{"url":"/dataset/prmbench-preview","name":"PRMBench_Preview","full_name":null,"description_markdown":"This is the official dataset for PRMBench. PRMBench is a benchmark dataset for evaluating process-level reward models (PRMs). It consists of 6,216 data instances, each containing a question, a solution process, and a modified process with errors. The dataset is designed to evaluate the ability of PRMs to identify fine-grained error types in the solution process. The dataset is annotated with error types and reasons for the errors, providing a comprehensive evaluation of PRMs.","description_withheld":null,"homepage":"https://prmbench.github.io/","introduced_date":"2025-01-06","introduced_date_note":null,"introduced_by":{"paper":"/paper/prmbench-a-fine-grained-and-challenging","title":"PRMBench: A Fine-grained and Challenging Benchmark for Process-Level Reward Models","first_author":"Mingyang Song","url":null},"license":{"name":"Apache 2.0","url":null},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["PRMBench_Preview"],"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."}