{"url":"/dataset/fixeval","name":"FixEval","full_name":"FixEval","description_markdown":"We introduce FixEval , a dataset for competitive programming bug fixing along with a comprehensive test suite and show the necessity of execution based evaluation compared to suboptimal match based evaluation metrics like BLEU, CodeBLEU, Syntax Match, Exact Match etc.","description_withheld":null,"homepage":"https://drive.google.com/drive/folders/1dzuHuouuWzlFCy1CMj9DYG9JGraEay27","introduced_date":"2022-06-15","introduced_date_note":null,"introduced_by":{"paper":"/paper/fixeval-execution-based-evaluation-of-program","title":"FixEval: Execution-based Evaluation of Program Fixes for Programming Problems","first_author":"Md Mahim Anjum Haque","url":null},"license":{"name":"MIT","url":"https://github.com/mahimanzum/FixEval"},"modalities":[],"tasks":[{"name":"Code Translation","url":"/task/code-translation","datasets_with_task":"/datasets/task/code-translation"},{"name":"Code Repair","url":"/task/code-repair","datasets_with_task":"/datasets/task/code-repair"},{"name":"Code Classification","url":"/task/code-classification","datasets_with_task":"/datasets/task/code-classification"}],"languages":[],"variants":["FixEval"],"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."}