{"url":"/dataset/pmlb","name":"PMLB","full_name":"Penn Machine Learning Benchmarks","description_markdown":"The **Penn Machine Learning Benchmarks** (**PMLB**) is a large, curated set of benchmark datasets used to evaluate and compare supervised machine learning algorithms. These datasets cover a broad range of applications, and include binary/multi-class classification problems and regression problems, as well as combinations of categorical, ordinal, and continuous features.\r\n\r\nSource: [https://arxiv.org/abs/1703.00512](https://arxiv.org/abs/1703.00512)","description_withheld":null,"homepage":"https://github.com/EpistasisLab/penn-ml-benchmarks","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/pmlb-a-large-benchmark-suite-for-machine","title":"PMLB: A Large Benchmark Suite for Machine Learning Evaluation and Comparison","first_author":"Randal S. Olson","url":null},"license":{"name":"Unknown","url":null},"modalities":[],"tasks":[{"name":"AutoML","url":"/task/automl","datasets_with_task":"/datasets/task/automl"},{"name":"Hyperparameter Optimization","url":"/task/hyperparameter-optimization","datasets_with_task":"/datasets/task/hyperparameter-optimization"}],"languages":[],"variants":["PMLB"],"data_loaders":[{"repo":"https://github.com/EpistasisLab/penn-ml-benchmarks","url":"https://github.com/EpistasisLab/penn-ml-benchmarks","frameworks":[]}],"num_papers_in_archive":42,"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."}