{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BM3DIATAFRRB4V5FN3CRS2L6DR","short_pith_number":"pith:BM3DIATA","schema_version":"1.0","canonical_sha256":"0b363402602c621e57a56ec519697e1c5a08498782358019f97b5f831082c828","source":{"kind":"arxiv","id":"2404.16006","version":1},"attestation_state":"computed","paper":{"title":"MMT-Bench: A Comprehensive Multimodal Benchmark for Evaluating Large Vision-Language Models Towards Multitask AGI","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fanqing Meng, Han Lin, Hao Zhang, Haozhe Zhang, Jiayi Lei, Jin Wang, Kaining Ying, Kaipeng Zhang, Peng Gao, Peng Xu, Ping Luo, Quanfeng Lu, Renrui Zhang, Runjian Chen, Shuo Liu, Wenbo Zhang, Wenqi Shao, Yali Wang, Yue Yang, Yu Qiao, Yuqi Lin, Zhiqian Li","submitted_at":"2024-04-24T17:37:05Z","abstract_excerpt":"Large Vision-Language Models (LVLMs) show significant strides in general-purpose multimodal applications such as visual dialogue and embodied navigation. However, existing multimodal evaluation benchmarks cover a limited number of multimodal tasks testing rudimentary capabilities, falling short in tracking LVLM development. In this study, we present MMT-Bench, a comprehensive benchmark designed to assess LVLMs across massive multimodal tasks requiring expert knowledge and deliberate visual recognition, localization, reasoning, and planning. MMT-Bench comprises $31,325$ meticulously curated mul"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2404.16006","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-24T17:37:05Z","cross_cats_sorted":[],"title_canon_sha256":"fb5c41527fc09e2bbc3748994c693f48ff0df09cfe3db89e60d4df47cbd1830e","abstract_canon_sha256":"efec1fe3e4b24dbe7ecc5b62cc472032ed1898d5770f0bcae3c38fac4d9966a9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:11:48.228280Z","signature_b64":"Y2LBQqUEuUQm555R4o8hZg/ItJU75Jgpc28Rnnq7ARtx7v0DDe6fL3JAoqQu7js64fLJD4IJJx0W5zZ1VTHuBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0b363402602c621e57a56ec519697e1c5a08498782358019f97b5f831082c828","last_reissued_at":"2026-07-05T08:11:48.227809Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:11:48.227809Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MMT-Bench: A Comprehensive Multimodal Benchmark for Evaluating Large Vision-Language Models Towards Multitask AGI","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fanqing Meng, Han Lin, Hao Zhang, Haozhe Zhang, Jiayi Lei, Jin Wang, Kaining Ying, Kaipeng Zhang, Peng Gao, Peng Xu, Ping Luo, Quanfeng Lu, Renrui Zhang, Runjian Chen, Shuo Liu, Wenbo Zhang, Wenqi Shao, Yali Wang, Yue Yang, Yu Qiao, Yuqi Lin, Zhiqian Li","submitted_at":"2024-04-24T17:37:05Z","abstract_excerpt":"Large Vision-Language Models (LVLMs) show significant strides in general-purpose multimodal applications such as visual dialogue and embodied navigation. However, existing multimodal evaluation benchmarks cover a limited number of multimodal tasks testing rudimentary capabilities, falling short in tracking LVLM development. In this study, we present MMT-Bench, a comprehensive benchmark designed to assess LVLMs across massive multimodal tasks requiring expert knowledge and deliberate visual recognition, localization, reasoning, and planning. MMT-Bench comprises $31,325$ meticulously curated mul"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.16006","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2404.16006/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2404.16006","created_at":"2026-07-05T08:11:48.227867+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.16006v1","created_at":"2026-07-05T08:11:48.227867+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.16006","created_at":"2026-07-05T08:11:48.227867+00:00"},{"alias_kind":"pith_short_12","alias_value":"BM3DIATAFRRB","created_at":"2026-07-05T08:11:48.227867+00:00"},{"alias_kind":"pith_short_16","alias_value":"BM3DIATAFRRB4V5F","created_at":"2026-07-05T08:11:48.227867+00:00"},{"alias_kind":"pith_short_8","alias_value":"BM3DIATA","created_at":"2026-07-05T08:11:48.227867+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":22,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25445","citing_title":"C3-Bench: A Context-Aware Change Captioning Benchmark","ref_index":100,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08464","citing_title":"TVI-CoT: Text-Visual Interleaved Chain-of-Thought Reasoning for Multimodal Understanding","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31986","citing_title":"CoLT: Teaching Multi-Modal Models to Think with Chain of Latent Thoughts","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00535","citing_title":"DREAM-S: Speculative Decoding with Searchable Drafting and Target-Aware Refinement for Multimodal Generation","ref_index":108,"is_internal_anchor":false},{"citing_arxiv_id":"2405.19088","citing_title":"Cracking the Code of Juxtaposition: Can AI Models Understand the Humorous Contradictions","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2503.23137","citing_title":"When 'YES' Meets 'BUT': Can Large Models Comprehend Contradictory Humor Through Comparative Reasoning?","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2501.00321","citing_title":"OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and Reasoning","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2511.20814","citing_title":"SPHINX: A Synthetic Environment for Visual Perception and Reasoning","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2512.03438","citing_title":"Multimodal Reinforcement Learning with Adaptive Verifier for AI Agents","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2512.03043","citing_title":"OneThinker: All-in-one Reasoning Model for Image and Video","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2406.09411","citing_title":"MuirBench: A Comprehensive Benchmark for Robust Multi-image Understanding","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2508.05748","citing_title":"WebWatcher: Breaking New Frontier of Vision-Language Deep Research Agent","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03893","citing_title":"FeynmanBench: Benchmarking Multimodal LLMs on Diagrammatic Physics Reasoning","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2404.16821","citing_title":"How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites","ref_index":129,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00814","citing_title":"Persistent Visual Memory: Sustaining Perception for Deep Generation in LVLMs","ref_index":88,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08884","citing_title":"HM-Bench: A Comprehensive Benchmark for Multimodal Large Language Models in Hyperspectral Remote Sensing","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07593","citing_title":"TraceAV-Bench: Benchmarking Multi-Hop Trajectory Reasoning over Long Audio-Visual Videos","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00814","citing_title":"Persistent Visual Memory: Sustaining Perception for Deep Generation in LVLMs","ref_index":88,"is_internal_anchor":false},{"citing_arxiv_id":"2306.13394","citing_title":"MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2504.10479","citing_title":"InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models","ref_index":138,"is_internal_anchor":false},{"citing_arxiv_id":"2412.05271","citing_title":"Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling","ref_index":278,"is_internal_anchor":false},{"citing_arxiv_id":"2508.18265","citing_title":"InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency","ref_index":167,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BM3DIATAFRRB4V5FN3CRS2L6DR","json":"https://pith.science/pith/BM3DIATAFRRB4V5FN3CRS2L6DR.json","graph_json":"https://pith.science/api/pith-number/BM3DIATAFRRB4V5FN3CRS2L6DR/graph.json","events_json":"https://pith.science/api/pith-number/BM3DIATAFRRB4V5FN3CRS2L6DR/events.json","paper":"https://pith.science/paper/BM3DIATA"},"agent_actions":{"view_html":"https://pith.science/pith/BM3DIATAFRRB4V5FN3CRS2L6DR","download_json":"https://pith.science/pith/BM3DIATAFRRB4V5FN3CRS2L6DR.json","view_paper":"https://pith.science/paper/BM3DIATA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.16006&json=true","fetch_graph":"https://pith.science/api/pith-number/BM3DIATAFRRB4V5FN3CRS2L6DR/graph.json","fetch_events":"https://pith.science/api/pith-number/BM3DIATAFRRB4V5FN3CRS2L6DR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BM3DIATAFRRB4V5FN3CRS2L6DR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BM3DIATAFRRB4V5FN3CRS2L6DR/action/storage_attestation","attest_author":"https://pith.science/pith/BM3DIATAFRRB4V5FN3CRS2L6DR/action/author_attestation","sign_citation":"https://pith.science/pith/BM3DIATAFRRB4V5FN3CRS2L6DR/action/citation_signature","submit_replication":"https://pith.science/pith/BM3DIATAFRRB4V5FN3CRS2L6DR/action/replication_record"}},"created_at":"2026-07-05T08:11:48.227867+00:00","updated_at":"2026-07-05T08:11:48.227867+00:00"}