{"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/mmmu-pro-a-more-robust-multi-discipline","title":"MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark","arxiv_id":"2409.02813","date":"2024-09-04","proceeding":null,"authors":["Xiang Yue","Tianyu Zheng","Yuansheng Ni","YuBo Wang","Kai Zhang","Shengbang Tong","Yuxuan Sun","Botao Yu","Ge Zhang","Huan Sun","Yu Su","Wenhu Chen","Graham Neubig"],"abstract":"This paper introduces MMMU-Pro, a robust version of the Massive Multi-discipline Multimodal Understanding and Reasoning (MMMU) benchmark. MMMU-Pro rigorously assesses multimodal models' true understanding and reasoning capabilities through a three-step process based on MMMU: (1) filtering out questions answerable by text-only models, (2) augmenting candidate options, and (3) introducing a vision-only input setting where questions are embedded within images. This setting challenges AI to truly \"see\" and \"read\" simultaneously, testing a fundamental human cognitive skill of seamlessly integrating visual and textual information. Results show that model performance is substantially lower on MMMU-Pro than on MMMU, ranging from 16.8% to 26.9% across models. We explore the impact of OCR prompts and Chain of Thought (CoT) reasoning, finding that OCR prompts have minimal effect while CoT generally improves performance. MMMU-Pro provides a more rigorous evaluation tool, closely mimicking real-world scenarios and offering valuable directions for future research in multimodal AI.","url_abs":"https://arxiv.org/abs/2409.02813v2","url_pdf":"https://arxiv.org/pdf/2409.02813v2.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":"mmmu-pro-a-more-robust-multi-discipline","repo_url":"https://github.com/MMMU-Benchmark/MMMU","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"mmmu-pro-a-more-robust-multi-discipline","repo_url":"https://github.com/opendatalab/pm4bench","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"optical-character-recognition","task_name":"Optical Character Recognition (OCR)"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2409.02813","atlas_url":"https://app.syntology.ai/?focus=2409.02813","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.02813"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/opendatalab/pm4bench","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MMMU-Benchmark/MMMU","reach":null}],"summary":{"ran":11,"unverified":1},"by_repo_kind":{"listed":{"samples":12,"ran":11,"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":"cc5c4cade54886a7","entry":"aggregate_scores","repo":"opendatalab/pm4bench","repo_kind":"listed","path":"src/pm4bench/miqa.py","file_url":"https://github.com/opendatalab/pm4bench/blob/HEAD/src/pm4bench/miqa.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":"cc5c4cade54886a7"}},{"code_sha256_prefix":"40019c900986263c","entry":"compare_gt","repo":"opendatalab/pm4bench","repo_kind":"listed","path":"src/pm4bench/mgui/render.py","file_url":"https://github.com/opendatalab/pm4bench/blob/HEAD/src/pm4bench/mgui/render.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":"40019c900986263c"}},{"code_sha256_prefix":"e929aabca68bb917","entry":"extract_answer_letter","repo":"opendatalab/pm4bench","repo_kind":"listed","path":"src/pm4bench/metrics.py","file_url":"https://github.com/opendatalab/pm4bench/blob/HEAD/src/pm4bench/metrics.py","link_basis":"harvester_set","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":"e929aabca68bb917"}},{"code_sha256_prefix":"6ec5c1760b10f4d4","entry":"extract_scores","repo":"opendatalab/pm4bench","repo_kind":"listed","path":"src/pm4bench/miqa.py","file_url":"https://github.com/opendatalab/pm4bench/blob/HEAD/src/pm4bench/miqa.py","link_basis":"harvester_set","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":"6ec5c1760b10f4d4"}},{"code_sha256_prefix":"c17d2901ecfbf4cb","entry":"format_reward","repo":"opendatalab/pm4bench","repo_kind":"listed","path":"src/pm4bench/qgo/reward.py","file_url":"https://github.com/opendatalab/pm4bench/blob/HEAD/src/pm4bench/qgo/reward.py","link_basis":"harvester_set","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":"c17d2901ecfbf4cb"}},{"code_sha256_prefix":"e6b5d81f514b3ebb","entry":"load_predictions","repo":"opendatalab/pm4bench","repo_kind":"listed","path":"src/pm4bench/io.py","file_url":"https://github.com/opendatalab/pm4bench/blob/HEAD/src/pm4bench/io.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":"e6b5d81f514b3ebb"}},{"code_sha256_prefix":"cd1307d13954b765","entry":"mdur_correct","repo":"opendatalab/pm4bench","repo_kind":"listed","path":"src/pm4bench/metrics.py","file_url":"https://github.com/opendatalab/pm4bench/blob/HEAD/src/pm4bench/metrics.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":"cd1307d13954b765"}},{"code_sha256_prefix":"3ad8b96dec73d6f2","entry":"normalize_historical_text","repo":"opendatalab/pm4bench","repo_kind":"listed","path":"src/pm4bench/mgui/render.py","file_url":"https://github.com/opendatalab/pm4bench/blob/HEAD/src/pm4bench/mgui/render.py","link_basis":"harvester_set","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":"3ad8b96dec73d6f2"}},{"code_sha256_prefix":"abd00a80d4ff626d","entry":"normalize_text","repo":"opendatalab/pm4bench","repo_kind":"listed","path":"src/pm4bench/metrics.py","file_url":"https://github.com/opendatalab/pm4bench/blob/HEAD/src/pm4bench/metrics.py","link_basis":"harvester_set","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":"abd00a80d4ff626d"}},{"code_sha256_prefix":"cbd1256114d18a72","entry":"record_key","repo":"opendatalab/pm4bench","repo_kind":"listed","path":"src/pm4bench/io.py","file_url":"https://github.com/opendatalab/pm4bench/blob/HEAD/src/pm4bench/io.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":"cbd1256114d18a72"}},{"code_sha256_prefix":"791bca2fe997c4f0","entry":"resolve_asset","repo":"opendatalab/pm4bench","repo_kind":"listed","path":"src/pm4bench/io.py","file_url":"https://github.com/opendatalab/pm4bench/blob/HEAD/src/pm4bench/io.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":"791bca2fe997c4f0"}},{"code_sha256_prefix":"9a98d066a6e55e2e","entry":"render_mgui","repo":"opendatalab/pm4bench","repo_kind":"listed","path":"src/pm4bench/mgui/render.py","file_url":"https://github.com/opendatalab/pm4bench/blob/HEAD/src/pm4bench/mgui/render.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":"9a98d066a6e55e2e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}