{"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/wildbench-benchmarking-llms-with-challenging","title":"WildBench: Benchmarking LLMs with Challenging Tasks from Real Users in the Wild","arxiv_id":"2406.04770","date":"2024-06-07","proceeding":null,"authors":["Bill Yuchen Lin","Yuntian Deng","Khyathi Chandu","Faeze Brahman","Abhilasha Ravichander","Valentina Pyatkin","Nouha Dziri","Ronan Le Bras","Yejin Choi"],"abstract":"We introduce WildBench, an automated evaluation framework designed to benchmark large language models (LLMs) using challenging, real-world user queries. WildBench consists of 1,024 tasks carefully selected from over one million human-chatbot conversation logs. For automated evaluation with WildBench, we have developed two metrics, WB-Reward and WB-Score, which are computable using advanced LLMs such as GPT-4-turbo. WildBench evaluation uses task-specific checklists to evaluate model outputs systematically and provides structured explanations that justify the scores and comparisons, resulting in more reliable and interpretable automatic judgments. WB-Reward employs fine-grained pairwise comparisons between model responses, generating five potential outcomes: much better, slightly better, slightly worse, much worse, or a tie. Unlike previous evaluations that employed a single baseline model, we selected three baseline models at varying performance levels to ensure a comprehensive pairwise evaluation. Additionally, we propose a simple method to mitigate length bias, by converting outcomes of ``slightly better/worse'' to ``tie'' if the winner response exceeds the loser one by more than $K$ characters. WB-Score evaluates the quality of model outputs individually, making it a fast and cost-efficient evaluation metric. WildBench results demonstrate a strong correlation with the human-voted Elo ratings from Chatbot Arena on hard tasks. Specifically, WB-Reward achieves a Pearson correlation of 0.98 with top-ranking models. Additionally, WB-Score reaches 0.95, surpassing both ArenaHard's 0.91 and AlpacaEval2.0's 0.89 for length-controlled win rates, as well as the 0.87 for regular win rates.","url_abs":"https://arxiv.org/abs/2406.04770v2","url_pdf":"https://arxiv.org/pdf/2406.04770v2.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":"wildbench-benchmarking-llms-with-challenging","repo_url":"https://github.com/allenai/wildbench","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"benchmarking","task_name":"Benchmarking"},{"task_slug":"chatbot","task_name":"Chatbot"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2406.04770","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.04770"}},"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/allenai/wildbench","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":5,"unverified":4},"by_repo_kind":{"official":{"samples":9,"ran":5,"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":"bab78e56b3db5391","entry":"clear_output","repo":"allenai/wildbench","repo_kind":"official","path":"src/unified_utils.py","file_url":"https://github.com/allenai/wildbench/blob/HEAD/src/unified_utils.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bab78e56b3db5391"}},{"code_sha256_prefix":"f835da725b875459","entry":"compute_single_round","repo":"allenai/wildbench","repo_kind":"official","path":"leaderboard/wb_elo.py","file_url":"https://github.com/allenai/wildbench/blob/HEAD/leaderboard/wb_elo.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f835da725b875459"}},{"code_sha256_prefix":"e6e6e2172255fa63","entry":"formatter","repo":"allenai/wildbench","repo_kind":"official","path":"leaderboard/data_utils.py","file_url":"https://github.com/allenai/wildbench/blob/HEAD/leaderboard/data_utils.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e6e6e2172255fa63"}},{"code_sha256_prefix":"ad6c9f4f8fa20c1c","entry":"get_all_votes","repo":"allenai/wildbench","repo_kind":"official","path":"leaderboard/wb_elo.py","file_url":"https://github.com/allenai/wildbench/blob/HEAD/leaderboard/wb_elo.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ad6c9f4f8fa20c1c"}},{"code_sha256_prefix":"8526e7d6eb6a6bd3","entry":"sanitize_args","repo":"allenai/wildbench","repo_kind":"official","path":"src/unified_infer.py","file_url":"https://github.com/allenai/wildbench/blob/HEAD/src/unified_infer.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8526e7d6eb6a6bd3"}},{"code_sha256_prefix":"55f88619b89a0830","entry":"compute_elo_based_on_votes","repo":"allenai/wildbench","repo_kind":"official","path":"leaderboard/wb_elo.py","file_url":"https://github.com/allenai/wildbench/blob/HEAD/leaderboard/wb_elo.py","link_basis":"plan_row","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":"55f88619b89a0830"}},{"code_sha256_prefix":"2e17447aecaa3b2e","entry":"get_conv_template","repo":"allenai/wildbench","repo_kind":"official","path":"src/fastchat_conversation.py","file_url":"https://github.com/allenai/wildbench/blob/HEAD/src/fastchat_conversation.py","link_basis":"plan_row","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":"2e17447aecaa3b2e"}},{"code_sha256_prefix":"6228967ca49853d1","entry":"load_infer_results","repo":"allenai/wildbench","repo_kind":"official","path":"leaderboard/data_utils.py","file_url":"https://github.com/allenai/wildbench/blob/HEAD/leaderboard/data_utils.py","link_basis":"first_harvest_node","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":"6228967ca49853d1"}},{"code_sha256_prefix":"3ea3d1a085a300ea","entry":"sample_an_eval_result","repo":"allenai/wildbench","repo_kind":"official","path":"leaderboard/data_utils.py","file_url":"https://github.com/allenai/wildbench/blob/HEAD/leaderboard/data_utils.py","link_basis":"first_harvest_node","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":"3ea3d1a085a300ea"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}