{"url":"/dataset/mbpp-et","name":"MBPP-ET","full_name":null,"description_markdown":"Extension test cases of MBPP, as well as generated code.","description_withheld":null,"homepage":"https://github.com/YihongDong/Extension-Dataset-of-CodeGenEvaluation","introduced_date":"2023-01-22","introduced_date_note":null,"introduced_by":{"paper":"/paper/codescore-evaluating-code-generation-by","title":"CodeScore: Evaluating Code Generation by Learning Code Execution","first_author":null,"url":null},"license":null,"modalities":[],"tasks":[{"name":"Code Generation","url":"/task/code-generation","datasets_with_task":"/datasets/task/code-generation"}],"languages":[],"variants":["MBPP-ET"],"data_loaders":[],"num_papers_in_archive":15,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/code-generation-on-mbpp-et","task":"Code Generation","dataset_variant":"MBPP-ET","rows":2,"metrics":["Pass@1"],"first_row_in_archive_order":{"model":"EG-CFG (DeepSeek-V3-0324)","paper":"/paper/execution-guided-line-by-line-code-generation","metrics":{"Pass@1":"73.0"},"code_links":[{"title":"boazlavon/eg_cfg","url":"https://github.com/boazlavon/eg_cfg"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/execution-guided-line-by-line-code-generation","title":"Execution Guided Line-by-Line Code Generation","date":"2025-06-12","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/planning-driven-programming-a-large-language","title":"Planning-Driven Programming: A Large Language Model Programming Workflow","date":"2024-11-21","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":9,"samples_ran":0,"samples_unverified":9,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":1,"samples_harvested":9,"samples_ran":0,"samples_unverified":9,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":1,"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."}