{"url":"/dataset/scibench","name":"SciBench","full_name":null,"description_markdown":"**SciBench** is a large-scale scientific problem-solving benchmark suite that aims to systematically examine the reasoning capabilities required for complex scientific problem solving. SciBench contains two carefully curated datasets: an open set featuring a range of collegiate-level scientific problems drawn from mathematics, chemistry, and physics textbooks, and a closed set comprising problems from undergraduate-level exams in computer science and mathematics.","description_withheld":null,"homepage":"https://github.com/mandyyyyii/scibench","introduced_date":"2023-07-20","introduced_date_note":null,"introduced_by":{"paper":"/paper/scibench-evaluating-college-level-scientific","title":"SciBench: Evaluating College-Level Scientific Problem-Solving Abilities of Large Language Models","first_author":"Xiaoxuan Wang","url":null},"license":{"name":"MIT License","url":"https://github.com/mandyyyyii/scibench/blob/main/LICENSE"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[],"languages":[],"variants":["SciBench"],"data_loaders":[],"num_papers_in_archive":33,"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."}