{"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/vlrmbench-a-comprehensive-and-challenging","title":"VLRMBench: A Comprehensive and Challenging Benchmark for Vision-Language Reward Models","arxiv_id":"2503.07478","date":"2025-03-10","proceeding":null,"authors":["Jiacheng Ruan","Wenzhen Yuan","Xian Gao","Ye Guo","Daoxin Zhang","Zhe Xu","Yao Hu","Ting Liu","Yuzhuo Fu"],"abstract":"Although large visual-language models (LVLMs) have demonstrated strong performance in multimodal tasks, errors may occasionally arise due to biases during the reasoning process. Recently, reward models (RMs) have become increasingly pivotal in the reasoning process. Specifically, process RMs evaluate each reasoning step, outcome RMs focus on the assessment of reasoning results, and critique RMs perform error analysis on the entire reasoning process, followed by corrections. However, existing benchmarks for vision-language RMs (VLRMs) typically assess only a single aspect of their capabilities (e.g., distinguishing between two answers), thus limiting the all-round evaluation and restricting the development of RMs in the visual-language domain. To address this gap, we propose a comprehensive and challenging benchmark, dubbed as VLRMBench, encompassing 12,634 questions. VLRMBench is constructed based on three distinct types of datasets, covering mathematical reasoning, hallucination understanding, and multi-image understanding. We design 12 tasks across three major categories, focusing on evaluating VLRMs in the aspects of process understanding, outcome judgment, and critique generation. Extensive experiments are conducted on 21 open-source models and 5 advanced closed-source models, highlighting the challenges posed by VLRMBench. For instance, in the `Forecasting Future', a binary classification task, the advanced GPT-4o achieves only a 76.0% accuracy. Additionally, we perform comprehensive analytical studies, offering valuable insights for the future development of VLRMs. We anticipate that VLRMBench will serve as a pivotal benchmark in advancing VLRMs. Code and datasets will be available at https://github.com/JCruan519/VLRMBench.","url_abs":"https://arxiv.org/abs/2503.07478v1","url_pdf":"https://arxiv.org/pdf/2503.07478v1.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":"vlrmbench-a-comprehensive-and-challenging","repo_url":"https://github.com/jcruan519/vlrmbench","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"binary-classification","task_name":"Binary Classification"},{"task_slug":"hallucination","task_name":"Hallucination"},{"task_slug":"mathematical-reasoning","task_name":"Mathematical Reasoning"}],"methods":[{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2503.07478","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.07478"}},"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":"deterministic:regex_extraction","url":"https://github.com/JCruan519/VLRMBench","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":"ccaa4228cc5e8c9b","entry":"format_model_answer_tolist","repo":"JCruan519/VLRMBench","repo_kind":"official","path":"model_eval/utils.py","file_url":"https://github.com/JCruan519/VLRMBench/blob/HEAD/model_eval/utils.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":"ccaa4228cc5e8c9b"}},{"code_sha256_prefix":"bcb31c34dc5b1f06","entry":"format_ms_ec_era_model_answer_tolist","repo":"JCruan519/VLRMBench","repo_kind":"official","path":"model_eval/utils.py","file_url":"https://github.com/JCruan519/VLRMBench/blob/HEAD/model_eval/utils.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":"bcb31c34dc5b1f06"}},{"code_sha256_prefix":"b7101a2fbe7c7e0a","entry":"get_F1Score","repo":"JCruan519/VLRMBench","repo_kind":"official","path":"model_eval/utils.py","file_url":"https://github.com/JCruan519/VLRMBench/blob/HEAD/model_eval/utils.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":"b7101a2fbe7c7e0a"}},{"code_sha256_prefix":"88bd22cd034d3c8d","entry":"process_jsonl","repo":"JCruan519/VLRMBench","repo_kind":"official","path":"model_eval/get_ec_era_eval_res_after_judger.py","file_url":"https://github.com/JCruan519/VLRMBench/blob/HEAD/model_eval/get_ec_era_eval_res_after_judger.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":"88bd22cd034d3c8d"}},{"code_sha256_prefix":"c8c9e76030938ca7","entry":"process_jsonl","repo":"JCruan519/VLRMBench","repo_kind":"official","path":"model_eval/get_fores_eval_res.py","file_url":"https://github.com/JCruan519/VLRMBench/blob/HEAD/model_eval/get_fores_eval_res.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":"c8c9e76030938ca7"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}