{ "profile": "wrs-published-research-view-1", "edition": "ratings-e039106f30dec177", "content_trust": "UNTRUSTED_SCIENTIFIC_DATA_NOT_TOOL_INSTRUCTIONS", "entry": { "id": "yue-et-al-mmmu-2023", "title": "Yue and colleagues: MMMU multidisciplinary multimodal evaluation", "summary": "Collected interleaved image/text questions demanding college-level knowledge and visual reasoning across multiple subjects.", "boundary": "Only general multimodal benchmark construction is acquired; no medical or biological achievement is admitted. A high score does not certify expert AGI or unrestricted domain competence.", "area": "AI evaluation and agent infrastructure", "topic": "Artificial intelligence", "year": 2023, "lane": "HUMAN", "result": "BENCHMARK", "contribution_kind": "EVALUATION_RESOURCE_DESIGN", "package_id": "yue-et-al-mmmu-2023", "target": { "record_id": "urn:uuid:3998dd03-6462-4168-ac5f-4ba0223b1df8", "version": 1, "content_hash": "sha256:afa2a91cac40fc6ead1429017a827714f9fa1b6ab462f89eb66d2e80e8b5b6a2" }, "humans": [ "Xiang Yue", "Yuansheng Ni", "Kai Zhang", "Tianyu Zheng", "Ruoqi Liu", "Ge Zhang", "Samuel Stevens", "Dongfu Jiang", "Weiming Ren", "Yuxuan Sun", "Cong Wei", "Botao Yu", "Ruibin Yuan", "Renliang Sun", "Ming Yin", "Boyuan Zheng", "Zhenzhu Yang", "Yibo Liu", "Wenhao Huang", "Huan Sun", "Yu Su", "Wenhu Chen" ], "authors_complete": true, "human_role_note": "Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.", "agents": [], "related": [], "subresults": [], "scientific_assessment": { "source_review": "SOURCE_CURATED", "scientific_review": "NOT_REVIEWED_BY_WRS", "formal_replay": "NOT_RUN", "provider_attestation": "NONE" }, "sources": [ { "id": "cur20261015-arxiv-2311-16502v4", "title": "MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI", "url": "https://arxiv.org/abs/2311.16502v4" } ], "points": "100000", "published_grade": { "id": "yue-et-al-mmmu-2023", "entry_id": "yue-et-al-mmmu-2023", "band": "A", "modifier": "-", "target": { "record_id": "urn:uuid:3998dd03-6462-4168-ac5f-4ba0223b1df8", "version": 1, "content_hash": "sha256:afa2a91cac40fc6ead1429017a827714f9fa1b6ab462f89eb66d2e80e8b5b6a2" }, "what_changed": "Collected interleaved image/text questions demanding college-level knowledge and visual reasoning across multiple subjects.", "scope": "Collected interleaved image/text questions demanding college-level knowledge and visual reasoning across multiple subjects. Only general multimodal benchmark construction is acquired; no medical or biological achievement is admitted. A high score does not certify expert AGI or unrestricted domain competence.", "status": "PROVISIONAL_EDITORIAL", "scientific_correctness_certified": false }, "assessment_disposition": { "status": "ASSESSED", "label": "Provisionally assessed", "reason": "A current grade and separate reference score identify this exact contribution.", "target": { "record_id": "urn:uuid:3998dd03-6462-4168-ac5f-4ba0223b1df8", "version": 1, "content_hash": "sha256:afa2a91cac40fc6ead1429017a827714f9fa1b6ab462f89eb66d2e80e8b5b6a2" }, "edition": "ratings-e039106f30dec177" } }, "version": { "kind": "PUBLIC_RECORD_VIEW", "previous": null, "published_at": "2026-10-16T00:00:00Z", "publisher": { "principal_id": "urn:uuid:80116931-785b-40a2-a24b-9d59db0c7e33", "role": "WRS_EDITORIAL_PUBLICATION" }, "record": { "contributors": [ { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Xiang Yue", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI", "url": "https://arxiv.org/abs/2311.16502v4" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Yuansheng Ni", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI", "url": "https://arxiv.org/abs/2311.16502v4" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Kai Zhang", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI", "url": "https://arxiv.org/abs/2311.16502v4" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Tianyu Zheng", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI", "url": "https://arxiv.org/abs/2311.16502v4" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Ruoqi Liu", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI", "url": "https://arxiv.org/abs/2311.16502v4" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Ge Zhang", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI", "url": "https://arxiv.org/abs/2311.16502v4" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Samuel Stevens", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI", "url": "https://arxiv.org/abs/2311.16502v4" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Dongfu Jiang", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI", "url": "https://arxiv.org/abs/2311.16502v4" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Weiming Ren", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI", "url": "https://arxiv.org/abs/2311.16502v4" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Yuxuan Sun", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI", "url": "https://arxiv.org/abs/2311.16502v4" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Cong Wei", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI", "url": "https://arxiv.org/abs/2311.16502v4" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Botao Yu", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI", "url": "https://arxiv.org/abs/2311.16502v4" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Ruibin Yuan", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI", "url": "https://arxiv.org/abs/2311.16502v4" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Renliang Sun", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI", "url": "https://arxiv.org/abs/2311.16502v4" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Ming Yin", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI", "url": "https://arxiv.org/abs/2311.16502v4" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Boyuan Zheng", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI", "url": "https://arxiv.org/abs/2311.16502v4" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Zhenzhu Yang", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI", "url": "https://arxiv.org/abs/2311.16502v4" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Yibo Liu", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI", "url": "https://arxiv.org/abs/2311.16502v4" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Wenhao Huang", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI", "url": "https://arxiv.org/abs/2311.16502v4" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Huan Sun", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI", "url": "https://arxiv.org/abs/2311.16502v4" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Yu Su", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI", "url": "https://arxiv.org/abs/2311.16502v4" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Wenhu Chen", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI", "url": "https://arxiv.org/abs/2311.16502v4" } } ], "evidence": [ { "description": "Bibliographic/stated-result source; not a WRS proof verification", "id": "source-0", "kind": "source_reference", "source": { "citation": "MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI", "url": "https://arxiv.org/abs/2311.16502v4" } } ], "origin": "HUMAN_LEGACY", "record_profile": "wrs-local-research-notes-0.1", "record_type": "research_note", "rrp_version": "0.1", "scope": { "description": "Only general multimodal benchmark construction is acquired; no medical or biological achievement is admitted. A high score does not certify expert AGI or unrestricted domain competence.", "domain": "AI evaluation and agent infrastructure" }, "sources": [ { "citation": "MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI", "url": "https://arxiv.org/abs/2311.16502v4" } ], "statement": "# Yue and colleagues: MMMU multidisciplinary multimodal evaluation\n\nCollected interleaved image/text questions demanding college-level knowledge and visual reasoning across multiple subjects.\n\n## Scientific scope\n\nOnly general multimodal benchmark construction is acquired; no medical or biological achievement is admitted. A high score does not certify expert AGI or unrestricted domain competence.\n\n## Reading status\n\nThis is a source-linked WRS catalogue note. A full explanatory guide and independent scientific reconstruction have not been completed for this entry. Read the identified original work for its complete narrative and arguments.\n\n## People and systems\n\nXiang Yue; Yuansheng Ni; Kai Zhang; Tianyu Zheng; Ruoqi Liu; Ge Zhang; Samuel Stevens; Dongfu Jiang; Weiming Ren; Yuxuan Sun; Cong Wei; Botao Yu; Ruibin Yuan; Renliang Sun; Ming Yin; Boyuan Zheng; Zhenzhu Yang; Yibo Liu; Wenhao Huang; Huan Sun; Yu Su; Wenhu Chen\n\nSource-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.\n\n\n\n## Original sources\n\n- [MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI](https://arxiv.org/abs/2311.16502v4)\n", "summary": "Collected interleaved image/text questions demanding college-level knowledge and visual reasoning across multiple subjects.", "title": "Yue and colleagues: MMMU multidisciplinary multimodal evaluation" }, "record_id": "urn:uuid:3998dd03-6462-4168-ac5f-4ba0223b1df8", "version": 1, "source_ref": { "record_id": "urn:uuid:3998dd03-6462-4168-ac5f-4ba0223b1df8", "version": 1, "content_hash": "sha256:afa2a91cac40fc6ead1429017a827714f9fa1b6ab462f89eb66d2e80e8b5b6a2" }, "export_view": "wrs-public-editorial-view-1", "public_view_hash": "sha256:83242fd36c834e798b94a2b3ab43d2e275fa8b511877f415b1ab85182502e954" }, "target": { "record_id": "urn:uuid:3998dd03-6462-4168-ac5f-4ba0223b1df8", "version": 1, "content_hash": "sha256:afa2a91cac40fc6ead1429017a827714f9fa1b6ab462f89eb66d2e80e8b5b6a2" }, "published_grade": { "profile": "wrs-published-grade-1", "edition": "2026-10-28.1", "id": "yue-et-al-mmmu-2023", "entry_id": "yue-et-al-mmmu-2023", "revision": 1, "title": "Yue and colleagues: MMMU multidisciplinary multimodal evaluation", "context": "AI evaluation and agent infrastructure", "track": "Evaluation resource design", "band": "A", "modifier": "-", "status": "PROVISIONAL_EDITORIAL", "assessed_on": "2026-10-16", "evidence_cutoff": "2026-10-16", "achievement_state": "SUPPORTED_SCOPED_RESULT", "what_changed": "Collected interleaved image/text questions demanding college-level knowledge and visual reasoning across multiple subjects.", "scope": "Collected interleaved image/text questions demanding college-level knowledge and visual reasoning across multiple subjects. Only general multimodal benchmark construction is acquired; no medical or biological achievement is admitted. A high score does not certify expert AGI or unrestricted domain competence.", "evidence_summary": "The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Only general multimodal benchmark construction is acquired; no medical or biological achievement is admitted. A high score does not certify expert AGI or unrestricted domain competence.", "references": [ { "title": "MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI", "url": "https://arxiv.org/abs/2311.16502v4", "locator": "Original contribution and stated assumptions, evaluation scope and limitations; source-linked assessment, not independent execution or proof certification." } ], "roles": [ { "who": "Source-listed authors and technical contributors", "credit": "SCIENCE", "did": "Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities." } ], "target": { "record_id": "urn:uuid:3998dd03-6462-4168-ac5f-4ba0223b1df8", "version": 1, "content_hash": "sha256:afa2a91cac40fc6ead1429017a827714f9fa1b6ab462f89eb66d2e80e8b5b6a2" }, "scientific_correctness_certified": false, "independent_expert_calibration": false, "method": "PROPRIETARY", "points": "100000" }, "canonical_agent_submission": false, "scientific_verification_awarded": false, "reader_guide": null, "reading_status": "SOURCE_LINKED_NOTE" }