{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:E4ST4TYIFZXUNH4NLCXSENDMNM","short_pith_number":"pith:E4ST4TYI","schema_version":"1.0","canonical_sha256":"27253e4f082e6f469f8d58af22346c6b1fce493d856b203c45919958e98d8fa0","source":{"kind":"arxiv","id":"2407.12772","version":2},"attestation_state":"computed","paper":{"title":"LMMs-Eval: Reality Check on the Evaluation of Large Multimodal Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Evaluating large multimodal models requires balancing wide task coverage, low computational cost, and zero data contamination in benchmarks.","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Bo Li, Chunyuan Li, Fanyi Pu, Jingkang Yang, Joshua Adrian Cahyono, Kaichen Zhang, Kairui Hu, Peiyuan Zhang, Shuai Liu, Yuanhan Zhang, Ziwei Liu","submitted_at":"2024-07-17T17:51:53Z","abstract_excerpt":"The advances of large foundation models necessitate wide-coverage, low-cost, and zero-contamination benchmarks. Despite continuous exploration of language model evaluations, comprehensive studies on the evaluation of Large Multi-modal Models (LMMs) remain limited. In this work, we introduce LMMS-EVAL, a unified and standardized multimodal benchmark framework with over 50 tasks and more than 10 models to promote transparent and reproducible evaluations. Although LMMS-EVAL offers comprehensive coverage, we find it still falls short in achieving low cost and zero contamination. To approach this e"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2407.12772","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-17T17:51:53Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"9304da0fd6df0a43a304bc7313fd5757487e366e8650beec5abefe326d06a3a2","abstract_canon_sha256":"4e942c277c09028045710149d7f7bf8b6da6f6a2028782aa5a1e0e123c0fb3bd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:15.009691Z","signature_b64":"/db6vdtnPHx4hLMrb7vbrQ9PC4Zkq95eghk3UFxjcSMIYOhlgF02PRRoqsQ0DPP8ymJjHwfBDWB66JDKQCsBBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"27253e4f082e6f469f8d58af22346c6b1fce493d856b203c45919958e98d8fa0","last_reissued_at":"2026-05-17T23:38:15.008955Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:15.008955Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LMMs-Eval: Reality Check on the Evaluation of Large Multimodal Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Evaluating large multimodal models requires balancing wide task coverage, low computational cost, and zero data contamination in benchmarks.","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Bo Li, Chunyuan Li, Fanyi Pu, Jingkang Yang, Joshua Adrian Cahyono, Kaichen Zhang, Kairui Hu, Peiyuan Zhang, Shuai Liu, Yuanhan Zhang, Ziwei Liu","submitted_at":"2024-07-17T17:51:53Z","abstract_excerpt":"The advances of large foundation models necessitate wide-coverage, low-cost, and zero-contamination benchmarks. Despite continuous exploration of language model evaluations, comprehensive studies on the evaluation of Large Multi-modal Models (LMMs) remain limited. In this work, we introduce LMMS-EVAL, a unified and standardized multimodal benchmark framework with over 50 tasks and more than 10 models to promote transparent and reproducible evaluations. Although LMMS-EVAL offers comprehensive coverage, we find it still falls short in achieving low cost and zero contamination. To approach this e"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Our work highlights the importance of considering the evaluation trilemma and provides practical solutions to navigate the trade-offs in evaluating large multi-modal models.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the live data sources and pruning rules in LMMS-EVAL LITE and LIVEBENCH truly deliver zero contamination and maintained coverage without introducing new selection biases or missing important capabilities.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"LMMS-EVAL delivers a standardized multimodal evaluation framework with lite and live variants that target the trade-offs among coverage, cost, and zero contamination.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Evaluating large multimodal models requires balancing wide task coverage, low computational cost, and zero data contamination in benchmarks.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"e3d49ea222040ef472c564e264ba79f6f27b0de3ed651315426759c8b1ffb32d"},"source":{"id":"2407.12772","kind":"arxiv","version":2},"verdict":{"id":"aea1499b-8ccf-4737-bb8a-8fa3e282bc8c","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-17T05:15:22.504049Z","strongest_claim":"Our work highlights the importance of considering the evaluation trilemma and provides practical solutions to navigate the trade-offs in evaluating large multi-modal models.","one_line_summary":"LMMS-EVAL delivers a standardized multimodal evaluation framework with lite and live variants that target the trade-offs among coverage, cost, and zero contamination.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the live data sources and pruning rules in LMMS-EVAL LITE and LIVEBENCH truly deliver zero contamination and maintained coverage without introducing new selection biases or missing important capabilities.","pith_extraction_headline":"Evaluating large multimodal models requires balancing wide task coverage, low computational cost, and zero data contamination in benchmarks."},"references":{"count":24,"sample":[{"doi":"","year":null,"title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","work_id":"f3aac728-ded0-4e55-aa9e-4a1635d4313d","ref_index":1,"cited_arxiv_id":"2305.06500","is_internal_anchor":true},{"doi":"","year":null,"title":"Internlm-xcomposer2- 4khd: A pioneering large vision-language model handling resolutions from 336 pixels to 4k hd","work_id":"799b1f12-2edc-4b09-a83b-dbd87e1404e7","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models","work_id":"806d2e73-71b3-4d56-87e0-39d571cc15d6","ref_index":3,"cited_arxiv_id":"2306.13394","is_internal_anchor":true},{"doi":"","year":2023,"title":"Making llama see and draw with seed tokenizer","work_id":"9453feaf-a19d-4603-b9de-da50593c5d43","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"A diagram is worth a dozen images.ArXiv, abs/1603.07396","work_id":"3cc7177d-7f05-4d4d-8066-04b7d589017f","ref_index":5,"cited_arxiv_id":"1603.07396","is_internal_anchor":true}],"resolved_work":24,"snapshot_sha256":"8259cdf1001bbc4b76ac39e2a416d1dc500d9bc07d1609c7bd56eafeaa80ae19","internal_anchors":3},"formal_canon":{"evidence_count":2,"snapshot_sha256":"0fe42ac1f960edabb5776079e4c5fb9f1ed2d110b322762081d32bcc4709db70"},"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":"2407.12772","created_at":"2026-05-17T23:38:15.009084+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.12772v2","created_at":"2026-05-17T23:38:15.009084+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.12772","created_at":"2026-05-17T23:38:15.009084+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":17,"internal_anchor_count":17,"sample":[{"citing_arxiv_id":"2505.16933","citing_title":"LLaDA-V: Large Language Diffusion Models with Visual Instruction Tuning","ref_index":112,"is_internal_anchor":true},{"citing_arxiv_id":"2506.20670","citing_title":"MMSearch-R1: Incentivizing LMMs to Search","ref_index":66,"is_internal_anchor":true},{"citing_arxiv_id":"2503.07536","citing_title":"LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL","ref_index":91,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14530","citing_title":"Mitigating Mask Prior Drift and Positional Attention Collapse in Large Diffusion Vision-Language Models","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2501.13826","citing_title":"Video-MMMU: Evaluating Knowledge Acquisition from Multi-Discipline Professional Videos","ref_index":47,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11477","citing_title":"LDDR: Linear-DPP-Based Dynamic-Resolution Frame Sampling for Video MLLMs","ref_index":43,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09649","citing_title":"Make Each Token Count: Towards Improving Long-Context Performance with KV Cache Eviction","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2604.11627","citing_title":"POINTS-Long: Adaptive Dual-Mode Visual Reasoning in MLLMs","ref_index":113,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07355","citing_title":"TTF: Temporal Token Fusion for Efficient Video-Language Model","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2605.05225","citing_title":"MACS: Modality-Aware Capacity Scaling for Efficient Multimodal MoE Inference","ref_index":40,"is_internal_anchor":true},{"citing_arxiv_id":"2506.09985","citing_title":"V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning","ref_index":56,"is_internal_anchor":true},{"citing_arxiv_id":"2604.06912","citing_title":"Q-Zoom: Query-Aware Adaptive Perception for Efficient Multimodal Large Language Models","ref_index":75,"is_internal_anchor":true},{"citing_arxiv_id":"2410.02713","citing_title":"LLaVA-Video: Video Instruction Tuning With Synthetic Data","ref_index":165,"is_internal_anchor":true},{"citing_arxiv_id":"2604.04500","citing_title":"Saliency-R1: Enforcing Interpretable and Faithful Vision-language Reasoning via Saliency-map Alignment Reward","ref_index":89,"is_internal_anchor":true},{"citing_arxiv_id":"2408.03326","citing_title":"LLaVA-OneVision: Easy Visual Task Transfer","ref_index":161,"is_internal_anchor":true},{"citing_arxiv_id":"2604.21343","citing_title":"Latent Denoising Improves Visual Alignment in Large Multimodal Models","ref_index":98,"is_internal_anchor":true},{"citing_arxiv_id":"2605.00789","citing_title":"Make Your LVLM KV Cache More Lightweight","ref_index":104,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E4ST4TYIFZXUNH4NLCXSENDMNM","json":"https://pith.science/pith/E4ST4TYIFZXUNH4NLCXSENDMNM.json","graph_json":"https://pith.science/api/pith-number/E4ST4TYIFZXUNH4NLCXSENDMNM/graph.json","events_json":"https://pith.science/api/pith-number/E4ST4TYIFZXUNH4NLCXSENDMNM/events.json","paper":"https://pith.science/paper/E4ST4TYI"},"agent_actions":{"view_html":"https://pith.science/pith/E4ST4TYIFZXUNH4NLCXSENDMNM","download_json":"https://pith.science/pith/E4ST4TYIFZXUNH4NLCXSENDMNM.json","view_paper":"https://pith.science/paper/E4ST4TYI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.12772&json=true","fetch_graph":"https://pith.science/api/pith-number/E4ST4TYIFZXUNH4NLCXSENDMNM/graph.json","fetch_events":"https://pith.science/api/pith-number/E4ST4TYIFZXUNH4NLCXSENDMNM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E4ST4TYIFZXUNH4NLCXSENDMNM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E4ST4TYIFZXUNH4NLCXSENDMNM/action/storage_attestation","attest_author":"https://pith.science/pith/E4ST4TYIFZXUNH4NLCXSENDMNM/action/author_attestation","sign_citation":"https://pith.science/pith/E4ST4TYIFZXUNH4NLCXSENDMNM/action/citation_signature","submit_replication":"https://pith.science/pith/E4ST4TYIFZXUNH4NLCXSENDMNM/action/replication_record"}},"created_at":"2026-05-17T23:38:15.009084+00:00","updated_at":"2026-05-17T23:38:15.009084+00:00"}