{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/prmbench-a-fine-grained-and-challenging","title":"PRMBench: A Fine-grained and Challenging Benchmark for Process-Level Reward Models","arxiv_id":"2501.03124","date":"2025-01-06","proceeding":null,"authors":["Mingyang Song","Zhaochen Su","Xiaoye Qu","Jiawei Zhou","Yu Cheng"],"abstract":"Process-level Reward Models (PRMs) are crucial for complex reasoning and decision-making tasks, where each intermediate step plays an important role in the reasoning process. Since language models are prone to various types of errors during the reasoning process, PRMs are required to possess nuanced capabilities for detecting various implicit error types in real-world scenarios. However, current benchmarks primarily focus on step correctness, failing to evaluate PRMs' performance systematically. To address this gap, we introduce PRMBench, a process-level benchmark specifically designed to assess the fine-grained error detection capabilities of PRMs. PRMBench comprises 6,216 carefully designed problems and 83,456 step-level labels, evaluating models across multiple dimensions, including simplicity, soundness, and sensitivity. In our experiments on 15 models, spanning both open-source PRMs and closed-source large language models prompted as critic models, we uncover significant weaknesses in current PRMs. These findings underscore the challenges inherent in process-level evaluation and highlight key directions for future research. We hope PRMBench can be a robust bench for advancing research on PRM evaluation and development.","url_abs":"https://arxiv.org/abs/2501.03124v2","url_pdf":"https://arxiv.org/pdf/2501.03124v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"prmbench-a-fine-grained-and-challenging","repo_url":"https://github.com/ssmisya/PRMBench","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"decision-making","task_name":"Decision Making"}],"methods":[{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[{"slug":"prmbench-preview","name":"PRMBench_Preview","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2501.03124","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.03124"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ssmisya/PRMBench","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":5},"by_repo_kind":{"official":{"samples":5,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"c3fbcd180889da35","entry":"eval_maj_of_n","repo":"ssmisya/PRMBench","repo_kind":"official","path":"mr_eval/tasks/prmbench_bon/task.py","file_url":"https://github.com/ssmisya/PRMBench/blob/HEAD/mr_eval/tasks/prmbench_bon/task.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c3fbcd180889da35"}},{"code_sha256_prefix":"79d235c075fccb12","entry":"eval_maj_of_n","repo":"ssmisya/PRMBench","repo_kind":"official","path":"mr_eval/tasks/prmbench_bon_subset50/task.py","file_url":"https://github.com/ssmisya/PRMBench/blob/HEAD/mr_eval/tasks/prmbench_bon_subset50/task.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"79d235c075fccb12"}},{"code_sha256_prefix":"5303747ae5ef3847","entry":"eval_on_hallucination_step","repo":"ssmisya/PRMBench","repo_kind":"official","path":"mr_eval/tasks/prmbench_stem/task.py","file_url":"https://github.com/ssmisya/PRMBench/blob/HEAD/mr_eval/tasks/prmbench_stem/task.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5303747ae5ef3847"}},{"code_sha256_prefix":"ae4a5f14c32e1ad6","entry":"eval_pass_at_n","repo":"ssmisya/PRMBench","repo_kind":"official","path":"mr_eval/tasks/prmbench_bon/task.py","file_url":"https://github.com/ssmisya/PRMBench/blob/HEAD/mr_eval/tasks/prmbench_bon/task.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ae4a5f14c32e1ad6"}},{"code_sha256_prefix":"a3c529098d61a8e9","entry":"eval_pass_at_n","repo":"ssmisya/PRMBench","repo_kind":"official","path":"mr_eval/tasks/prmbench_bon_subset50/task.py","file_url":"https://github.com/ssmisya/PRMBench/blob/HEAD/mr_eval/tasks/prmbench_bon_subset50/task.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a3c529098d61a8e9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}