{"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/judgebench-a-benchmark-for-evaluating-llm","title":"JudgeBench: A Benchmark for Evaluating LLM-based Judges","arxiv_id":"2410.12784","date":"2024-10-16","proceeding":null,"authors":["Sijun Tan","Siyuan Zhuang","Kyle Montgomery","William Y. Tang","Alejandro Cuadron","Chenguang Wang","Raluca Ada Popa","Ion Stoica"],"abstract":"LLM-based judges have emerged as a scalable alternative to human evaluation and are increasingly used to assess, compare, and improve models. However, the reliability of LLM-based judges themselves is rarely scrutinized. As LLMs become more advanced, their responses grow more sophisticated, requiring stronger judges to evaluate them. Existing benchmarks primarily focus on a judge's alignment with human preferences, but often fail to account for more challenging tasks where crowdsourced human preference is a poor indicator of factual and logical correctness. To address this, we propose a novel evaluation framework to objectively evaluate LLM-based judges. Based on this framework, we propose JudgeBench, a benchmark for evaluating LLM-based judges on challenging response pairs spanning knowledge, reasoning, math, and coding. JudgeBench leverages a novel pipeline for converting existing difficult datasets into challenging response pairs with preference labels reflecting objective correctness. Our comprehensive evaluation on a collection of prompted judges, fine-tuned judges, multi-agent judges, and reward models shows that JudgeBench poses a significantly greater challenge than previous benchmarks, with many strong models (e.g., GPT-4o) performing just slightly better than random guessing. Overall, JudgeBench offers a reliable platform for assessing increasingly advanced LLM-based judges. Data and code are available at https://github.com/ScalerLab/JudgeBench .","url_abs":"https://arxiv.org/abs/2410.12784v1","url_pdf":"https://arxiv.org/pdf/2410.12784v1.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":"judgebench-a-benchmark-for-evaluating-llm","repo_url":"https://github.com/ScalerLab/JudgeBench","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"math","task_name":"Math"}],"methods":[{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2410.12784","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.12784"}},"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/ScalerLab/JudgeBench","reach":{"status":"ok"}}],"summary":{"ran":3,"unverified":1},"by_repo_kind":{"official":{"samples":4,"ran":3,"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":4,"samples":[{"code_sha256_prefix":"2bb16d114379b0a9","entry":"compute_final_metrics","repo":"ScalerLab/JudgeBench","repo_kind":"official","path":"utils/metrics.py","file_url":"https://github.com/ScalerLab/JudgeBench/blob/HEAD/utils/metrics.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2bb16d114379b0a9"}},{"code_sha256_prefix":"e713d200f87c80bc","entry":"flip_judgment","repo":"ScalerLab/JudgeBench","repo_kind":"official","path":"utils/metrics.py","file_url":"https://github.com/ScalerLab/JudgeBench/blob/HEAD/utils/metrics.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e713d200f87c80bc"}},{"code_sha256_prefix":"195bbcd43396ba20","entry":"read_jsonl","repo":"ScalerLab/JudgeBench","repo_kind":"official","path":"utils/file_operations.py","file_url":"https://github.com/ScalerLab/JudgeBench/blob/HEAD/utils/file_operations.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"195bbcd43396ba20"}},{"code_sha256_prefix":"1f8fad089086e873","entry":"render_template","repo":"ScalerLab/JudgeBench","repo_kind":"official","path":"utils/prompts.py","file_url":"https://github.com/ScalerLab/JudgeBench/blob/HEAD/utils/prompts.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1f8fad089086e873"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}