{"url":"/dataset/ds-1000","name":"DS-1000","full_name":null,"description_markdown":"**DS-1000** is a code generation benchmark with a thousand data science questions spanning seven Python libraries that (1) reflects diverse, realistic, and practical use cases, (2) has a reliable metric, (3) defends against memorization by perturbing questions.\r\n\r\nSource: [DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation](https://arxiv.org/abs/2211.11501)\r\n\r\nImage Source: [https://arxiv.org/abs/2211.11501](https://arxiv.org/abs/2211.11501)","description_withheld":null,"homepage":"https://ds1000-code-gen.github.io/","introduced_date":"2022-11-18","introduced_date_note":null,"introduced_by":{"paper":"/paper/ds-1000-a-natural-and-reliable-benchmark-for","title":"DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation","first_author":"Yuhang Lai","url":null},"license":{"name":"Apache-2.0 license","url":"https://github.com/HKUNLP/DS-1000/blob/main/LICENSE"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Code Generation","url":"/task/code-generation","datasets_with_task":"/datasets/task/code-generation"},{"name":"Memorization","url":"/task/memorization","datasets_with_task":"/datasets/task/memorization"}],"languages":[],"variants":["DS-1000"],"data_loaders":[],"num_papers_in_archive":72,"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."}