{"url":"/dataset/swe-bench","name":"SWE-bench-lite","full_name":null,"description_markdown":"SWE-bench is a dataset that tests systems’ ability to solve GitHub issues automatically. The dataset collects 2,294 Issue-Pull Request pairs from 12 popular Python repositories. Evaluation is performed by unit test verification using post-PR behavior as the reference solution.\r\n\r\nSWE-bench lite is a subset of SWE-bench, which is curated to make evaluation less costly and more accessible. SWE-bench lite  comprises 300 instances that have been sampled to be more self-contained, with a focus on evaluating functional bug fixes.","description_withheld":null,"homepage":"https://www.swebench.com","introduced_date":"2023-10-10","introduced_date_note":null,"introduced_by":{"paper":"/paper/swe-bench-can-language-models-resolve-real","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","first_author":"Carlos E. Jimenez","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Bug fixing","url":"/task/bug-fixing","datasets_with_task":"/datasets/task/bug-fixing"}],"languages":[],"variants":["SWE-bench-lite"],"data_loaders":[],"num_papers_in_archive":18,"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."}