivated by the capability taxonomy for solving math problems mentioned in Polya's principles, this paper identifies 5 perspectives to guide the development of GSM-Plus:\r\n\r\n* Numerical Variation refers to altering the numerical data or its types, including 3 subcategories: Numerical Substitution, Digit Expansion, and Integer-decimal-fraction Conversion.\r\n* Arithmetic Variation refers to reversing or introducing additional operations (e.g., addition, subtraction, multiplication, and division) to math problems, including 2 subcategories: Adding Operation and Reversing Operation.\r\n* Problem Understanding refers to rephrasing the text description of the math problems.\r\n* Distractor Insertion refers to inserting topic-related but useless sentences to the problems.\r\n* Critical Thinking focuses on question or doubt ability when the question lacks necessary statements.\r\n\r\nGSM-Plus can be used to evaluate the robustness of current LLMs in mathematical reasoning.","description_withheld":null,"homepage":"https://qtli.github.io/GSM-Plus/","introduced_date":"2024-02-29","introduced_date_note":null,"introduced_by":{"paper":"/paper/gsm-plus-a-comprehensive-benchmark-for","title":"GSM-Plus: A Comprehensive Benchmark for Evaluating the Robustness of LLMs as Mathematical Problem Solvers","first_author":"Qintong Li","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Logical Reasoning","url":"/task/logical-reasoning","datasets_with_task":"/datasets/task/logical-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"},{"name":"Math","url":"/task/math","datasets_with_task":"/datasets/task/math"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["GSM-Plus"],"data_loaders":[],"num_papers_in_archive":17,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/math-word-problem-solving-on-gsm-plus","task":"Math Word Problem Solving","dataset_variant":"GSM-Plus","rows":1,"metrics":["1:1 Accuracy"],"first_row_in_archive_order":{"model":"GPT-4","paper":"/paper/gsm-plus-a-comprehensive-benchmark-for","metrics":{"1:1 Accuracy":"85.6"},"code_links":[{"title":"qtli/gsm-plus","url":"https://github.com/qtli/gsm-plus"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/gsm-plus-a-comprehensive-benchmark-for","title":"GSM-Plus: A Comprehensive Benchmark for Evaluating the Robustness of LLMs as Mathematical Problem Solvers","date":"2024-02-29","rows_on_this_dataset":1,"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."}