{"url":"/dataset/asymob","name":"ASyMOB","full_name":"ASyMOB: Algebraic Symbolic Mathematical Operations Benchmark","description_markdown":"ASyMOB (pronounced Asimov, in tribute to the renowned author), is a novel assessment framework focused exclusively on symbolic manipulation, featuring 17,092 unique math challenges, organized by similarity and complexity. ASyMOB enables analysis of LLM failure root-causes and generalization capabilities by comparing performance in problems that differ by simple numerical or symbolic \"perturbations\".","description_withheld":null,"homepage":"https://huggingface.co/datasets/Shalyt/ASyMOB-Algebraic_Symbolic_Mathematical_Operations_Benchmark","introduced_date":"2025-04-30","introduced_date_note":null,"introduced_by":{"paper":"/paper/asymob-algebraic-symbolic-mathematical","title":"ASyMOB: Algebraic Symbolic Mathematical Operations Benchmark","first_author":"Michael Shalyt","url":null},"license":{"name":"CC BY-SA 4.0","url":"https://creativecommons.org/licenses/by-sa/4.0/"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Mathematical Reasoning","url":"/task/mathematical-reasoning","datasets_with_task":"/datasets/task/mathematical-reasoning"},{"name":"College Mathematics","url":"/task/college-mathematics","datasets_with_task":"/datasets/task/college-mathematics"},{"name":"Mathematical Problem-Solving","url":"/task/mathematical-problem-solving","datasets_with_task":"/datasets/task/mathematical-problem-solving"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["ASyMOB"],"data_loaders":[],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"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."}