{"url":"/dataset/prm800k","name":"PRM800K","full_name":null,"description_markdown":"**PRM800K** is a process supervision dataset containing 800,000 step-level correctness labels for model-generated solutions to problems from the MATH dataset.\r\n\r\nSource: [PRM800K: A Process Supervision Dataset | GitHub Repo](https://github.com/openai/prm800k)\r\n\r\nImage Source: [PRM800K: A Process Supervision Dataset | GitHub Repo](https://github.com/openai/prm800k)","description_withheld":null,"homepage":"https://github.com/openai/prm800k","introduced_date":"2023-05-31","introduced_date_note":null,"introduced_by":{"paper":"/paper/let-s-verify-step-by-step-1","title":"Let's Verify Step by Step","first_author":"Hunter Lightman","url":null},"license":{"name":"MIT License","url":"https://github.com/openai/prm800k/blob/main/LICENSE"},"modalities":[],"tasks":[{"name":"Reinforcement Learning (RL)","url":"/task/reinforcement-learning-1","datasets_with_task":"/datasets/task/reinforcement-learning-1"}],"languages":[],"variants":["PRM800K"],"data_loaders":[],"num_papers_in_archive":53,"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."}