{ "title": "A Survey of World Model Benchmarks", "version": "August 31, 2026 corpus; joint task-level coding finalized September 15, 2026", "framework": "Target–Protocol–Metrics–Data", "schemaVersion": 12, "total": 102, "crossCategory": 85, "protocolLabels": { "OL": "Open-Loop Evaluation", "CL": "Closed-Loop Interaction" }, "metricLabels": { "P": "Prediction-Level Metrics", "O": "Downstream Outcome Metrics" }, "dataLabels": { "RWD": "Real-World Data Collection", "SBG": "Simulation-Based Generation", "SPTC": "Scenario, Prompt, and Task Curation", "HCP": "Hybrid Construction Pipelines" }, "timelineBins": [ { "label": "2018–2021", "years": [ 2018, 2019, 2020, 2021 ] }, { "label": "2022–2023", "years": [ 2022, 2023 ] }, { "label": "2024", "years": [ 2024 ] }, { "label": "2025", "years": [ 2025 ] }, { "label": "2026", "years": [ 2026 ] } ], "targetLabels": { "T1": "Visual & Temporal Quality", "T2": "Spatial & State Consistency", "T3": "Long-Horizon Memory & State Persistence", "T4": "Physical Plausibility", "T5": "Causal & Counterfactual Reasoning", "T6": "Control Fidelity & Interactive Dynamics", "T7": "Functional Utility" }, "subtargetLabels": { "S1": "Visual Quality", "S2": "Temporal Quality", "S3": "Observation-Grounded Evaluation", "S4": "Intervention-Grounded Evaluation", "S5": "Pre-specified Control Fidelity", "S6": "Interactive Action Fidelity", "S7": "Data Engine", "S8": "Policy Evaluator", "S9": "Planner", "S10": "Interactive Training Environment" }, "aliases": { "Pedestrian sim.": "PEDRA" }, "removed": [ "EvalCrafter", "FETV", "Scalable Policy Eval", "T2V-CompBench", "VBench", "VBench++", "VideoScore", "stable-worldmodel", "CATER", "NExT-QA", "IntentQA", "VCRBench" ], "added": { "CausalSpatial": { "id": "causalspatial", "shortName": "CausalSpatial", "title": "CausalSpatial: A Benchmark for Object-Centric Causal Spatial Reasoning", "venue": "arXiv", "paperUrl": "https://arxiv.org/abs/2601.13304", "arxivId": "2601.13304", "reference": "CausalSpatial: A Benchmark for Object-Centric Causal Spatial Reasoning, arXiv:2601.13304, 2026." }, "WoW-World-Eval": { "id": "wow-world-eval", "shortName": "WoW-World-Eval", "title": "Wow, Wo, Val! A Comprehensive Embodied World Model Evaluation Turing Test", "venue": "arXiv", "paperUrl": "https://arxiv.org/abs/2601.04137", "arxivId": "2601.04137", "reference": "C.-K. Fan et al., “Wow, Wo, Val! A Comprehensive Embodied World Model Evaluation Turing Test,” arXiv:2601.04137, 2026." }, "RBench": { "id": "rbench", "shortName": "RBench", "title": "Rethinking Video Generation Model for the Embodied World", "venue": "ICML", "paperUrl": "https://arxiv.org/abs/2601.15282", "arxivId": "2601.15282", "reference": "Y. Deng et al., “Rethinking Video Generation Model for the Embodied World,” ICML, 2026." }, "PAI-Bench": { "id": "pai-bench", "shortName": "PAI-Bench", "title": "PAI-Bench: A Comprehensive Benchmark for Physical AI", "venue": "CVPR", "paperUrl": "https://arxiv.org/abs/2512.01989", "arxivId": "2512.01989", "reference": "F. Zhou et al., “PAI-Bench: A Comprehensive Benchmark for Physical AI,” CVPR, 2026." }, "EZS-Bench": { "id": "ezs-bench", "shortName": "EZS-Bench", "title": "ABot-PhysWorld: Interactive World Foundation Model for Robotic Manipulation with Physics Alignment (introduces EZS-Bench)", "venue": "arXiv", "paperUrl": "https://arxiv.org/abs/2603.23376", "arxivId": "2603.23376", "reference": "Y. Chen et al., “ABot-PhysWorld: Interactive World Foundation Model for Robotic Manipulation with Physics Alignment,” arXiv:2603.23376, 2026." }, "AutumnBench": { "id": "autumnbench", "shortName": "AutumnBench", "title": "Benchmarking World-Model Learning (introduces AutumnBench)", "venue": "ICML", "paperUrl": "https://arxiv.org/abs/2510.19788", "arxivId": "2510.19788", "reference": "A. Warrier et al., “Benchmarking World-Model Learning,” arXiv:2510.19788, 2025." }, "MVP": { "id": "mvp", "shortName": "MVP", "title": "A Shortcut-Aware Video-QA Benchmark for Physical Understanding via Minimal Video Pairs", "venue": "arXiv", "paperUrl": "https://arxiv.org/abs/2506.09987", "arxivId": "2506.09987", "reference": "B. Krojer et al., “A Shortcut-Aware Video-QA Benchmark for Physical Understanding via Minimal Video Pairs,” arXiv:2506.09987, 2025." }, "WorldRoamBench": { "id": "worldroambench", "shortName": "WorldRoamBench", "title": "WorldRoamBench: An Open-World Benchmark for Long-Horizon Stability of Interactive World Models", "venue": "arXiv", "paperUrl": "https://arxiv.org/abs/2606.31672", "arxivId": "2606.31672", "reference": "WorldRoamBench: An Open-World Benchmark for Long-Horizon Stability of Interactive World Models, arXiv:2606.31672, 2026." }, "CrashTwin": { "id": "crashtwin", "shortName": "CrashTwin", "title": "A Physics-Grounded Benchmark for Multi-Agent Dynamics in World Models", "venue": "arXiv", "paperUrl": "https://arxiv.org/abs/2606.28757", "arxivId": "2606.28757", "reference": "A Physics-Grounded Benchmark for Multi-Agent Dynamics in World Models, arXiv:2606.28757, 2026." }, "MemoBench": { "id": "memobench", "shortName": "MemoBench", "title": "MemoBench: Benchmarking World Modeling in Dynamically Changing Environments", "venue": "arXiv", "paperUrl": "https://arxiv.org/abs/2606.27537", "arxivId": "2606.27537", "reference": "MemoBench: Benchmarking World Modeling in Dynamically Changing Environments, arXiv:2606.27537, 2026." }, "RoboTrustBench": { "id": "robotrustbench", "shortName": "RoboTrustBench", "title": "RoboTrustBench: Benchmarking the Trustworthiness of Video World Models for Robotic Manipulation", "venue": "arXiv", "paperUrl": "https://arxiv.org/abs/2606.01600", "arxivId": "2606.01600", "reference": "RoboTrustBench: Benchmarking the Trustworthiness of Video World Models for Robotic Manipulation, arXiv:2606.01600, 2026." }, "ContactWorld": { "id": "contactworld", "shortName": "ContactWorld", "title": "ContactWorld: What Matters in Vision-Tactile World Models for Contact-Rich Manipulation", "venue": "arXiv", "paperUrl": "https://arxiv.org/abs/2606.13877", "arxivId": "2606.13877", "reference": "ContactWorld: What Matters in Vision-Tactile World Models for Contact-Rich Manipulation, arXiv:2606.13877, 2026." }, "ScratchWorld": { "id": "scratchworld", "shortName": "ScratchWorld", "title": "ScratchWorld: Evaluating if World Models Compute Executable Consequences", "venue": "arXiv", "paperUrl": "https://arxiv.org/abs/2606.31689", "arxivId": "2606.31689", "reference": "ScratchWorld: Evaluating if World Models Compute Executable Consequences, arXiv:2606.31689, 2026." }, "MiraBench": { "id": "mirabench", "shortName": "MiraBench", "title": "MiraBench: Evaluating Action-Conditioned Reliability in Robotic World Models", "venue": "arXiv", "paperUrl": "https://arxiv.org/abs/2605.29360", "arxivId": "2605.29360", "reference": "MiraBench: Evaluating Action-Conditioned Reliability in Robotic World Models, arXiv:2605.29360, 2026." }, "Chess-World-Model": { "id": "chess-world-model", "shortName": "Chess-World-Model", "title": "Chess-World-Model: A 10M-Game Benchmark for Exact State Tracking from Chess Move Sequences", "venue": "arXiv", "paperUrl": "https://arxiv.org/abs/2605.30100", "arxivId": "2605.30100", "reference": "Chess-World-Model: A 10M-Game Benchmark for Exact State Tracking from Chess Move Sequences, arXiv:2605.30100, 2026." }, "Apple-π": { "id": "apple-pi", "shortName": "Apple-π", "title": "Apple-π: Benchmarking Thinking with Video Towards Law-Grounded Physical Intelligence", "venue": "arXiv", "paperUrl": "https://arxiv.org/abs/2607.16401", "arxivId": "2607.16401", "reference": "Apple-π: Benchmarking Thinking with Video Towards Law-Grounded Physical Intelligence, arXiv:2607.16401, 2026." }, "KineBench": { "id": "kinebench", "shortName": "KineBench", "title": "KineBench: Benchmarking Embodied World Models via IDM-Free Kinematic Grounding", "venue": "arXiv", "paperUrl": "https://arxiv.org/abs/2607.19876", "arxivId": "2607.19876", "reference": "KineBench: Benchmarking Embodied World Models via IDM-Free Kinematic Grounding, arXiv:2607.19876, 2026." }, "ReactSim-Bench": { "id": "reactsim-bench", "shortName": "ReactSim-Bench", "title": "ReactSim-Bench: Benchmarking Reactive Behavior World Model Simulation in Autonomous Driving", "venue": "arXiv", "paperUrl": "https://arxiv.org/abs/2606.14058", "arxivId": "2606.14058", "reference": "ReactSim-Bench: Benchmarking Reactive Behavior World Model Simulation in Autonomous Driving, arXiv:2606.14058, 2026." }, "WMBench": { "id": "wmbench", "shortName": "WMBench", "title": "GigaWorld-1: A Roadmap to Build World Models for Robot Policy Evaluation (introduces WMBench)", "venue": "arXiv", "paperUrl": "https://arxiv.org/abs/2607.02642", "arxivId": "2607.02642", "reference": "GigaWorld-1: A Roadmap to Build World Models for Robot Policy Evaluation (introduces WMBench), arXiv:2607.02642, 2026." }, "WorldExam": { "id": "worldexam", "shortName": "WorldExam", "title": "WorldExam: Benchmarking World Models from Apparent Appearance to Inherent Reactivity", "venue": "arXiv", "paperUrl": "https://arxiv.org/abs/2608.02603", "arxivId": "2608.02603", "reference": "Y. Yang et al., “WorldExam: Benchmarking World Models from Apparent Appearance to Inherent Reactivity,” arXiv:2608.02603, 2026." }, "SurgWMBench": { "id": "surgwmbench", "shortName": "SurgWMBench", "title": "SurgWMBench: A Vision-Based Benchmark for World-Modeling Surgical Instrument Motion Planning", "venue": "arXiv", "paperUrl": "https://arxiv.org/abs/2608.08070", "arxivId": "2608.08070", "reference": "H. Liu et al., “SurgWMBench: A Vision-Based Benchmark for World-Modeling Surgical Instrument Motion Planning,” arXiv:2608.08070, 2026." }, "H2R-Bench": { "id": "h2r-bench", "shortName": "H2R-Bench", "title": "H2R-Bench: Benchmarking Human-to-Robot Manipulation Video Generation in World Models", "venue": "arXiv", "paperUrl": "https://arxiv.org/abs/2608.13049", "arxivId": "2608.13049", "reference": "D. Rong et al., “H2R-Bench: Benchmarking Human-to-Robot Manipulation Video Generation in World Models,” arXiv:2608.13049, 2026." }, "PlayWorld": { "id": "playworld", "shortName": "PlayWorld", "title": "PlayWorld: Benchmarking World Models with Agent Players over Long-Horizon Objectives", "venue": "arXiv", "paperUrl": "https://arxiv.org/abs/2608.13552", "arxivId": "2608.13552", "reference": "K. Ding et al., “PlayWorld: Benchmarking World Models with Agent Players over Long-Horizon Objectives,” arXiv:2608.13552, 2026." }, "XEWorld": { "id": "xeworld", "shortName": "XEWorld", "title": "XEWorld: Can Action-Conditioned World Models Generalize to Unseen Robot Embodiments?", "venue": "arXiv", "paperUrl": "https://arxiv.org/abs/2608.05799", "arxivId": "2608.05799", "reference": "Y. Chen et al., “XEWorld: Can Action-Conditioned World Models Generalize to Unseen Robot Embodiments?” arXiv:2608.05799, 2026." }, "HarnessEval-W": { "id": "harnesseval-w", "shortName": "HarnessEval-W", "title": "HarnessEval-W: Agentifying the Evaluation of Visual Worlds", "venue": "arXiv", "paperUrl": "https://arxiv.org/abs/2608.16859", "arxivId": "2608.16859", "reference": "W. Chen et al., “HarnessEval-W: Agentifying the Evaluation of Visual Worlds,” arXiv:2608.16859, 2026." }, "WorldEcho": { "id": "worldecho", "shortName": "WorldEcho", "title": "Do Robotic World Models Really Follow Actions? Diagnosing and Aligning Action-Conditioned Generation for Policy Learning (introduces WorldEcho)", "venue": "arXiv", "paperUrl": "https://arxiv.org/abs/2608.24885", "arxivId": "2608.24885", "reference": "S. Chen et al., “Do Robotic World Models Really Follow Actions? Diagnosing and Aligning Action-Conditioned Generation for Policy Learning,” arXiv:2608.24885, 2026." }, "GAUGE": { "id": "gauge", "shortName": "GAUGE", "title": "GAUGE: A Measurement-Grounded Benchmark for Physical Fidelity in Simulation Engines and Video World Models", "venue": "arXiv", "paperUrl": "https://arxiv.org/abs/2608.05948", "arxivId": "2608.05948", "reference": "S. Wang et al., “GAUGE: A Measurement-Grounded Benchmark for Physical Fidelity in Simulation Engines and Video World Models,” arXiv:2608.05948, 2026." }, "CaliBench": { "id": "calibench", "shortName": "CaliBench", "title": "CaliBench: Are the Stochastic Dynamics of Video World Models Physically Calibrated?", "venue": "arXiv", "paperUrl": "https://arxiv.org/abs/2608.16829", "arxivId": "2608.16829", "reference": "J. Sadeghi et al., “CaliBench: Are the Stochastic Dynamics of Video World Models Physically Calibrated?” arXiv:2608.16829, 2026." }, "WorldSimProbe": { "id": "worldsimprobe", "shortName": "WorldSimProbe", "title": "WorldSimProbe: Diagnosing Simulator Faithfulness in Action-Conditioned World Models for Embodied Manipulation", "venue": "arXiv", "paperUrl": "https://arxiv.org/abs/2608.09298", "arxivId": "2608.09298", "reference": "P. Co et al., “WorldSimProbe: Diagnosing Simulator Faithfulness in Action-Conditioned World Models for Embodied Manipulation,” arXiv:2608.09298, 2026." }, "ExPhy": { "id": "exphy", "shortName": "ExPhy", "title": "ExPhy: A Benchmark for Explicit Physical Property Learning in Multi-Object Trajectory Forecasting", "venue": "arXiv", "paperUrl": "https://arxiv.org/abs/2608.20009", "arxivId": "2608.20009", "reference": "R. Wang et al., “ExPhy: A Benchmark for Explicit Physical Property Learning in Multi-Object Trajectory Forecasting,” arXiv:2608.20009, 2026." } }, "records": { "RoboWM-Bench": [ 38, 2026, "embodied", "OL", "O", "HCP", "T3+T4+T6+T7", "S6+S9" ], "World-in-World": [ 42, 2025, "embodied", "CL", "O", "HCP", "T7", "S9" ], "IntPhys": [ 43, 2018, "video", "OL", "P", "SBG", "T2+T4", "" ], "CLEVRER": [ 44, 2019, "video", "OL", "P", "SBG", "T4+T5", "S3+S4" ], "Physion": [ 45, 2021, "video", "OL", "P", "SBG", "T4+T5", "S3" ], "MIND": [ 46, 2026, "video", "OL", "P", "SBG", "T1+T2+T3+T6", "S1+S6" ], "WorldOlympiad": [ 47, 2026, "video", "OL", "P", "HCP", "T2+T3+T4+T6", "S6" ], "WorldArena": [ 48, 2026, "embodied", "OL+CL", "P+O", "SBG+HCP", "T1+T2+T4+T6+T7", "S1+S2+S5+S7+S8+S9" ], "WorldArena 2.0": [ 49, 2026, "embodied", "OL+CL", "P+O", "RWD+SBG+HCP", "T1+T2+T4+T6+T7", "S2+S6+S7+S9+S10" ], "ChronoMagic-Bench": [ 68, 2024, "video", "OL", "P", "SPTC", "T1", "S1+S2" ], "WorldScore": [ 69, 2025, "video", "OL", "P", "SPTC+HCP", "T1+T2+T6", "S1+S2+S5" ], "VMBench": [ 70, 2025, "video", "OL", "P", "SPTC", "T1+T4", "S1+S2" ], "EWMBench": [ 71, 2025, "embodied", "OL", "P", "RWD", "T1+T2+T4+T6", "S1+S2+S5" ], "GameWorld Score": [ 72, 2025, "game", "OL", "P", "SBG", "T1+T2+T4+T6", "S1+S2+S5" ], "WorldMark": [ 73, 2026, "game+video", "OL", "P", "HCP", "T1+T2+T3+T6", "S1+S2+S6" ], "4DWorldBench": [ 74, 2025, "video", "OL", "P", "RWD+SPTC+HCP", "T1+T2+T4+T6", "S1+S2+S5" ], "WorldLens": [ 75, 2025, "driving", "OL+CL", "P+O", "RWD+HCP", "T1+T2+T4+T7", "S1+S2+S9" ], "DrivingGen": [ 76, 2026, "driving", "OL", "P", "RWD", "T1+T2+T4+T6", "S1+S2+S5" ], "PEDRA": [ 77, 2025, "video", "OL", "P", "RWD+SPTC", "T1+T2+T4", "S1+S2" ], "Gen-ViRe": [ 78, 2025, "video", "OL", "P", "HCP", "T1+T2+T4", "S1+S2" ], "iWorld-Bench": [ 79, 2026, "video", "OL", "P", "HCP", "T1+T2+T3+T6", "S1+S6" ], "TC-Bench": [ 106, 2024, "video", "OL", "P", "RWD+SPTC", "T1+T6", "S2+S5" ], "WBench": [ 107, 2026, "video", "OL", "P", "HCP", "T1+T2+T3+T4+T6", "S2+S6" ], "PDI-Bench": [ 111, 2026, "video", "OL", "P", "SPTC", "T2+T4", "" ], "LoopNav": [ 112, 2025, "game", "OL", "P", "SBG", "T2+T3", "" ], "MBench": [ 113, 2026, "video", "OL", "P", "RWD", "T2+T3+T4+T6", "S5" ], "STEVO-Bench": [ 114, 2026, "video", "OL", "P", "SPTC", "T2+T4+T6", "S5" ], "CausalSpatial": [ 115, 2026, "video", "OL", "P", "SBG", "T2+T4+T5", "S4" ], "What-If World": [ 116, 2026, "driving+embodied", "OL", "P", "RWD", "T2+T4+T5+T6", "S3+S5" ], "HOCA-Bench": [ 117, 2026, "video", "OL", "P", "SPTC+HCP", "T2+T4+T5", "S3" ], "WorldPrediction": [ 128, 2025, "video", "OL", "P", "RWD", "T3+T5", "S3" ], "SmallWorlds": [ 125, 2025, "video", "OL", "P", "SBG", "T2+T3+T4", "" ], "WR-Arena": [ 110, 2026, "driving+embodied", "OL+CL", "P+O", "HCP", "T1+T3+T5+T6+T7", "S2+S3+S6+S9" ], "HTEWorld": [ 95, 2026, "embodied", "OL", "P", "SBG", "T1+T2+T3+T4+T6", "S1+S2+S6" ], "IntPhys 2": [ 124, 2025, "video", "OL", "P", "SBG", "T2+T4", "" ], "CoPhy": [ 130, 2019, "video", "OL", "P", "SBG", "T4+T5", "S4" ], "PHYRE": [ 131, 2019, "video", "OL+CL", "O", "SBG", "T4", "" ], "CRAFT": [ 132, 2020, "video", "OL", "P", "SBG", "T4+T5", "S3+S4" ], "Physion++": [ 133, 2023, "video", "OL", "P", "SBG", "T4", "" ], "ComPhy": [ 134, 2022, "video", "OL", "P", "SBG", "T4+T5", "S4" ], "ContPhy": [ 135, 2024, "video", "OL", "P", "SBG", "T4+T5", "S3+S4" ], "PhyCoBench": [ 136, 2025, "video", "OL", "P", "SPTC", "T4", "" ], "VideoPhy": [ 137, 2024, "video", "OL", "P", "SPTC", "T4+T6", "S5" ], "VideoPhy-2": [ 138, 2025, "video", "OL", "P", "SPTC", "T4+T6", "S5" ], "PhyGenBench": [ 139, 2024, "video", "OL", "P", "SPTC", "T4+T6", "S5" ], "T2VPhysBench": [ 140, 2025, "video", "OL", "P", "SPTC", "T4", "" ], "Physics-IQ": [ 141, 2025, "video", "OL", "P", "RWD", "T4+T5", "S3" ], "WorldBench": [ 127, 2026, "video", "OL", "P", "HCP", "T2+T4", "" ], "PhyWorldBench": [ 142, 2025, "video", "OL", "P", "SPTC", "T4+T6", "S5" ], "T2VWorldBench": [ 101, 2025, "video", "OL", "P", "SPTC", "T1+T4+T5", "S1+S2+S3" ], "WorldModelBench": [ 103, 2025, "video", "OL", "P", "SPTC+HCP", "T1+T4+T6", "S1+S2+S5" ], "VBench-2.0": [ 126, 2025, "video", "OL", "P", "SPTC", "T2+T4+T6", "S5" ], "RigidBench": [ 96, 2026, "video", "OL", "P", "SBG", "T1+T2+T4", "S1" ], "Morpheus": [ 143, 2025, "video", "OL", "P", "RWD+HCP", "T4", "" ], "DreamGen Bench": [ 144, 2025, "embodied", "OL", "P", "HCP", "T4+T6", "S5" ], "PhyGround": [ 145, 2026, "video", "OL", "P", "HCP", "T4", "" ], "Physion-Eval": [ 146, 2026, "video", "OL", "P", "RWD", "T4", "" ], "CRONOS": [ 147, 2026, "video", "OL", "P", "SBG", "T4+T5", "S3" ], "VACT": [ 148, 2025, "video", "OL", "P", "SPTC", "T4+T5+T6", "S3+S5" ], "PhysicsMind": [ 149, 2026, "video", "OL", "P", "HCP", "T4+T5", "S3" ], "ACWM-Phys": [ 94, 2026, "video", "OL", "P", "SBG", "T1+T4+T6", "S1+S6" ], "Causal-VidQA": [ 155, 2022, "video", "OL", "P", "RWD", "T5", "S3" ], "MMWorld": [ 157, 2024, "video", "OL", "P", "HCP", "T5", "S3" ], "CausalVQA": [ 158, 2025, "video", "OL", "P", "RWD", "T5", "S3" ], "ACQUIRED": [ 156, 2023, "video", "OL", "P", "RWD", "T5", "S3" ], "StoryEval": [ 159, 2024, "video", "OL", "P", "SPTC", "T6", "S5" ], "OSCBench": [ 100, 2026, "video", "OL", "P", "SPTC", "T1+T2+T6", "S1+S5" ], "MoveBench": [ 98, 2025, "video", "OL", "P", "RWD", "T1+T6", "S1+S2+S5" ], "MagicBench": [ 97, 2025, "video", "OL", "P", "RWD", "T1+T6", "S1+S2+S5" ], "ACT-Bench": [ 160, 2024, "driving", "OL", "P", "RWD", "T6", "S5" ], "Omni-WorldBench": [ 99, 2026, "video", "OL", "P", "SPTC+HCP", "T1+T2+T4+T6", "S1+S2+S5" ], "WorldSimBench": [ 104, 2024, "game+driving+embodied", "OL+CL", "P+O", "RWD+SBG+SPTC+HCP", "T1+T2+T4+T6+T7", "S1+S6+S9" ], "EVA-Bench": [ 109, 2024, "embodied", "OL+CL", "P+O", "HCP", "T1+T2+T7", "S2+S9" ], "WoW-World-Eval": [ 80, 2026, "embodied", "OL", "P+O", "HCP", "T1+T2+T3+T4+T5+T6+T7", "S1+S2+S3+S5+S9" ], "RBench": [ 81, 2026, "embodied", "OL", "P", "RWD", "T1+T2+T3+T4+T5+T6", "S1+S2+S3+S5" ], "PAI-Bench": [ 82, 2025, "video", "OL", "P", "RWD+SPTC", "T1+T2+T4+T5+T6", "S1+S2+S3+S5" ], "EZS-Bench": [ 83, 2026, "embodied", "OL", "P", "HCP", "T1+T2+T4+T6", "S1+S2+S5" ], "AutumnBench": [ 118, 2025, "game", "CL", "P+O", "SBG", "T2+T3+T5+T7", "S4+S9" ], "MVP": [ 119, 2025, "video", "OL", "P", "HCP", "T2+T4+T5", "S3" ], "WorldRoamBench": [ 84, 2026, "video+game", "OL", "P", "HCP", "T1+T2+T3+T4+T6", "S1+S2+S6" ], "CrashTwin": [ 108, 2026, "driving+video", "OL", "P", "HCP", "T1+T2+T4", "S2" ], "MemoBench": [ 85, 2026, "video", "OL", "P", "HCP", "T1+T2+T3+T4+T6", "S1+S2+S5" ], "RoboTrustBench": [ 86, 2026, "embodied", "OL", "P", "HCP", "T1+T2+T4+T5+T6", "S1+S2+S3+S5" ], "ContactWorld": [ 120, 2026, "embodied", "OL+CL", "P+O", "SBG+HCP", "T2+T3+T4+T7", "S9" ], "ScratchWorld": [ 121, 2026, "game", "OL", "P", "SBG", "T2+T3+T5+T6", "S4+S5" ], "MiraBench": [ 122, 2026, "embodied", "OL", "P", "HCP", "T2+T4+T5+T6", "S3+S5" ], "Chess-World-Model": [ 123, 2026, "game", "OL", "P", "SBG", "T2+T3+T6", "S5" ], "Apple-π": [ 105, 2026, "video", "OL", "P", "HCP", "T1+T2+T4", "S1+S2" ], "KineBench": [ 150, 2026, "embodied", "CL", "P+O", "HCP", "T4+T6+T7", "S5+S9" ], "ReactSim-Bench": [ 151, 2026, "driving", "OL", "P", "HCP", "T4+T5+T6", "S4+S6" ], "WMBench": [ 102, 2026, "embodied", "OL+CL", "P+O", "RWD+HCP", "T1+T2+T3+T4+T6+T7", "S1+S2+S6+S8" ], "WorldExam": [ 87, 2026, "video", "OL", "P", "SPTC+HCP", "T1+T2+T4+T5+T6", "S1+S2+S3+S5" ], "SurgWMBench": [ 88, 2026, "embodied", "OL", "P", "RWD", "T1+T2", "S1+S2" ], "H2R-Bench": [ 89, 2026, "embodied", "OL", "P", "RWD+HCP", "T1+T2+T4+T6", "S1+S2+S5" ], "PlayWorld": [ 90, 2026, "game+video", "CL", "P", "HCP", "T1+T2+T3+T4+T5+T6", "S1+S2+S3+S6" ], "XEWorld": [ 91, 2026, "embodied", "OL", "P", "SBG", "T1+T2+T4+T6", "S1+S2+S5" ], "HarnessEval-W": [ 92, 2026, "video", "OL", "P", "SPTC", "T1+T2+T3+T4+T5+T6", "S1+S2+S3+S5" ], "WorldEcho": [ 93, 2026, "embodied", "OL", "P", "SBG", "T1+T6", "S1+S2+S5" ], "GAUGE": [ 152, 2026, "video", "OL", "P", "RWD", "T4", "" ], "CaliBench": [ 153, 2026, "video", "OL", "P", "SPTC", "T4", "" ], "WorldSimProbe": [ 154, 2026, "embodied", "OL", "P", "SBG", "T4+T5+T6", "S4+S5" ], "ExPhy": [ 129, 2026, "embodied", "OL", "P", "SBG", "T3+T4", "" ] }, "supportingResources": [ { "name": "VideoScore", "url": "https://arxiv.org/abs/2406.15252" }, { "name": "Scalable Policy Evaluation", "url": "https://arxiv.org/abs/2511.11520" }, { "name": "stable-worldmodel", "url": "https://arxiv.org/abs/2605.21800" } ], "snapshotDate": "2026-08-31", "targetCounts": { "Visual & Temporal Quality": 46, "Spatial & State Consistency": 55, "Long-Horizon Memory & State Persistence": 24, "Physical Plausibility": 77, "Causal & Counterfactual Reasoning": 33, "Control Fidelity & Interactive Dynamics": 55, "Functional Utility": 13 }, "subtargetCounts": { "Visual Quality": 40, "Temporal Quality": 40, "Observation-Grounded Evaluation": 26, "Intervention-Grounded Evaluation": 10, "Pre-specified Control Fidelity": 40, "Interactive Action Fidelity": 15, "Data Engine": 2, "Policy Evaluator": 2, "Planner": 12, "Interactive Training Environment": 1 }, "sourceNote": "The 102-benchmark corpus remains checked through August 31, 2026. Taxonomy membership follows Supplementary Fig. S1; 401 target-task records and their fully classified joint Protocol-Metrics-Data coding follow Supplementary Tables S1-S7 and the final September 15, 2026 consistency checklist. Two auxiliary records are retained for traceability and excluded from target-task statistics.", "classificationFingerprint": "a6b483658d12cbbf8012d795b7fc828edee6f025f177537393236e65baf51caf", "recordFingerprint": "a6b483658d12cbbf8012d795b7fc828edee6f025f177537393236e65baf51caf", "fingerprintFields": [ "benchmark", "reference", "year", "domain", "protocol", "metrics", "data", "targets", "subtargets" ], "sourcePdfSha256": "53ae5b5247d71cd832f95c19f7644653b579fb6cef0451ed57f1c4745188e2de", "corpusChanges": { "previousTotal": 106, "currentTotal": 102, "removedBenchmarks": [ "CATER", "NExT-QA", "IntentQA", "VCRBench" ], "updatedRecords": { "WR-Arena": { "protocol": "OL+CL", "metrics": "P+O" } }, "sourcePdfSha256": "c96efe634f70b1297e281e36786dc6a5fedd3b747bf4fc57ad58583c69a50dad" }, "yearBasis": "Benchmark release year as coded in Figure 2 of the final September 15, 2026 manuscript; distinct from formal publication year.", "releaseYearRevision": { "sourcePdf": "main.pdf", "sourcePdfSha256": "53ae5b5247d71cd832f95c19f7644653b579fb6cef0451ed57f1c4745188e2de", "date": "2026-09-15", "changedRecords": 0, "preservedFromPreviousAudit": 102 }, "releaseWindowCounts": { "2018–2021": 6, "2022–2023": 4, "2024": 10, "2025": 30, "2026": 52 }, "publicationMetadata": { "CLEVRER": { "venue": "ICLR", "publicationYear": 2020 }, "CoPhy": { "venue": "ICLR", "publicationYear": 2020 }, "CRAFT": { "venue": "Findings of ACL", "publicationYear": 2022 }, "MMWorld": { "venue": "ICLR", "publicationYear": 2025 }, "WorldLens": { "venue": "CVPR", "publicationYear": 2026 } }, "categoryRecords": { "T1": { "MIND": [ "OL", "P" ], "WorldArena": [ "OL", "P" ], "WorldArena 2.0": [ "OL", "P" ], "ChronoMagic-Bench": [ "OL", "P" ], "WorldScore": [ "OL", "P" ], "VMBench": [ "OL", "P" ], "EWMBench": [ "OL", "P" ], "GameWorld Score": [ "OL", "P" ], "WorldMark": [ "OL", "P" ], "4DWorldBench": [ "OL", "P" ], "WorldLens": [ "OL", "P" ], "DrivingGen": [ "OL", "P" ], "PEDRA": [ "OL", "P" ], "Gen-ViRe": [ "OL", "P" ], "iWorld-Bench": [ "OL", "P" ], "WoW-World-Eval": [ "OL", "P" ], "RBench": [ "OL", "P" ], "PAI-Bench": [ "OL", "P" ], "EZS-Bench": [ "OL", "P" ], "WorldRoamBench": [ "OL", "P" ], "MemoBench": [ "OL", "P" ], "RoboTrustBench": [ "OL", "P" ], "WorldExam": [ "OL", "P" ], "SurgWMBench": [ "OL", "P" ], "H2R-Bench": [ "OL", "P" ], "PlayWorld": [ "CL", "P" ], "XEWorld": [ "OL", "P" ], "HarnessEval-W": [ "OL", "P" ], "WorldEcho": [ "OL", "P" ], "ACWM-Phys": [ "OL", "P" ], "HTEWorld": [ "OL", "P" ], "RigidBench": [ "OL", "P" ], "MagicBench": [ "OL", "P" ], "MoveBench": [ "OL", "P" ], "Omni-WorldBench": [ "OL", "P" ], "OSCBench": [ "OL", "P" ], "T2VWorldBench": [ "OL", "P" ], "WMBench": [ "OL+CL", "P" ], "WorldModelBench": [ "OL", "P" ], "WorldSimBench": [ "OL", "P" ], "Apple-π": [ "OL", "P" ], "TC-Bench": [ "OL", "P" ], "WBench": [ "OL", "P" ], "CrashTwin": [ "OL", "P" ], "EVA-Bench": [ "OL+CL", "P" ], "WR-Arena": [ "OL", "P" ] }, "T2": { "IntPhys": [ "OL", "P" ], "MIND": [ "OL", "P" ], "WorldOlympiad": [ "OL", "P" ], "WorldArena": [ "OL", "P" ], "WorldArena 2.0": [ "OL", "P" ], "WorldScore": [ "OL", "P" ], "EWMBench": [ "OL", "P" ], "GameWorld Score": [ "OL", "P" ], "WorldMark": [ "OL", "P" ], "4DWorldBench": [ "OL", "P" ], "WorldLens": [ "OL", "P" ], "DrivingGen": [ "OL", "P" ], "PEDRA": [ "OL", "P" ], "Gen-ViRe": [ "OL", "P" ], "iWorld-Bench": [ "OL", "P" ], "WoW-World-Eval": [ "OL", "P" ], "RBench": [ "OL", "P" ], "PAI-Bench": [ "OL", "P" ], "EZS-Bench": [ "OL", "P" ], "WorldRoamBench": [ "OL", "P" ], "MemoBench": [ "OL", "P" ], "RoboTrustBench": [ "OL", "P" ], "WorldExam": [ "OL", "P" ], "SurgWMBench": [ "OL", "P" ], "H2R-Bench": [ "OL", "P" ], "PlayWorld": [ "CL", "P" ], "XEWorld": [ "OL", "P" ], "HarnessEval-W": [ "OL", "P" ], "HTEWorld": [ "OL", "P" ], "RigidBench": [ "OL", "P" ], "Omni-WorldBench": [ "OL", "P" ], "OSCBench": [ "OL", "P" ], "WMBench": [ "OL+CL", "P" ], "WorldSimBench": [ "OL", "P" ], "Apple-π": [ "OL", "P" ], "WBench": [ "OL", "P" ], "CrashTwin": [ "OL", "P" ], "EVA-Bench": [ "OL+CL", "P" ], "PDI-Bench": [ "OL", "P" ], "LoopNav": [ "OL", "P" ], "MBench": [ "OL", "P" ], "STEVO-Bench": [ "OL", "P" ], "CausalSpatial": [ "OL", "P" ], "What-If World": [ "OL", "P" ], "HOCA-Bench": [ "OL", "P" ], "AutumnBench": [ "CL", "P+O" ], "MVP": [ "OL", "P" ], "ContactWorld": [ "CL", "O" ], "ScratchWorld": [ "OL", "P" ], "MiraBench": [ "OL", "P" ], "Chess-World-Model": [ "OL", "P" ], "IntPhys 2": [ "OL", "P" ], "SmallWorlds": [ "OL", "P" ], "VBench-2.0": [ "OL", "P" ], "WorldBench": [ "OL", "P" ] }, "T3": { "RoboWM-Bench": [ "OL", "O" ], "MIND": [ "OL", "P" ], "WorldOlympiad": [ "OL", "P" ], "WorldMark": [ "OL", "P" ], "iWorld-Bench": [ "OL", "P" ], "WoW-World-Eval": [ "OL", "P" ], "RBench": [ "OL", "P" ], "WorldRoamBench": [ "OL", "P" ], "MemoBench": [ "OL", "P" ], "PlayWorld": [ "CL", "P" ], "HarnessEval-W": [ "OL", "P" ], "HTEWorld": [ "OL", "P" ], "WMBench": [ "OL+CL", "P" ], "WBench": [ "OL", "P" ], "WR-Arena": [ "OL", "P" ], "LoopNav": [ "OL", "P" ], "MBench": [ "OL", "P" ], "AutumnBench": [ "CL", "P+O" ], "ContactWorld": [ "OL+CL", "P+O" ], "ScratchWorld": [ "OL", "P" ], "Chess-World-Model": [ "OL", "P" ], "SmallWorlds": [ "OL", "P" ], "WorldPrediction": [ "OL", "P" ], "ExPhy": [ "OL", "P" ] }, "T4": { "RoboWM-Bench": [ "OL", "O" ], "IntPhys": [ "OL", "P" ], "CLEVRER": [ "OL", "P" ], "Physion": [ "OL", "P" ], "WorldOlympiad": [ "OL", "P" ], "WorldArena": [ "OL", "P" ], "WorldArena 2.0": [ "OL", "P" ], "VMBench": [ "OL", "P" ], "EWMBench": [ "OL", "P" ], "GameWorld Score": [ "OL", "P" ], "4DWorldBench": [ "OL", "P" ], "WorldLens": [ "OL", "P" ], "DrivingGen": [ "OL", "P" ], "PEDRA": [ "OL", "P" ], "Gen-ViRe": [ "OL", "P" ], "WoW-World-Eval": [ "OL", "P+O" ], "RBench": [ "OL", "P" ], "PAI-Bench": [ "OL", "P" ], "EZS-Bench": [ "OL", "P" ], "WorldRoamBench": [ "OL", "P" ], "MemoBench": [ "OL", "P" ], "RoboTrustBench": [ "OL", "P" ], "WorldExam": [ "OL", "P" ], "H2R-Bench": [ "OL", "P" ], "PlayWorld": [ "CL", "P" ], "XEWorld": [ "OL", "P" ], "HarnessEval-W": [ "OL", "P" ], "ACWM-Phys": [ "OL", "P" ], "HTEWorld": [ "OL", "P" ], "RigidBench": [ "OL", "P" ], "Omni-WorldBench": [ "OL", "P" ], "T2VWorldBench": [ "OL", "P" ], "WMBench": [ "CL", "P" ], "WorldModelBench": [ "OL", "P" ], "WorldSimBench": [ "OL+CL", "P+O" ], "Apple-π": [ "OL", "P" ], "WBench": [ "OL", "P" ], "CrashTwin": [ "OL", "P" ], "PDI-Bench": [ "OL", "P" ], "MBench": [ "OL", "P" ], "STEVO-Bench": [ "OL", "P" ], "CausalSpatial": [ "OL", "P" ], "What-If World": [ "OL", "P" ], "HOCA-Bench": [ "OL", "P" ], "MVP": [ "OL", "P" ], "ContactWorld": [ "CL", "O" ], "MiraBench": [ "OL", "P" ], "IntPhys 2": [ "OL", "P" ], "SmallWorlds": [ "OL", "P" ], "VBench-2.0": [ "OL", "P" ], "WorldBench": [ "OL", "P" ], "ExPhy": [ "OL", "P" ], "CoPhy": [ "OL", "P" ], "PHYRE": [ "OL+CL", "O" ], "CRAFT": [ "OL", "P" ], "Physion++": [ "OL", "P" ], "ComPhy": [ "OL", "P" ], "ContPhy": [ "OL", "P" ], "PhyCoBench": [ "OL", "P" ], "VideoPhy": [ "OL", "P" ], "VideoPhy-2": [ "OL", "P" ], "PhyGenBench": [ "OL", "P" ], "T2VPhysBench": [ "OL", "P" ], "Physics-IQ": [ "OL", "P" ], "PhyWorldBench": [ "OL", "P" ], "Morpheus": [ "OL", "P" ], "DreamGen Bench": [ "OL", "P" ], "PhyGround": [ "OL", "P" ], "Physion-Eval": [ "OL", "P" ], "CRONOS": [ "OL", "P" ], "VACT": [ "OL", "P" ], "PhysicsMind": [ "OL", "P" ], "KineBench": [ "CL", "P+O" ], "ReactSim-Bench": [ "OL", "P" ], "GAUGE": [ "OL", "P" ], "CaliBench": [ "OL", "P" ], "WorldSimProbe": [ "OL", "P" ] }, "T5": { "CLEVRER": [ "OL", "P" ], "Physion": [ "OL", "P" ], "WoW-World-Eval": [ "OL", "P" ], "RBench": [ "OL", "P" ], "PAI-Bench": [ "OL", "P" ], "RoboTrustBench": [ "OL", "P" ], "WorldExam": [ "OL", "P" ], "PlayWorld": [ "CL", "P" ], "HarnessEval-W": [ "OL", "P" ], "T2VWorldBench": [ "OL", "P" ], "WR-Arena": [ "OL", "P" ], "CausalSpatial": [ "OL", "P" ], "What-If World": [ "OL", "P" ], "HOCA-Bench": [ "OL", "P" ], "AutumnBench": [ "CL", "P" ], "MVP": [ "OL", "P" ], "ScratchWorld": [ "OL", "P" ], "MiraBench": [ "OL", "P" ], "WorldPrediction": [ "OL", "P" ], "CoPhy": [ "OL", "P" ], "CRAFT": [ "OL", "P" ], "ComPhy": [ "OL", "P" ], "ContPhy": [ "OL", "P" ], "Physics-IQ": [ "OL", "P" ], "CRONOS": [ "OL", "P" ], "VACT": [ "OL", "P" ], "PhysicsMind": [ "OL", "P" ], "ReactSim-Bench": [ "OL", "P" ], "WorldSimProbe": [ "OL", "P" ], "Causal-VidQA": [ "OL", "P" ], "ACQUIRED": [ "OL", "P" ], "MMWorld": [ "OL", "P" ], "CausalVQA": [ "OL", "P" ] }, "S5": { "WorldArena": [ "OL", "P" ], "WorldScore": [ "OL", "P" ], "EWMBench": [ "OL", "P" ], "GameWorld Score": [ "OL", "P" ], "4DWorldBench": [ "OL", "P" ], "DrivingGen": [ "OL", "P" ], "WoW-World-Eval": [ "OL", "P+O" ], "RBench": [ "OL", "P" ], "PAI-Bench": [ "OL", "P" ], "EZS-Bench": [ "OL", "P" ], "MemoBench": [ "OL", "P" ], "RoboTrustBench": [ "OL", "P" ], "WorldExam": [ "OL", "P" ], "H2R-Bench": [ "OL", "P" ], "XEWorld": [ "OL", "P" ], "HarnessEval-W": [ "OL", "P" ], "WorldEcho": [ "OL", "P" ], "MagicBench": [ "OL", "P" ], "MoveBench": [ "OL", "P" ], "Omni-WorldBench": [ "OL", "P" ], "OSCBench": [ "OL", "P" ], "WorldModelBench": [ "OL", "P" ], "TC-Bench": [ "OL", "P" ], "MBench": [ "OL", "P" ], "STEVO-Bench": [ "OL", "P" ], "What-If World": [ "OL", "P" ], "ScratchWorld": [ "OL", "P" ], "MiraBench": [ "OL", "P" ], "Chess-World-Model": [ "OL", "P" ], "VBench-2.0": [ "OL", "P" ], "VideoPhy": [ "OL", "P" ], "VideoPhy-2": [ "OL", "P" ], "PhyGenBench": [ "OL", "P" ], "PhyWorldBench": [ "OL", "P" ], "DreamGen Bench": [ "OL", "P" ], "VACT": [ "OL", "P" ], "KineBench": [ "CL", "O" ], "WorldSimProbe": [ "OL", "P" ], "StoryEval": [ "OL", "P" ], "ACT-Bench": [ "OL", "P" ] }, "S6": { "RoboWM-Bench": [ "OL", "O" ], "MIND": [ "OL", "P" ], "WorldOlympiad": [ "OL", "P" ], "WorldArena 2.0": [ "OL", "P" ], "WorldMark": [ "OL", "P" ], "iWorld-Bench": [ "OL", "P" ], "WorldRoamBench": [ "OL", "P" ], "PlayWorld": [ "CL", "P" ], "ACWM-Phys": [ "OL", "P" ], "HTEWorld": [ "OL", "P" ], "WMBench": [ "OL+CL", "P" ], "WorldSimBench": [ "OL+CL", "P+O" ], "WBench": [ "OL", "P" ], "WR-Arena": [ "OL", "P" ], "ReactSim-Bench": [ "OL", "P" ] }, "S7": { "WorldArena": [ "OL", "O" ], "WorldArena 2.0": [ "OL", "O" ] }, "S8": { "WorldArena": [ "CL", "O" ], "WMBench": [ "CL", "O" ] }, "S9": { "RoboWM-Bench": [ "OL", "O" ], "World-in-World": [ "CL", "O" ], "WorldArena": [ "CL", "O" ], "WorldArena 2.0": [ "CL", "O" ], "WorldLens": [ "OL+CL", "O" ], "WoW-World-Eval": [ "OL", "O" ], "WorldSimBench": [ "CL", "O" ], "EVA-Bench": [ "OL+CL", "O" ], "WR-Arena": [ "CL", "O" ], "AutumnBench": [ "CL", "O" ], "ContactWorld": [ "CL", "O" ], "KineBench": [ "CL", "O" ] }, "S10": { "WorldArena 2.0": [ "CL", "O" ] } }, "evaluationTrackFingerprint": "57506b97cd7eb30d66632bb51fef231635ad01661311b674294139332d4b9808", "codingScope": "Each evaluationRecords item is one observed Protocol-Metrics-Data combination within a target or downstream role. Filters match all selected evidence dimensions within the same combination; selections within a filter group use OR and selections across groups use AND. Benchmark-level records contain unions for overview only.", "codingRevision": { "mainSourcePdf": "main.pdf", "mainSourcePdfSha256": "53ae5b5247d71cd832f95c19f7644653b579fb6cef0451ed57f1c4745188e2de", "mainSourceArchive": "Main_Manuscript_LaTeX.zip", "mainSourceArchiveSha256": "dad0477f487c44f847dd7a988677178f65025329d491810fe0ad76bb6738bd9a", "supplementarySourcePdf": "A Survey of World Model Benchmarks - Supplementary Material.pdf", "supplementarySourcePdfSha256": "af6a8440614fe85d9505d5c6ec2b9283c16ea32d0078ed8b7be3492b26923d41", "codingChecklist": "网页逐项修改清单(1).md", "codingChecklistSha256": "b6ec17d6c68186f62aab9edb4194be8377ea6d71e232a1a5bf53a1ff815be1a4", "date": "2026-09-15", "targetRoleParentRows": 307, "targetTaskRecords": 401, "auxiliaryRecords": 2, "displayCombinations": 369, "changedTargetRoleRows": 23, "changedBenchmarkOverviewRecords": 31, "preservedReleaseYears": 102 }, "sourceSupplementaryPdfSha256": "af6a8440614fe85d9505d5c6ec2b9283c16ea32d0078ed8b7be3492b26923d41", "evaluationRecords": [ { "id": "EC0001", "benchmark": "MIND", "scope": "T1", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S1-042" ], "sourceTable": "S1", "sourcePages": [ 5 ] }, { "id": "EC0002", "benchmark": "WorldArena", "scope": "T1", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S1-057" ], "sourceTable": "S1", "sourcePages": [ 6 ] }, { "id": "EC0003", "benchmark": "WorldArena 2.0", "scope": "T1", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskIds": [ "S1-059" ], "sourceTable": "S1", "sourcePages": [ 6 ] }, { "id": "EC0004", "benchmark": "WorldArena 2.0", "scope": "T1", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S1-058" ], "sourceTable": "S1", "sourcePages": [ 6 ] }, { "id": "EC0005", "benchmark": "ChronoMagic-Bench", "scope": "T1", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskIds": [ "S1-001" ], "sourceTable": "S1", "sourcePages": [ 4 ] }, { "id": "EC0006", "benchmark": "WorldScore", "scope": "T1", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskIds": [ "S1-028" ], "sourceTable": "S1", "sourcePages": [ 5 ] }, { "id": "EC0007", "benchmark": "WorldScore", "scope": "T1", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S1-029" ], "sourceTable": "S1", "sourcePages": [ 5 ] }, { "id": "EC0008", "benchmark": "VMBench", "scope": "T1", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskIds": [ "S1-024" ], "sourceTable": "S1", "sourcePages": [ 5 ] }, { "id": "EC0009", "benchmark": "EWMBench", "scope": "T1", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskIds": [ "S1-014" ], "sourceTable": "S1", "sourcePages": [ 4 ] }, { "id": "EC0010", "benchmark": "GameWorld Score", "scope": "T1", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S1-015" ], "sourceTable": "S1", "sourcePages": [ 4 ] }, { "id": "EC0011", "benchmark": "WorldMark", "scope": "T1", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S1-063" ], "sourceTable": "S1", "sourcePages": [ 6 ] }, { "id": "EC0012", "benchmark": "4DWorldBench", "scope": "T1", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskIds": [ "S1-011" ], "sourceTable": "S1", "sourcePages": [ 4 ] }, { "id": "EC0013", "benchmark": "4DWorldBench", "scope": "T1", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskIds": [ "S1-010" ], "sourceTable": "S1", "sourcePages": [ 4 ] }, { "id": "EC0014", "benchmark": "4DWorldBench", "scope": "T1", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S1-012", "S1-013" ], "sourceTable": "S1", "sourcePages": [ 4 ] }, { "id": "EC0015", "benchmark": "WorldLens", "scope": "T1", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskIds": [ "S1-025" ], "sourceTable": "S1", "sourcePages": [ 5 ] }, { "id": "EC0016", "benchmark": "DrivingGen", "scope": "T1", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskIds": [ "S1-033", "S1-034" ], "sourceTable": "S1", "sourcePages": [ 5 ] }, { "id": "EC0017", "benchmark": "PEDRA", "scope": "T1", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskIds": [ "S1-021" ], "sourceTable": "S1", "sourcePages": [ 4 ] }, { "id": "EC0018", "benchmark": "PEDRA", "scope": "T1", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskIds": [ "S1-022" ], "sourceTable": "S1", "sourcePages": [ 4 ] }, { "id": "EC0019", "benchmark": "Gen-ViRe", "scope": "T1", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S1-016" ], "sourceTable": "S1", "sourcePages": [ 4 ] }, { "id": "EC0020", "benchmark": "iWorld-Bench", "scope": "T1", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S1-040" ], "sourceTable": "S1", "sourcePages": [ 5 ] }, { "id": "EC0021", "benchmark": "WoW-World-Eval", "scope": "T1", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S1-065" ], "sourceTable": "S1", "sourcePages": [ 6 ] }, { "id": "EC0022", "benchmark": "RBench", "scope": "T1", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskIds": [ "S1-048" ], "sourceTable": "S1", "sourcePages": [ 6 ] }, { "id": "EC0023", "benchmark": "PAI-Bench", "scope": "T1", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskIds": [ "S1-020" ], "sourceTable": "S1", "sourcePages": [ 4 ] }, { "id": "EC0024", "benchmark": "PAI-Bench", "scope": "T1", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskIds": [ "S1-019" ], "sourceTable": "S1", "sourcePages": [ 4 ] }, { "id": "EC0025", "benchmark": "EZS-Bench", "scope": "T1", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S1-035" ], "sourceTable": "S1", "sourcePages": [ 5 ] }, { "id": "EC0026", "benchmark": "WorldRoamBench", "scope": "T1", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S1-064" ], "sourceTable": "S1", "sourcePages": [ 6 ] }, { "id": "EC0027", "benchmark": "MemoBench", "scope": "T1", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S1-041" ], "sourceTable": "S1", "sourcePages": [ 5 ] }, { "id": "EC0028", "benchmark": "RoboTrustBench", "scope": "T1", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S1-050" ], "sourceTable": "S1", "sourcePages": [ 6 ] }, { "id": "EC0029", "benchmark": "WorldExam", "scope": "T1", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskIds": [ "S1-062" ], "sourceTable": "S1", "sourcePages": [ 6 ] }, { "id": "EC0030", "benchmark": "WorldExam", "scope": "T1", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S1-061" ], "sourceTable": "S1", "sourcePages": [ 6 ] }, { "id": "EC0031", "benchmark": "SurgWMBench", "scope": "T1", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskIds": [ "S1-051", "S1-052" ], "sourceTable": "S1", "sourcePages": [ 6 ] }, { "id": "EC0032", "benchmark": "H2R-Bench", "scope": "T1", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskIds": [ "S1-036" ], "sourceTable": "S1", "sourcePages": [ 5 ] }, { "id": "EC0033", "benchmark": "H2R-Bench", "scope": "T1", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S1-037" ], "sourceTable": "S1", "sourcePages": [ 5 ] }, { "id": "EC0034", "benchmark": "PlayWorld", "scope": "T1", "protocol": "CL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S1-047" ], "sourceTable": "S1", "sourcePages": [ 5 ] }, { "id": "EC0035", "benchmark": "XEWorld", "scope": "T1", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S1-067" ], "sourceTable": "S1", "sourcePages": [ 6 ] }, { "id": "EC0036", "benchmark": "HarnessEval-W", "scope": "T1", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskIds": [ "S1-038" ], "sourceTable": "S1", "sourcePages": [ 5 ] }, { "id": "EC0037", "benchmark": "WorldEcho", "scope": "T1", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S1-060" ], "sourceTable": "S1", "sourcePages": [ 6 ] }, { "id": "EC0038", "benchmark": "ACWM-Phys", "scope": "T1", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S1-030" ], "sourceTable": "S1", "sourcePages": [ 5 ] }, { "id": "EC0039", "benchmark": "HTEWorld", "scope": "T1", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S1-039" ], "sourceTable": "S1", "sourcePages": [ 5 ] }, { "id": "EC0040", "benchmark": "RigidBench", "scope": "T1", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S1-049" ], "sourceTable": "S1", "sourcePages": [ 6 ] }, { "id": "EC0041", "benchmark": "MagicBench", "scope": "T1", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskIds": [ "S1-017" ], "sourceTable": "S1", "sourcePages": [ 4 ] }, { "id": "EC0042", "benchmark": "MoveBench", "scope": "T1", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskIds": [ "S1-018" ], "sourceTable": "S1", "sourcePages": [ 4 ] }, { "id": "EC0043", "benchmark": "Omni-WorldBench", "scope": "T1", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskIds": [ "S1-043" ], "sourceTable": "S1", "sourcePages": [ 5 ] }, { "id": "EC0044", "benchmark": "Omni-WorldBench", "scope": "T1", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S1-044", "S1-045" ], "sourceTable": "S1", "sourcePages": [ 5 ] }, { "id": "EC0045", "benchmark": "OSCBench", "scope": "T1", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskIds": [ "S1-046" ], "sourceTable": "S1", "sourcePages": [ 5 ] }, { "id": "EC0046", "benchmark": "T2VWorldBench", "scope": "T1", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskIds": [ "S1-023" ], "sourceTable": "S1", "sourcePages": [ 4 ] }, { "id": "EC0047", "benchmark": "WMBench", "scope": "T1", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskIds": [ "S1-055", "S1-056" ], "sourceTable": "S1", "sourcePages": [ 6 ] }, { "id": "EC0048", "benchmark": "WMBench", "scope": "T1", "protocol": "CL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S1-054" ], "sourceTable": "S1", "sourcePages": [ 6 ] }, { "id": "EC0049", "benchmark": "WorldModelBench", "scope": "T1", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskIds": [ "S1-026" ], "sourceTable": "S1", "sourcePages": [ 5 ] }, { "id": "EC0050", "benchmark": "WorldModelBench", "scope": "T1", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S1-027" ], "sourceTable": "S1", "sourcePages": [ 5 ] }, { "id": "EC0051", "benchmark": "WorldSimBench", "scope": "T1", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskIds": [ "S1-008", "S1-009" ], "sourceTable": "S1", "sourcePages": [ 4 ] }, { "id": "EC0052", "benchmark": "WorldSimBench", "scope": "T1", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S1-007" ], "sourceTable": "S1", "sourcePages": [ 4 ] }, { "id": "EC0053", "benchmark": "WorldSimBench", "scope": "T1", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskIds": [ "S1-006" ], "sourceTable": "S1", "sourcePages": [ 4 ] }, { "id": "EC0054", "benchmark": "Apple-π", "scope": "T1", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S1-031" ], "sourceTable": "S1", "sourcePages": [ 5 ] }, { "id": "EC0055", "benchmark": "TC-Bench", "scope": "T1", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskIds": [ "S1-005" ], "sourceTable": "S1", "sourcePages": [ 4 ] }, { "id": "EC0056", "benchmark": "TC-Bench", "scope": "T1", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskIds": [ "S1-004" ], "sourceTable": "S1", "sourcePages": [ 4 ] }, { "id": "EC0057", "benchmark": "WBench", "scope": "T1", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S1-053" ], "sourceTable": "S1", "sourcePages": [ 6 ] }, { "id": "EC0058", "benchmark": "CrashTwin", "scope": "T1", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S1-032" ], "sourceTable": "S1", "sourcePages": [ 5 ] }, { "id": "EC0059", "benchmark": "EVA-Bench", "scope": "T1", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S1-002" ], "sourceTable": "S1", "sourcePages": [ 4 ] }, { "id": "EC0060", "benchmark": "EVA-Bench", "scope": "T1", "protocol": "CL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S1-003" ], "sourceTable": "S1", "sourcePages": [ 4 ] }, { "id": "EC0061", "benchmark": "WR-Arena", "scope": "T1", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S1-066" ], "sourceTable": "S1", "sourcePages": [ 6 ] }, { "id": "EC0062", "benchmark": "IntPhys", "scope": "T2", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S2-001" ], "sourceTable": "S2", "sourcePages": [ 7 ] }, { "id": "EC0063", "benchmark": "MIND", "scope": "T2", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S2-046" ], "sourceTable": "S2", "sourcePages": [ 8 ] }, { "id": "EC0064", "benchmark": "WorldOlympiad", "scope": "T2", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S2-072" ], "sourceTable": "S2", "sourcePages": [ 10 ] }, { "id": "EC0065", "benchmark": "WorldArena", "scope": "T2", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S2-066" ], "sourceTable": "S2", "sourcePages": [ 9 ] }, { "id": "EC0066", "benchmark": "WorldArena 2.0", "scope": "T2", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskIds": [ "S2-068" ], "sourceTable": "S2", "sourcePages": [ 9 ] }, { "id": "EC0067", "benchmark": "WorldArena 2.0", "scope": "T2", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S2-067" ], "sourceTable": "S2", "sourcePages": [ 9 ] }, { "id": "EC0068", "benchmark": "WorldScore", "scope": "T2", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskIds": [ "S2-027" ], "sourceTable": "S2", "sourcePages": [ 8 ] }, { "id": "EC0069", "benchmark": "WorldScore", "scope": "T2", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S2-028" ], "sourceTable": "S2", "sourcePages": [ 8 ] }, { "id": "EC0070", "benchmark": "EWMBench", "scope": "T2", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskIds": [ "S2-014" ], "sourceTable": "S2", "sourcePages": [ 7 ] }, { "id": "EC0071", "benchmark": "GameWorld Score", "scope": "T2", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S2-015" ], "sourceTable": "S2", "sourcePages": [ 7 ] }, { "id": "EC0072", "benchmark": "WorldMark", "scope": "T2", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S2-071" ], "sourceTable": "S2", "sourcePages": [ 10 ] }, { "id": "EC0073", "benchmark": "4DWorldBench", "scope": "T2", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskIds": [ "S2-009" ], "sourceTable": "S2", "sourcePages": [ 7 ] }, { "id": "EC0074", "benchmark": "4DWorldBench", "scope": "T2", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskIds": [ "S2-008" ], "sourceTable": "S2", "sourcePages": [ 7 ] }, { "id": "EC0075", "benchmark": "4DWorldBench", "scope": "T2", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S2-010", "S2-011" ], "sourceTable": "S2", "sourcePages": [ 7 ] }, { "id": "EC0076", "benchmark": "WorldLens", "scope": "T2", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskIds": [ "S2-026" ], "sourceTable": "S2", "sourcePages": [ 8 ] }, { "id": "EC0077", "benchmark": "DrivingGen", "scope": "T2", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskIds": [ "S2-035", "S2-036" ], "sourceTable": "S2", "sourcePages": [ 8 ] }, { "id": "EC0078", "benchmark": "PEDRA", "scope": "T2", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskIds": [ "S2-022" ], "sourceTable": "S2", "sourcePages": [ 7 ] }, { "id": "EC0079", "benchmark": "PEDRA", "scope": "T2", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskIds": [ "S2-023" ], "sourceTable": "S2", "sourcePages": [ 7 ] }, { "id": "EC0080", "benchmark": "Gen-ViRe", "scope": "T2", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S2-016" ], "sourceTable": "S2", "sourcePages": [ 7 ] }, { "id": "EC0081", "benchmark": "iWorld-Bench", "scope": "T2", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S2-043" ], "sourceTable": "S2", "sourcePages": [ 8 ] }, { "id": "EC0082", "benchmark": "WoW-World-Eval", "scope": "T2", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S2-074" ], "sourceTable": "S2", "sourcePages": [ 10 ] }, { "id": "EC0083", "benchmark": "RBench", "scope": "T2", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskIds": [ "S2-054" ], "sourceTable": "S2", "sourcePages": [ 9 ] }, { "id": "EC0084", "benchmark": "PAI-Bench", "scope": "T2", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskIds": [ "S2-020", "S2-021" ], "sourceTable": "S2", "sourcePages": [ 7 ] }, { "id": "EC0085", "benchmark": "EZS-Bench", "scope": "T2", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S2-037" ], "sourceTable": "S2", "sourcePages": [ 8 ] }, { "id": "EC0086", "benchmark": "WorldRoamBench", "scope": "T2", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S2-073" ], "sourceTable": "S2", "sourcePages": [ 10 ] }, { "id": "EC0087", "benchmark": "MemoBench", "scope": "T2", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S2-045" ], "sourceTable": "S2", "sourcePages": [ 8 ] }, { "id": "EC0088", "benchmark": "RoboTrustBench", "scope": "T2", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S2-056" ], "sourceTable": "S2", "sourcePages": [ 9 ] }, { "id": "EC0089", "benchmark": "WorldExam", "scope": "T2", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S2-070" ], "sourceTable": "S2", "sourcePages": [ 10 ] }, { "id": "EC0090", "benchmark": "SurgWMBench", "scope": "T2", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskIds": [ "S2-059", "S2-060", "S2-061" ], "sourceTable": "S2", "sourcePages": [ 9 ] }, { "id": "EC0091", "benchmark": "H2R-Bench", "scope": "T2", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskIds": [ "S2-038" ], "sourceTable": "S2", "sourcePages": [ 8 ] }, { "id": "EC0092", "benchmark": "H2R-Bench", "scope": "T2", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S2-039" ], "sourceTable": "S2", "sourcePages": [ 8 ] }, { "id": "EC0093", "benchmark": "PlayWorld", "scope": "T2", "protocol": "CL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S2-053" ], "sourceTable": "S2", "sourcePages": [ 9 ] }, { "id": "EC0094", "benchmark": "XEWorld", "scope": "T2", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S2-075" ], "sourceTable": "S2", "sourcePages": [ 10 ] }, { "id": "EC0095", "benchmark": "HarnessEval-W", "scope": "T2", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskIds": [ "S2-040" ], "sourceTable": "S2", "sourcePages": [ 8 ] }, { "id": "EC0096", "benchmark": "HTEWorld", "scope": "T2", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S2-042" ], "sourceTable": "S2", "sourcePages": [ 8 ] }, { "id": "EC0097", "benchmark": "RigidBench", "scope": "T2", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S2-055" ], "sourceTable": "S2", "sourcePages": [ 9 ] }, { "id": "EC0098", "benchmark": "Omni-WorldBench", "scope": "T2", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskIds": [ "S2-048" ], "sourceTable": "S2", "sourcePages": [ 9 ] }, { "id": "EC0099", "benchmark": "Omni-WorldBench", "scope": "T2", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S2-049", "S2-050" ], "sourceTable": "S2", "sourcePages": [ 9 ] }, { "id": "EC0100", "benchmark": "OSCBench", "scope": "T2", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskIds": [ "S2-051" ], "sourceTable": "S2", "sourcePages": [ 9 ] }, { "id": "EC0101", "benchmark": "WMBench", "scope": "T2", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskIds": [ "S2-065" ], "sourceTable": "S2", "sourcePages": [ 9 ] }, { "id": "EC0102", "benchmark": "WMBench", "scope": "T2", "protocol": "CL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S2-064" ], "sourceTable": "S2", "sourcePages": [ 9 ] }, { "id": "EC0103", "benchmark": "WorldSimBench", "scope": "T2", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskIds": [ "S2-006", "S2-007" ], "sourceTable": "S2", "sourcePages": [ 7 ] }, { "id": "EC0104", "benchmark": "WorldSimBench", "scope": "T2", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S2-005" ], "sourceTable": "S2", "sourcePages": [ 7 ] }, { "id": "EC0105", "benchmark": "WorldSimBench", "scope": "T2", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskIds": [ "S2-004" ], "sourceTable": "S2", "sourcePages": [ 7 ] }, { "id": "EC0106", "benchmark": "Apple-π", "scope": "T2", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S2-029" ], "sourceTable": "S2", "sourcePages": [ 8 ] }, { "id": "EC0107", "benchmark": "WBench", "scope": "T2", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S2-062" ], "sourceTable": "S2", "sourcePages": [ 9 ] }, { "id": "EC0108", "benchmark": "CrashTwin", "scope": "T2", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S2-034" ], "sourceTable": "S2", "sourcePages": [ 8 ] }, { "id": "EC0109", "benchmark": "EVA-Bench", "scope": "T2", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S2-002" ], "sourceTable": "S2", "sourcePages": [ 7 ] }, { "id": "EC0110", "benchmark": "EVA-Bench", "scope": "T2", "protocol": "CL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S2-003" ], "sourceTable": "S2", "sourcePages": [ 7 ] }, { "id": "EC0111", "benchmark": "PDI-Bench", "scope": "T2", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskIds": [ "S2-052" ], "sourceTable": "S2", "sourcePages": [ 9 ] }, { "id": "EC0112", "benchmark": "LoopNav", "scope": "T2", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S2-018" ], "sourceTable": "S2", "sourcePages": [ 7 ] }, { "id": "EC0113", "benchmark": "MBench", "scope": "T2", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskIds": [ "S2-044" ], "sourceTable": "S2", "sourcePages": [ 8 ] }, { "id": "EC0114", "benchmark": "STEVO-Bench", "scope": "T2", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskIds": [ "S2-058" ], "sourceTable": "S2", "sourcePages": [ 9 ] }, { "id": "EC0115", "benchmark": "CausalSpatial", "scope": "T2", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S2-030" ], "sourceTable": "S2", "sourcePages": [ 8 ] }, { "id": "EC0116", "benchmark": "What-If World", "scope": "T2", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskIds": [ "S2-063" ], "sourceTable": "S2", "sourcePages": [ 9 ] }, { "id": "EC0117", "benchmark": "HOCA-Bench", "scope": "T2", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskIds": [ "S2-041" ], "sourceTable": "S2", "sourcePages": [ 8 ] }, { "id": "EC0118", "benchmark": "AutumnBench", "scope": "T2", "protocol": "CL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S2-012" ], "sourceTable": "S2", "sourcePages": [ 7 ] }, { "id": "EC0119", "benchmark": "AutumnBench", "scope": "T2", "protocol": "CL", "metric": "O", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S2-013" ], "sourceTable": "S2", "sourcePages": [ 7 ] }, { "id": "EC0120", "benchmark": "MVP", "scope": "T2", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S2-019" ], "sourceTable": "S2", "sourcePages": [ 7 ] }, { "id": "EC0121", "benchmark": "ContactWorld", "scope": "T2", "protocol": "CL", "metric": "O", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S2-033" ], "sourceTable": "S2", "sourcePages": [ 8 ] }, { "id": "EC0122", "benchmark": "ScratchWorld", "scope": "T2", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S2-057" ], "sourceTable": "S2", "sourcePages": [ 9 ] }, { "id": "EC0123", "benchmark": "MiraBench", "scope": "T2", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S2-047" ], "sourceTable": "S2", "sourcePages": [ 9 ] }, { "id": "EC0124", "benchmark": "Chess-World-Model", "scope": "T2", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S2-031", "S2-032" ], "sourceTable": "S2", "sourcePages": [ 8 ] }, { "id": "EC0125", "benchmark": "IntPhys 2", "scope": "T2", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S2-017" ], "sourceTable": "S2", "sourcePages": [ 7 ] }, { "id": "EC0126", "benchmark": "SmallWorlds", "scope": "T2", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S2-024" ], "sourceTable": "S2", "sourcePages": [ 8 ] }, { "id": "EC0127", "benchmark": "VBench-2.0", "scope": "T2", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskIds": [ "S2-025" ], "sourceTable": "S2", "sourcePages": [ 8 ] }, { "id": "EC0128", "benchmark": "WorldBench", "scope": "T2", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S2-069" ], "sourceTable": "S2", "sourcePages": [ 9 ] }, { "id": "EC0129", "benchmark": "RoboWM-Bench", "scope": "T3", "protocol": "OL", "metric": "O", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S3-019" ], "sourceTable": "S3", "sourcePages": [ 11 ] }, { "id": "EC0130", "benchmark": "MIND", "scope": "T3", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S3-016" ], "sourceTable": "S3", "sourcePages": [ 11 ] }, { "id": "EC0131", "benchmark": "WorldOlympiad", "scope": "T3", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S3-025" ], "sourceTable": "S3", "sourcePages": [ 12 ] }, { "id": "EC0132", "benchmark": "WorldMark", "scope": "T3", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S3-024" ], "sourceTable": "S3", "sourcePages": [ 12 ] }, { "id": "EC0133", "benchmark": "iWorld-Bench", "scope": "T3", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S3-013" ], "sourceTable": "S3", "sourcePages": [ 11 ] }, { "id": "EC0134", "benchmark": "WoW-World-Eval", "scope": "T3", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S3-027" ], "sourceTable": "S3", "sourcePages": [ 12 ] }, { "id": "EC0135", "benchmark": "RBench", "scope": "T3", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskIds": [ "S3-018" ], "sourceTable": "S3", "sourcePages": [ 11 ] }, { "id": "EC0136", "benchmark": "WorldRoamBench", "scope": "T3", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S3-026" ], "sourceTable": "S3", "sourcePages": [ 12 ] }, { "id": "EC0137", "benchmark": "MemoBench", "scope": "T3", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S3-015" ], "sourceTable": "S3", "sourcePages": [ 11 ] }, { "id": "EC0138", "benchmark": "PlayWorld", "scope": "T3", "protocol": "CL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S3-017" ], "sourceTable": "S3", "sourcePages": [ 11 ] }, { "id": "EC0139", "benchmark": "HarnessEval-W", "scope": "T3", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskIds": [ "S3-011" ], "sourceTable": "S3", "sourcePages": [ 11 ] }, { "id": "EC0140", "benchmark": "HTEWorld", "scope": "T3", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S3-012" ], "sourceTable": "S3", "sourcePages": [ 11 ] }, { "id": "EC0141", "benchmark": "WMBench", "scope": "T3", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskIds": [ "S3-023" ], "sourceTable": "S3", "sourcePages": [ 11 ] }, { "id": "EC0142", "benchmark": "WMBench", "scope": "T3", "protocol": "CL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S3-022" ], "sourceTable": "S3", "sourcePages": [ 11 ] }, { "id": "EC0143", "benchmark": "WBench", "scope": "T3", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S3-021" ], "sourceTable": "S3", "sourcePages": [ 11 ] }, { "id": "EC0144", "benchmark": "WR-Arena", "scope": "T3", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S3-028" ], "sourceTable": "S3", "sourcePages": [ 12 ] }, { "id": "EC0145", "benchmark": "LoopNav", "scope": "T3", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S3-003" ], "sourceTable": "S3", "sourcePages": [ 11 ] }, { "id": "EC0146", "benchmark": "MBench", "scope": "T3", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskIds": [ "S3-014" ], "sourceTable": "S3", "sourcePages": [ 11 ] }, { "id": "EC0147", "benchmark": "AutumnBench", "scope": "T3", "protocol": "CL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S3-001" ], "sourceTable": "S3", "sourcePages": [ 11 ] }, { "id": "EC0148", "benchmark": "AutumnBench", "scope": "T3", "protocol": "CL", "metric": "O", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S3-002" ], "sourceTable": "S3", "sourcePages": [ 11 ] }, { "id": "EC0149", "benchmark": "ContactWorld", "scope": "T3", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S3-008" ], "sourceTable": "S3", "sourcePages": [ 11 ] }, { "id": "EC0150", "benchmark": "ContactWorld", "scope": "T3", "protocol": "CL", "metric": "O", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S3-009" ], "sourceTable": "S3", "sourcePages": [ 11 ] }, { "id": "EC0151", "benchmark": "ScratchWorld", "scope": "T3", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S3-020" ], "sourceTable": "S3", "sourcePages": [ 11 ] }, { "id": "EC0152", "benchmark": "Chess-World-Model", "scope": "T3", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S3-006", "S3-007" ], "sourceTable": "S3", "sourcePages": [ 11 ] }, { "id": "EC0153", "benchmark": "SmallWorlds", "scope": "T3", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S3-004" ], "sourceTable": "S3", "sourcePages": [ 11 ] }, { "id": "EC0154", "benchmark": "WorldPrediction", "scope": "T3", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskIds": [ "S3-005" ], "sourceTable": "S3", "sourcePages": [ 11 ] }, { "id": "EC0155", "benchmark": "ExPhy", "scope": "T3", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S3-010" ], "sourceTable": "S3", "sourcePages": [ 11 ] }, { "id": "EC0156", "benchmark": "RoboWM-Bench", "scope": "T4", "protocol": "OL", "metric": "O", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S4-086" ], "sourceTable": "S4", "sourcePages": [ 16 ] }, { "id": "EC0157", "benchmark": "IntPhys", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S4-001" ], "sourceTable": "S4", "sourcePages": [ 13 ] }, { "id": "EC0158", "benchmark": "CLEVRER", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S4-002" ], "sourceTable": "S4", "sourcePages": [ 13 ] }, { "id": "EC0159", "benchmark": "Physion", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S4-007" ], "sourceTable": "S4", "sourcePages": [ 13 ] }, { "id": "EC0160", "benchmark": "WorldOlympiad", "scope": "T4", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S4-096" ], "sourceTable": "S4", "sourcePages": [ 17 ] }, { "id": "EC0161", "benchmark": "WorldArena", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S4-091" ], "sourceTable": "S4", "sourcePages": [ 16 ] }, { "id": "EC0162", "benchmark": "WorldArena 2.0", "scope": "T4", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskIds": [ "S4-093" ], "sourceTable": "S4", "sourcePages": [ 16 ] }, { "id": "EC0163", "benchmark": "WorldArena 2.0", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S4-092" ], "sourceTable": "S4", "sourcePages": [ 16 ] }, { "id": "EC0164", "benchmark": "VMBench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskIds": [ "S4-044" ], "sourceTable": "S4", "sourcePages": [ 14 ] }, { "id": "EC0165", "benchmark": "EWMBench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskIds": [ "S4-022" ], "sourceTable": "S4", "sourcePages": [ 13 ] }, { "id": "EC0166", "benchmark": "GameWorld Score", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S4-023" ], "sourceTable": "S4", "sourcePages": [ 13 ] }, { "id": "EC0167", "benchmark": "4DWorldBench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskIds": [ "S4-019", "S4-020" ], "sourceTable": "S4", "sourcePages": [ 13 ] }, { "id": "EC0168", "benchmark": "4DWorldBench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskIds": [ "S4-018" ], "sourceTable": "S4", "sourcePages": [ 13 ] }, { "id": "EC0169", "benchmark": "WorldLens", "scope": "T4", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskIds": [ "S4-045" ], "sourceTable": "S4", "sourcePages": [ 14 ] }, { "id": "EC0170", "benchmark": "DrivingGen", "scope": "T4", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskIds": [ "S4-055", "S4-056" ], "sourceTable": "S4", "sourcePages": [ 15 ] }, { "id": "EC0171", "benchmark": "PEDRA", "scope": "T4", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskIds": [ "S4-033" ], "sourceTable": "S4", "sourcePages": [ 14 ] }, { "id": "EC0172", "benchmark": "PEDRA", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskIds": [ "S4-034" ], "sourceTable": "S4", "sourcePages": [ 14 ] }, { "id": "EC0173", "benchmark": "Gen-ViRe", "scope": "T4", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S4-024" ], "sourceTable": "S4", "sourcePages": [ 13 ] }, { "id": "EC0174", "benchmark": "WoW-World-Eval", "scope": "T4", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S4-099" ], "sourceTable": "S4", "sourcePages": [ 17 ] }, { "id": "EC0175", "benchmark": "WoW-World-Eval", "scope": "T4", "protocol": "OL", "metric": "O", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S4-100" ], "sourceTable": "S4", "sourcePages": [ 17 ] }, { "id": "EC0176", "benchmark": "RBench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskIds": [ "S4-082" ], "sourceTable": "S4", "sourcePages": [ 16 ] }, { "id": "EC0177", "benchmark": "PAI-Bench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskIds": [ "S4-030", "S4-031", "S4-032" ], "sourceTable": "S4", "sourcePages": [ 14 ] }, { "id": "EC0178", "benchmark": "PAI-Bench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskIds": [ "S4-029" ], "sourceTable": "S4", "sourcePages": [ 14 ] }, { "id": "EC0179", "benchmark": "EZS-Bench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S4-058" ], "sourceTable": "S4", "sourcePages": [ 15 ] }, { "id": "EC0180", "benchmark": "WorldRoamBench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S4-097" ], "sourceTable": "S4", "sourcePages": [ 17 ] }, { "id": "EC0181", "benchmark": "MemoBench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S4-070" ], "sourceTable": "S4", "sourcePages": [ 15 ] }, { "id": "EC0182", "benchmark": "RoboTrustBench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S4-085" ], "sourceTable": "S4", "sourcePages": [ 16 ] }, { "id": "EC0183", "benchmark": "WorldExam", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskIds": [ "S4-095" ], "sourceTable": "S4", "sourcePages": [ 17 ] }, { "id": "EC0184", "benchmark": "H2R-Bench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskIds": [ "S4-061" ], "sourceTable": "S4", "sourcePages": [ 15 ] }, { "id": "EC0185", "benchmark": "H2R-Bench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S4-062" ], "sourceTable": "S4", "sourcePages": [ 15 ] }, { "id": "EC0186", "benchmark": "PlayWorld", "scope": "T4", "protocol": "CL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S4-081" ], "sourceTable": "S4", "sourcePages": [ 16 ] }, { "id": "EC0187", "benchmark": "XEWorld", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S4-101" ], "sourceTable": "S4", "sourcePages": [ 17 ] }, { "id": "EC0188", "benchmark": "HarnessEval-W", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskIds": [ "S4-063" ], "sourceTable": "S4", "sourcePages": [ 15 ] }, { "id": "EC0189", "benchmark": "ACWM-Phys", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S4-048" ], "sourceTable": "S4", "sourcePages": [ 15 ] }, { "id": "EC0190", "benchmark": "HTEWorld", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S4-066" ], "sourceTable": "S4", "sourcePages": [ 15 ] }, { "id": "EC0191", "benchmark": "RigidBench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S4-084" ], "sourceTable": "S4", "sourcePages": [ 16 ] }, { "id": "EC0192", "benchmark": "Omni-WorldBench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskIds": [ "S4-072" ], "sourceTable": "S4", "sourcePages": [ 16 ] }, { "id": "EC0193", "benchmark": "Omni-WorldBench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S4-073", "S4-074" ], "sourceTable": "S4", "sourcePages": [ 16 ] }, { "id": "EC0194", "benchmark": "T2VWorldBench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskIds": [ "S4-040" ], "sourceTable": "S4", "sourcePages": [ 14 ] }, { "id": "EC0195", "benchmark": "WMBench", "scope": "T4", "protocol": "CL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S4-090" ], "sourceTable": "S4", "sourcePages": [ 16 ] }, { "id": "EC0196", "benchmark": "WorldModelBench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskIds": [ "S4-046" ], "sourceTable": "S4", "sourcePages": [ 14 ] }, { "id": "EC0197", "benchmark": "WorldModelBench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S4-047" ], "sourceTable": "S4", "sourcePages": [ 14 ] }, { "id": "EC0198", "benchmark": "WorldSimBench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskIds": [ "S4-015", "S4-016" ], "sourceTable": "S4", "sourcePages": [ 13 ] }, { "id": "EC0199", "benchmark": "WorldSimBench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S4-014" ], "sourceTable": "S4", "sourcePages": [ 13 ] }, { "id": "EC0200", "benchmark": "WorldSimBench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskIds": [ "S4-013" ], "sourceTable": "S4", "sourcePages": [ 13 ] }, { "id": "EC0201", "benchmark": "WorldSimBench", "scope": "T4", "protocol": "CL", "metric": "O", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S4-017" ], "sourceTable": "S4", "sourcePages": [ 13 ] }, { "id": "EC0202", "benchmark": "Apple-π", "scope": "T4", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S4-049" ], "sourceTable": "S4", "sourcePages": [ 15 ] }, { "id": "EC0203", "benchmark": "WBench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S4-088" ], "sourceTable": "S4", "sourcePages": [ 16 ] }, { "id": "EC0204", "benchmark": "CrashTwin", "scope": "T4", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S4-053" ], "sourceTable": "S4", "sourcePages": [ 15 ] }, { "id": "EC0205", "benchmark": "PDI-Bench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskIds": [ "S4-075" ], "sourceTable": "S4", "sourcePages": [ 16 ] }, { "id": "EC0206", "benchmark": "MBench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskIds": [ "S4-069" ], "sourceTable": "S4", "sourcePages": [ 15 ] }, { "id": "EC0207", "benchmark": "STEVO-Bench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskIds": [ "S4-087" ], "sourceTable": "S4", "sourcePages": [ 16 ] }, { "id": "EC0208", "benchmark": "CausalSpatial", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S4-051" ], "sourceTable": "S4", "sourcePages": [ 15 ] }, { "id": "EC0209", "benchmark": "What-If World", "scope": "T4", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskIds": [ "S4-089" ], "sourceTable": "S4", "sourcePages": [ 16 ] }, { "id": "EC0210", "benchmark": "HOCA-Bench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskIds": [ "S4-065" ], "sourceTable": "S4", "sourcePages": [ 15 ] }, { "id": "EC0211", "benchmark": "HOCA-Bench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S4-064" ], "sourceTable": "S4", "sourcePages": [ 15 ] }, { "id": "EC0212", "benchmark": "MVP", "scope": "T4", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S4-028" ], "sourceTable": "S4", "sourcePages": [ 14 ] }, { "id": "EC0213", "benchmark": "ContactWorld", "scope": "T4", "protocol": "CL", "metric": "O", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S4-052" ], "sourceTable": "S4", "sourcePages": [ 15 ] }, { "id": "EC0214", "benchmark": "MiraBench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S4-071" ], "sourceTable": "S4", "sourcePages": [ 15 ] }, { "id": "EC0215", "benchmark": "IntPhys 2", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S4-025" ], "sourceTable": "S4", "sourcePages": [ 14 ] }, { "id": "EC0216", "benchmark": "SmallWorlds", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S4-038" ], "sourceTable": "S4", "sourcePages": [ 14 ] }, { "id": "EC0217", "benchmark": "VBench-2.0", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskIds": [ "S4-042" ], "sourceTable": "S4", "sourcePages": [ 14 ] }, { "id": "EC0218", "benchmark": "WorldBench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S4-094" ], "sourceTable": "S4", "sourcePages": [ 17 ] }, { "id": "EC0219", "benchmark": "ExPhy", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S4-057" ], "sourceTable": "S4", "sourcePages": [ 15 ] }, { "id": "EC0220", "benchmark": "CoPhy", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S4-003" ], "sourceTable": "S4", "sourcePages": [ 13 ] }, { "id": "EC0221", "benchmark": "PHYRE", "scope": "T4", "protocol": "OL", "metric": "O", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S4-005" ], "sourceTable": "S4", "sourcePages": [ 13 ] }, { "id": "EC0222", "benchmark": "PHYRE", "scope": "T4", "protocol": "CL", "metric": "O", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S4-004" ], "sourceTable": "S4", "sourcePages": [ 13 ] }, { "id": "EC0223", "benchmark": "CRAFT", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S4-006" ], "sourceTable": "S4", "sourcePages": [ 13 ] }, { "id": "EC0224", "benchmark": "Physion++", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S4-009" ], "sourceTable": "S4", "sourcePages": [ 13 ] }, { "id": "EC0225", "benchmark": "ComPhy", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S4-008" ], "sourceTable": "S4", "sourcePages": [ 13 ] }, { "id": "EC0226", "benchmark": "ContPhy", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S4-010" ], "sourceTable": "S4", "sourcePages": [ 13 ] }, { "id": "EC0227", "benchmark": "PhyCoBench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskIds": [ "S4-035" ], "sourceTable": "S4", "sourcePages": [ 14 ] }, { "id": "EC0228", "benchmark": "VideoPhy", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskIds": [ "S4-012" ], "sourceTable": "S4", "sourcePages": [ 13 ] }, { "id": "EC0229", "benchmark": "VideoPhy-2", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskIds": [ "S4-043" ], "sourceTable": "S4", "sourcePages": [ 14 ] }, { "id": "EC0230", "benchmark": "PhyGenBench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskIds": [ "S4-011" ], "sourceTable": "S4", "sourcePages": [ 13 ] }, { "id": "EC0231", "benchmark": "T2VPhysBench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskIds": [ "S4-039" ], "sourceTable": "S4", "sourcePages": [ 14 ] }, { "id": "EC0232", "benchmark": "Physics-IQ", "scope": "T4", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskIds": [ "S4-036" ], "sourceTable": "S4", "sourcePages": [ 14 ] }, { "id": "EC0233", "benchmark": "PhyWorldBench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskIds": [ "S4-037" ], "sourceTable": "S4", "sourcePages": [ 14 ] }, { "id": "EC0234", "benchmark": "Morpheus", "scope": "T4", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskIds": [ "S4-026" ], "sourceTable": "S4", "sourcePages": [ 14 ] }, { "id": "EC0235", "benchmark": "Morpheus", "scope": "T4", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S4-027" ], "sourceTable": "S4", "sourcePages": [ 14 ] }, { "id": "EC0236", "benchmark": "DreamGen Bench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S4-021" ], "sourceTable": "S4", "sourcePages": [ 13 ] }, { "id": "EC0237", "benchmark": "PhyGround", "scope": "T4", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S4-076" ], "sourceTable": "S4", "sourcePages": [ 16 ] }, { "id": "EC0238", "benchmark": "Physion-Eval", "scope": "T4", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskIds": [ "S4-079" ], "sourceTable": "S4", "sourcePages": [ 16 ] }, { "id": "EC0239", "benchmark": "CRONOS", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S4-054" ], "sourceTable": "S4", "sourcePages": [ 15 ] }, { "id": "EC0240", "benchmark": "VACT", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskIds": [ "S4-041" ], "sourceTable": "S4", "sourcePages": [ 14 ] }, { "id": "EC0241", "benchmark": "PhysicsMind", "scope": "T4", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S4-077", "S4-078" ], "sourceTable": "S4", "sourcePages": [ 16 ] }, { "id": "EC0242", "benchmark": "KineBench", "scope": "T4", "protocol": "CL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S4-067" ], "sourceTable": "S4", "sourcePages": [ 15 ] }, { "id": "EC0243", "benchmark": "KineBench", "scope": "T4", "protocol": "CL", "metric": "O", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S4-068" ], "sourceTable": "S4", "sourcePages": [ 15 ] }, { "id": "EC0244", "benchmark": "ReactSim-Bench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S4-083" ], "sourceTable": "S4", "sourcePages": [ 16 ] }, { "id": "EC0245", "benchmark": "GAUGE", "scope": "T4", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskIds": [ "S4-059" ], "sourceTable": "S4", "sourcePages": [ 15 ] }, { "id": "EC0246", "benchmark": "CaliBench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskIds": [ "S4-050" ], "sourceTable": "S4", "sourcePages": [ 15 ] }, { "id": "EC0247", "benchmark": "WorldSimProbe", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S4-098" ], "sourceTable": "S4", "sourcePages": [ 17 ] }, { "id": "EC0248", "benchmark": "CLEVRER", "scope": "T5", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S5-001" ], "sourceTable": "S5", "sourcePages": [ 18 ] }, { "id": "EC0249", "benchmark": "Physion", "scope": "T5", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S5-004" ], "sourceTable": "S5", "sourcePages": [ 18 ] }, { "id": "EC0250", "benchmark": "WoW-World-Eval", "scope": "T5", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S5-034" ], "sourceTable": "S5", "sourcePages": [ 19 ] }, { "id": "EC0251", "benchmark": "RBench", "scope": "T5", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskIds": [ "S5-027" ], "sourceTable": "S5", "sourcePages": [ 19 ] }, { "id": "EC0252", "benchmark": "PAI-Bench", "scope": "T5", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskIds": [ "S5-013", "S5-014" ], "sourceTable": "S5", "sourcePages": [ 18 ] }, { "id": "EC0253", "benchmark": "RoboTrustBench", "scope": "T5", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S5-029" ], "sourceTable": "S5", "sourcePages": [ 19 ] }, { "id": "EC0254", "benchmark": "WorldExam", "scope": "T5", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskIds": [ "S5-032" ], "sourceTable": "S5", "sourcePages": [ 19 ] }, { "id": "EC0255", "benchmark": "PlayWorld", "scope": "T5", "protocol": "CL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S5-026" ], "sourceTable": "S5", "sourcePages": [ 19 ] }, { "id": "EC0256", "benchmark": "HarnessEval-W", "scope": "T5", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskIds": [ "S5-021" ], "sourceTable": "S5", "sourcePages": [ 18 ] }, { "id": "EC0257", "benchmark": "T2VWorldBench", "scope": "T5", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskIds": [ "S5-016" ], "sourceTable": "S5", "sourcePages": [ 18 ] }, { "id": "EC0258", "benchmark": "WR-Arena", "scope": "T5", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S5-035" ], "sourceTable": "S5", "sourcePages": [ 19 ] }, { "id": "EC0259", "benchmark": "CausalSpatial", "scope": "T5", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S5-019" ], "sourceTable": "S5", "sourcePages": [ 18 ] }, { "id": "EC0260", "benchmark": "What-If World", "scope": "T5", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskIds": [ "S5-031" ], "sourceTable": "S5", "sourcePages": [ 19 ] }, { "id": "EC0261", "benchmark": "HOCA-Bench", "scope": "T5", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskIds": [ "S5-022" ], "sourceTable": "S5", "sourcePages": [ 18 ] }, { "id": "EC0262", "benchmark": "AutumnBench", "scope": "T5", "protocol": "CL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S5-010" ], "sourceTable": "S5", "sourcePages": [ 18 ] }, { "id": "EC0263", "benchmark": "MVP", "scope": "T5", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S5-012" ], "sourceTable": "S5", "sourcePages": [ 18 ] }, { "id": "EC0264", "benchmark": "ScratchWorld", "scope": "T5", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S5-030" ], "sourceTable": "S5", "sourcePages": [ 19 ] }, { "id": "EC0265", "benchmark": "MiraBench", "scope": "T5", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S5-023" ], "sourceTable": "S5", "sourcePages": [ 18 ] }, { "id": "EC0266", "benchmark": "WorldPrediction", "scope": "T5", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskIds": [ "S5-018" ], "sourceTable": "S5", "sourcePages": [ 18 ] }, { "id": "EC0267", "benchmark": "CoPhy", "scope": "T5", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S5-002" ], "sourceTable": "S5", "sourcePages": [ 18 ] }, { "id": "EC0268", "benchmark": "CRAFT", "scope": "T5", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S5-003" ], "sourceTable": "S5", "sourcePages": [ 18 ] }, { "id": "EC0269", "benchmark": "ComPhy", "scope": "T5", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S5-006" ], "sourceTable": "S5", "sourcePages": [ 18 ] }, { "id": "EC0270", "benchmark": "ContPhy", "scope": "T5", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S5-008" ], "sourceTable": "S5", "sourcePages": [ 18 ] }, { "id": "EC0271", "benchmark": "Physics-IQ", "scope": "T5", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskIds": [ "S5-015" ], "sourceTable": "S5", "sourcePages": [ 18 ] }, { "id": "EC0272", "benchmark": "CRONOS", "scope": "T5", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S5-020" ], "sourceTable": "S5", "sourcePages": [ 18 ] }, { "id": "EC0273", "benchmark": "VACT", "scope": "T5", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskIds": [ "S5-017" ], "sourceTable": "S5", "sourcePages": [ 18 ] }, { "id": "EC0274", "benchmark": "PhysicsMind", "scope": "T5", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S5-024", "S5-025" ], "sourceTable": "S5", "sourcePages": [ 19 ] }, { "id": "EC0275", "benchmark": "ReactSim-Bench", "scope": "T5", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S5-028" ], "sourceTable": "S5", "sourcePages": [ 19 ] }, { "id": "EC0276", "benchmark": "WorldSimProbe", "scope": "T5", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S5-033" ], "sourceTable": "S5", "sourcePages": [ 19 ] }, { "id": "EC0277", "benchmark": "Causal-VidQA", "scope": "T5", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskIds": [ "S5-005" ], "sourceTable": "S5", "sourcePages": [ 18 ] }, { "id": "EC0278", "benchmark": "ACQUIRED", "scope": "T5", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskIds": [ "S5-007" ], "sourceTable": "S5", "sourcePages": [ 18 ] }, { "id": "EC0279", "benchmark": "MMWorld", "scope": "T5", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S5-009" ], "sourceTable": "S5", "sourcePages": [ 18 ] }, { "id": "EC0280", "benchmark": "CausalVQA", "scope": "T5", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskIds": [ "S5-011" ], "sourceTable": "S5", "sourcePages": [ 18 ] }, { "id": "EC0281", "benchmark": "WorldArena", "scope": "S5", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S6-047" ], "sourceTable": "S6", "sourcePages": [ 22 ] }, { "id": "EC0282", "benchmark": "WorldScore", "scope": "S5", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskIds": [ "S6-025" ], "sourceTable": "S6", "sourcePages": [ 21 ] }, { "id": "EC0283", "benchmark": "WorldScore", "scope": "S5", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S6-026" ], "sourceTable": "S6", "sourcePages": [ 21 ] }, { "id": "EC0284", "benchmark": "EWMBench", "scope": "S5", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskIds": [ "S6-012" ], "sourceTable": "S6", "sourcePages": [ 20 ] }, { "id": "EC0285", "benchmark": "GameWorld Score", "scope": "S5", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S6-013" ], "sourceTable": "S6", "sourcePages": [ 20 ] }, { "id": "EC0286", "benchmark": "4DWorldBench", "scope": "S5", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskIds": [ "S6-008" ], "sourceTable": "S6", "sourcePages": [ 20 ] }, { "id": "EC0287", "benchmark": "4DWorldBench", "scope": "S5", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskIds": [ "S6-007" ], "sourceTable": "S6", "sourcePages": [ 20 ] }, { "id": "EC0288", "benchmark": "4DWorldBench", "scope": "S5", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S6-009", "S6-010" ], "sourceTable": "S6", "sourcePages": [ 20 ] }, { "id": "EC0289", "benchmark": "DrivingGen", "scope": "S5", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskIds": [ "S6-029" ], "sourceTable": "S6", "sourcePages": [ 21 ] }, { "id": "EC0290", "benchmark": "WoW-World-Eval", "scope": "S5", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S6-052" ], "sourceTable": "S6", "sourcePages": [ 22 ] }, { "id": "EC0291", "benchmark": "WoW-World-Eval", "scope": "S5", "protocol": "OL", "metric": "O", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S6-053" ], "sourceTable": "S6", "sourcePages": [ 22 ] }, { "id": "EC0292", "benchmark": "RBench", "scope": "S5", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskIds": [ "S6-042" ], "sourceTable": "S6", "sourcePages": [ 21 ] }, { "id": "EC0293", "benchmark": "PAI-Bench", "scope": "S5", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskIds": [ "S6-016", "S6-018" ], "sourceTable": "S6", "sourcePages": [ 20 ] }, { "id": "EC0294", "benchmark": "PAI-Bench", "scope": "S5", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskIds": [ "S6-017" ], "sourceTable": "S6", "sourcePages": [ 20 ] }, { "id": "EC0295", "benchmark": "EZS-Bench", "scope": "S5", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S6-030" ], "sourceTable": "S6", "sourcePages": [ 21 ] }, { "id": "EC0296", "benchmark": "MemoBench", "scope": "S5", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S6-036" ], "sourceTable": "S6", "sourcePages": [ 21 ] }, { "id": "EC0297", "benchmark": "RoboTrustBench", "scope": "S5", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S6-043" ], "sourceTable": "S6", "sourcePages": [ 22 ] }, { "id": "EC0298", "benchmark": "WorldExam", "scope": "S5", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskIds": [ "S6-050" ], "sourceTable": "S6", "sourcePages": [ 22 ] }, { "id": "EC0299", "benchmark": "WorldExam", "scope": "S5", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S6-049" ], "sourceTable": "S6", "sourcePages": [ 22 ] }, { "id": "EC0300", "benchmark": "H2R-Bench", "scope": "S5", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskIds": [ "S6-031" ], "sourceTable": "S6", "sourcePages": [ 21 ] }, { "id": "EC0301", "benchmark": "H2R-Bench", "scope": "S5", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S6-032" ], "sourceTable": "S6", "sourcePages": [ 21 ] }, { "id": "EC0302", "benchmark": "XEWorld", "scope": "S5", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S6-054" ], "sourceTable": "S6", "sourcePages": [ 22 ] }, { "id": "EC0303", "benchmark": "HarnessEval-W", "scope": "S5", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskIds": [ "S6-033" ], "sourceTable": "S6", "sourcePages": [ 21 ] }, { "id": "EC0304", "benchmark": "WorldEcho", "scope": "S5", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S6-048" ], "sourceTable": "S6", "sourcePages": [ 22 ] }, { "id": "EC0305", "benchmark": "MagicBench", "scope": "S5", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskIds": [ "S6-014" ], "sourceTable": "S6", "sourcePages": [ 20 ] }, { "id": "EC0306", "benchmark": "MoveBench", "scope": "S5", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskIds": [ "S6-015" ], "sourceTable": "S6", "sourcePages": [ 20 ] }, { "id": "EC0307", "benchmark": "Omni-WorldBench", "scope": "S5", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskIds": [ "S6-038" ], "sourceTable": "S6", "sourcePages": [ 21 ] }, { "id": "EC0308", "benchmark": "Omni-WorldBench", "scope": "S5", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S6-039", "S6-040" ], "sourceTable": "S6", "sourcePages": [ 21 ] }, { "id": "EC0309", "benchmark": "OSCBench", "scope": "S5", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskIds": [ "S6-041" ], "sourceTable": "S6", "sourcePages": [ 21 ] }, { "id": "EC0310", "benchmark": "WorldModelBench", "scope": "S5", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskIds": [ "S6-023" ], "sourceTable": "S6", "sourcePages": [ 21 ] }, { "id": "EC0311", "benchmark": "WorldModelBench", "scope": "S5", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S6-024" ], "sourceTable": "S6", "sourcePages": [ 21 ] }, { "id": "EC0312", "benchmark": "TC-Bench", "scope": "S5", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskIds": [ "S6-005" ], "sourceTable": "S6", "sourcePages": [ 20 ] }, { "id": "EC0313", "benchmark": "TC-Bench", "scope": "S5", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskIds": [ "S6-004" ], "sourceTable": "S6", "sourcePages": [ 20 ] }, { "id": "EC0314", "benchmark": "MBench", "scope": "S5", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskIds": [ "S6-035" ], "sourceTable": "S6", "sourcePages": [ 21 ] }, { "id": "EC0315", "benchmark": "STEVO-Bench", "scope": "S5", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskIds": [ "S6-045" ], "sourceTable": "S6", "sourcePages": [ 22 ] }, { "id": "EC0316", "benchmark": "What-If World", "scope": "S5", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskIds": [ "S6-046" ], "sourceTable": "S6", "sourcePages": [ 22 ] }, { "id": "EC0317", "benchmark": "ScratchWorld", "scope": "S5", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S6-044" ], "sourceTable": "S6", "sourcePages": [ 22 ] }, { "id": "EC0318", "benchmark": "MiraBench", "scope": "S5", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S6-037" ], "sourceTable": "S6", "sourcePages": [ 21 ] }, { "id": "EC0319", "benchmark": "Chess-World-Model", "scope": "S5", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S6-027", "S6-028" ], "sourceTable": "S6", "sourcePages": [ 21 ] }, { "id": "EC0320", "benchmark": "VBench-2.0", "scope": "S5", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskIds": [ "S6-021" ], "sourceTable": "S6", "sourcePages": [ 20 ] }, { "id": "EC0321", "benchmark": "VideoPhy", "scope": "S5", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskIds": [ "S6-006" ], "sourceTable": "S6", "sourcePages": [ 20 ] }, { "id": "EC0322", "benchmark": "VideoPhy-2", "scope": "S5", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskIds": [ "S6-022" ], "sourceTable": "S6", "sourcePages": [ 21 ] }, { "id": "EC0323", "benchmark": "PhyGenBench", "scope": "S5", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskIds": [ "S6-002" ], "sourceTable": "S6", "sourcePages": [ 20 ] }, { "id": "EC0324", "benchmark": "PhyWorldBench", "scope": "S5", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskIds": [ "S6-019" ], "sourceTable": "S6", "sourcePages": [ 20 ] }, { "id": "EC0325", "benchmark": "DreamGen Bench", "scope": "S5", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S6-011" ], "sourceTable": "S6", "sourcePages": [ 20 ] }, { "id": "EC0326", "benchmark": "VACT", "scope": "S5", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskIds": [ "S6-020" ], "sourceTable": "S6", "sourcePages": [ 20 ] }, { "id": "EC0327", "benchmark": "KineBench", "scope": "S5", "protocol": "CL", "metric": "O", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S6-034" ], "sourceTable": "S6", "sourcePages": [ 21 ] }, { "id": "EC0328", "benchmark": "WorldSimProbe", "scope": "S5", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S6-051" ], "sourceTable": "S6", "sourcePages": [ 22 ] }, { "id": "EC0329", "benchmark": "StoryEval", "scope": "S5", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskIds": [ "S6-003" ], "sourceTable": "S6", "sourcePages": [ 20 ] }, { "id": "EC0330", "benchmark": "ACT-Bench", "scope": "S5", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskIds": [ "S6-001" ], "sourceTable": "S6", "sourcePages": [ 20 ] }, { "id": "EC0331", "benchmark": "RoboWM-Bench", "scope": "S6", "protocol": "OL", "metric": "O", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S6-066" ], "sourceTable": "S6", "sourcePages": [ 23 ] }, { "id": "EC0332", "benchmark": "MIND", "scope": "S6", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S6-063" ], "sourceTable": "S6", "sourcePages": [ 22 ] }, { "id": "EC0333", "benchmark": "WorldOlympiad", "scope": "S6", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S6-073" ], "sourceTable": "S6", "sourcePages": [ 23 ] }, { "id": "EC0334", "benchmark": "WorldArena 2.0", "scope": "S6", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskIds": [ "S6-071" ], "sourceTable": "S6", "sourcePages": [ 23 ] }, { "id": "EC0335", "benchmark": "WorldArena 2.0", "scope": "S6", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S6-070" ], "sourceTable": "S6", "sourcePages": [ 23 ] }, { "id": "EC0336", "benchmark": "WorldMark", "scope": "S6", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S6-072" ], "sourceTable": "S6", "sourcePages": [ 23 ] }, { "id": "EC0337", "benchmark": "iWorld-Bench", "scope": "S6", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S6-062" ], "sourceTable": "S6", "sourcePages": [ 22 ] }, { "id": "EC0338", "benchmark": "WorldRoamBench", "scope": "S6", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S6-074" ], "sourceTable": "S6", "sourcePages": [ 23 ] }, { "id": "EC0339", "benchmark": "PlayWorld", "scope": "S6", "protocol": "CL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S6-064" ], "sourceTable": "S6", "sourcePages": [ 22 ] }, { "id": "EC0340", "benchmark": "ACWM-Phys", "scope": "S6", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S6-060" ], "sourceTable": "S6", "sourcePages": [ 22 ] }, { "id": "EC0341", "benchmark": "HTEWorld", "scope": "S6", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S6-061" ], "sourceTable": "S6", "sourcePages": [ 22 ] }, { "id": "EC0342", "benchmark": "WMBench", "scope": "S6", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskIds": [ "S6-069" ], "sourceTable": "S6", "sourcePages": [ 23 ] }, { "id": "EC0343", "benchmark": "WMBench", "scope": "S6", "protocol": "CL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S6-068" ], "sourceTable": "S6", "sourcePages": [ 23 ] }, { "id": "EC0344", "benchmark": "WorldSimBench", "scope": "S6", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskIds": [ "S6-057", "S6-058" ], "sourceTable": "S6", "sourcePages": [ 22 ] }, { "id": "EC0345", "benchmark": "WorldSimBench", "scope": "S6", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S6-056" ], "sourceTable": "S6", "sourcePages": [ 22 ] }, { "id": "EC0346", "benchmark": "WorldSimBench", "scope": "S6", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskIds": [ "S6-055" ], "sourceTable": "S6", "sourcePages": [ 22 ] }, { "id": "EC0347", "benchmark": "WorldSimBench", "scope": "S6", "protocol": "CL", "metric": "O", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S6-059" ], "sourceTable": "S6", "sourcePages": [ 22 ] }, { "id": "EC0348", "benchmark": "WBench", "scope": "S6", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S6-067" ], "sourceTable": "S6", "sourcePages": [ 23 ] }, { "id": "EC0349", "benchmark": "WR-Arena", "scope": "S6", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S6-075" ], "sourceTable": "S6", "sourcePages": [ 23 ] }, { "id": "EC0350", "benchmark": "ReactSim-Bench", "scope": "S6", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S6-065" ], "sourceTable": "S6", "sourcePages": [ 23 ] }, { "id": "EC0351", "benchmark": "WorldArena", "scope": "S7", "protocol": "OL", "metric": "O", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S7-001" ], "sourceTable": "S7", "sourcePages": [ 24 ] }, { "id": "EC0352", "benchmark": "WorldArena 2.0", "scope": "S7", "protocol": "OL", "metric": "O", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S7-002" ], "sourceTable": "S7", "sourcePages": [ 24 ] }, { "id": "EC0353", "benchmark": "WorldArena", "scope": "S8", "protocol": "CL", "metric": "O", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S7-004" ], "sourceTable": "S7", "sourcePages": [ 24 ] }, { "id": "EC0354", "benchmark": "WMBench", "scope": "S8", "protocol": "CL", "metric": "O", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S7-003" ], "sourceTable": "S7", "sourcePages": [ 24 ] }, { "id": "EC0355", "benchmark": "RoboWM-Bench", "scope": "S9", "protocol": "OL", "metric": "O", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S7-015" ], "sourceTable": "S7", "sourcePages": [ 24 ] }, { "id": "EC0356", "benchmark": "World-in-World", "scope": "S9", "protocol": "CL", "metric": "O", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S7-009" ], "sourceTable": "S7", "sourcePages": [ 24 ] }, { "id": "EC0357", "benchmark": "WorldArena", "scope": "S9", "protocol": "CL", "metric": "O", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S7-016" ], "sourceTable": "S7", "sourcePages": [ 24 ] }, { "id": "EC0358", "benchmark": "WorldArena 2.0", "scope": "S9", "protocol": "CL", "metric": "O", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S7-017", "S7-018" ], "sourceTable": "S7", "sourcePages": [ 24 ] }, { "id": "EC0359", "benchmark": "WorldLens", "scope": "S9", "protocol": "OL", "metric": "O", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S7-010" ], "sourceTable": "S7", "sourcePages": [ 24 ] }, { "id": "EC0360", "benchmark": "WorldLens", "scope": "S9", "protocol": "CL", "metric": "O", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S7-011" ], "sourceTable": "S7", "sourcePages": [ 24 ] }, { "id": "EC0361", "benchmark": "WoW-World-Eval", "scope": "S9", "protocol": "OL", "metric": "O", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S7-019" ], "sourceTable": "S7", "sourcePages": [ 25 ] }, { "id": "EC0362", "benchmark": "WorldSimBench", "scope": "S9", "protocol": "CL", "metric": "O", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S7-007" ], "sourceTable": "S7", "sourcePages": [ 24 ] }, { "id": "EC0363", "benchmark": "EVA-Bench", "scope": "S9", "protocol": "OL", "metric": "O", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S7-005" ], "sourceTable": "S7", "sourcePages": [ 24 ] }, { "id": "EC0364", "benchmark": "EVA-Bench", "scope": "S9", "protocol": "CL", "metric": "O", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S7-006" ], "sourceTable": "S7", "sourcePages": [ 24 ] }, { "id": "EC0365", "benchmark": "WR-Arena", "scope": "S9", "protocol": "CL", "metric": "O", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S7-020", "S7-021" ], "sourceTable": "S7", "sourcePages": [ 25 ] }, { "id": "EC0366", "benchmark": "AutumnBench", "scope": "S9", "protocol": "CL", "metric": "O", "data": "SBG", "dataStatus": "classified", "taskIds": [ "S7-008" ], "sourceTable": "S7", "sourcePages": [ 24 ] }, { "id": "EC0367", "benchmark": "ContactWorld", "scope": "S9", "protocol": "CL", "metric": "O", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S7-012", "S7-013" ], "sourceTable": "S7", "sourcePages": [ 24 ] }, { "id": "EC0368", "benchmark": "KineBench", "scope": "S9", "protocol": "CL", "metric": "O", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S7-014" ], "sourceTable": "S7", "sourcePages": [ 24 ] }, { "id": "EC0369", "benchmark": "WorldArena 2.0", "scope": "S10", "protocol": "CL", "metric": "O", "data": "HCP", "dataStatus": "classified", "taskIds": [ "S7-022" ], "sourceTable": "S7", "sourcePages": [ 25 ] } ], "taskRecords": [ { "taskId": "S1-001", "benchmark": "ChronoMagic-Bench", "scope": "T1", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "MTScore; GPT4o-MTScore; CHScore", "source": { "table": "S1", "page": 4, "tableRow": 1 }, "auxiliary": false }, { "taskId": "S1-002", "benchmark": "EVA-Bench", "scope": "T1", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Fixed-condition generation baseline", "measuredReadout": "Video quality; FVD and other generation scores", "source": { "table": "S1", "page": 4, "tableRow": 2 }, "auxiliary": false }, { "taskId": "S1-003", "benchmark": "EVA-Bench", "scope": "T1", "protocol": "CL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Generation with RoG adaptation", "measuredReadout": "Video quality; FVD and other generation scores", "source": { "table": "S1", "page": 4, "tableRow": 3 }, "auxiliary": false }, { "taskId": "S1-004", "benchmark": "TC-Bench", "scope": "T1", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskBranch": "T2V / output consistency", "measuredReadout": "Transition-object / other-object consis- tency assertions", "source": { "table": "S1", "page": 4, "tableRow": 4 }, "auxiliary": false }, { "taskId": "S1-005", "benchmark": "TC-Bench", "scope": "T1", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "I2V / reference-frame consistency", "measuredReadout": "CLIP / flow / trajectory frame consistency", "source": { "table": "S1", "page": 4, "tableRow": 5 }, "auxiliary": false }, { "taskId": "S1-006", "benchmark": "WorldSimBench", "scope": "T1", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskBranch": "Explicit / T2V", "measuredReadout": "Aesthetics; Background / Foreground Consistency", "source": { "table": "S1", "page": 4, "tableRow": 6 }, "auxiliary": false }, { "taskId": "S1-007", "benchmark": "WorldSimBench", "scope": "T1", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Explicit I2V / OE / Minecraft", "measuredReadout": "Background / Foreground Consistency", "source": { "table": "S1", "page": 4, "tableRow": 7 }, "auxiliary": false }, { "taskId": "S1-008", "benchmark": "WorldSimBench", "scope": "T1", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "Explicit I2V / AD / nuScenes", "measuredReadout": "Aesthetics", "source": { "table": "S1", "page": 4, "tableRow": 8 }, "auxiliary": false }, { "taskId": "S1-009", "benchmark": "WorldSimBench", "scope": "T1", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "Explicit I2V / RM / RH20T- P", "measuredReadout": "Aesthetics; Background / Foreground Consistency", "source": { "table": "S1", "page": 4, "tableRow": 9 }, "auxiliary": false }, { "taskId": "S1-010", "benchmark": "4DWorldBench", "scope": "T1", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskBranch": "Text-to-4D", "measuredReadout": "Perceptual quality; visual stability scores", "source": { "table": "S1", "page": 4, "tableRow": 10 }, "auxiliary": false }, { "taskId": "S1-011", "benchmark": "4DWorldBench", "scope": "T1", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "Image-to-4D / physical WISA", "measuredReadout": "Perceptual quality; visual stability scores", "source": { "table": "S1", "page": 4, "tableRow": 11 }, "auxiliary": false }, { "taskId": "S1-012", "benchmark": "4DWorldBench", "scope": "T1", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "dataResolution": "final-consistency-checklist", "taskBranch": "Image-to-4D / nonphysical VBench2", "measuredReadout": "Perceptual quality; visual stability scores", "source": { "table": "S1", "page": 4, "tableRow": 12 }, "auxiliary": false }, { "taskId": "S1-013", "benchmark": "4DWorldBench", "scope": "T1", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Video-to-4D / mixed suite", "measuredReadout": "Perceptual quality; visual stability scores", "source": { "table": "S1", "page": 4, "tableRow": 13 }, "auxiliary": false }, { "taskId": "S1-014", "benchmark": "EWMBench", "scope": "T1", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Scene Consistency; inter-frame visual stability", "source": { "table": "S1", "page": 4, "tableRow": 14 }, "auxiliary": false }, { "taskId": "S1-015", "benchmark": "GameWorld Score", "scope": "T1", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "LAION aesthetics; MUSIQ; CLIP temporal consistency; motion smoothness", "source": { "table": "S1", "page": 4, "tableRow": 15 }, "auxiliary": false }, { "taskId": "S1-016", "benchmark": "Gen-ViRe", "scope": "T1", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Dynamic-task continuity criteria, includ- ing C2 Physical Continuity", "source": { "table": "S1", "page": 4, "tableRow": 16 }, "auxiliary": false }, { "taskId": "S1-017", "benchmark": "MagicBench", "scope": "T1", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "Fixed initial-image / trajec- tory generation", "measuredReadout": "FID; FVD", "source": { "table": "S1", "page": 4, "tableRow": 17 }, "auxiliary": false }, { "taskId": "S1-018", "benchmark": "MoveBench", "scope": "T1", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "Fixed initial-image / trajec- tory generation", "measuredReadout": "FID; FVD; PSNR; SSIM", "source": { "table": "S1", "page": 4, "tableRow": 18 }, "auxiliary": false }, { "taskId": "S1-019", "benchmark": "PAI-Bench", "scope": "T1", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskBranch": "PAI-G / T2V", "measuredReadout": "Quality Score: temporal stability; motion smoothness; aesthetic / imaging quality", "source": { "table": "S1", "page": 4, "tableRow": 19 }, "auxiliary": false }, { "taskId": "S1-020", "benchmark": "PAI-Bench", "scope": "T1", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "PAI-G / I2V", "measuredReadout": "Quality Score: temporal stability; motion smoothness; aesthetic / imaging quality", "source": { "table": "S1", "page": 4, "tableRow": 20 }, "auxiliary": false }, { "taskId": "S1-021", "benchmark": "PEDRA", "scope": "T1", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "I2V / ETH-UCY reference", "measuredReadout": "Disappearance; MOT Confidence; EMD for reference-distribution terms", "source": { "table": "S1", "page": 4, "tableRow": 21 }, "auxiliary": false }, { "taskId": "S1-022", "benchmark": "PEDRA", "scope": "T1", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskBranch": "T2V / prompt-only physical-unit", "measuredReadout": "Disappearance; MOT Confidence; statistics / reference ranges", "source": { "table": "S1", "page": 4, "tableRow": 22 }, "auxiliary": false }, { "taskId": "S1-023", "benchmark": "T2VWorldBench", "scope": "T1", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Video-quality / consistency ratings", "source": { "table": "S1", "page": 4, "tableRow": 23 }, "auxiliary": false }, { "taskId": "S1-024", "benchmark": "VMBench", "scope": "T1", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "MSS; OIS; TCS; quality / continuity components of CAS", "source": { "table": "S1", "page": 5, "tableRow": 24 }, "auxiliary": false }, { "taskId": "S1-025", "benchmark": "WorldLens", "scope": "T1", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "Generation / reconstruction diagnostics", "measuredReadout": "Generation FVD / visual quality; recon- struction LPIPS / PSNR / SSIM", "source": { "table": "S1", "page": 5, "tableRow": 25 }, "auxiliary": false }, { "taskId": "S1-026", "benchmark": "WorldModelBench", "scope": "T1", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskBranch": "T2V", "measuredReadout": "Binary frame-wise / temporal-quality items", "source": { "table": "S1", "page": 5, "tableRow": 26 }, "auxiliary": false }, { "taskId": "S1-027", "benchmark": "WorldModelBench", "scope": "T1", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "I2V", "measuredReadout": "Binary frame-wise / temporal-quality items", "source": { "table": "S1", "page": 5, "tableRow": 27 }, "auxiliary": false }, { "taskId": "S1-028", "benchmark": "WorldScore", "scope": "T1", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskBranch": "T2V interface", "measuredReadout": "Aesthetic / image quality; motion / style consistency", "source": { "table": "S1", "page": 5, "tableRow": 28 }, "auxiliary": false }, { "taskId": "S1-029", "benchmark": "WorldScore", "scope": "T1", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Image-conditioned interface", "measuredReadout": "Aesthetic / image quality; motion / style consistency", "source": { "table": "S1", "page": 5, "tableRow": 29 }, "auxiliary": false }, { "taskId": "S1-030", "benchmark": "ACWM-Phys", "scope": "T1", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "MSE; SSIM; PSNR", "source": { "table": "S1", "page": 5, "tableRow": 30 }, "auxiliary": false }, { "taskId": "S1-031", "benchmark": "Apple-π", "scope": "T1", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Integrity / fidelity subscores", "source": { "table": "S1", "page": 5, "tableRow": 31 }, "auxiliary": false }, { "taskId": "S1-032", "benchmark": "CrashTwin", "scope": "T1", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Fixed test subset quality", "measuredReadout": "Identity / appearance stability; video", "source": { "table": "S1", "page": 5, "tableRow": 32 }, "auxiliary": false }, { "taskId": "S1-033", "benchmark": "DrivingGen", "scope": "T1", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "Open-domain driving", "measuredReadout": "Image / video generation quality", "source": { "table": "S1", "page": 5, "tableRow": 33 }, "auxiliary": false }, { "taskId": "S1-034", "benchmark": "DrivingGen", "scope": "T1", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "Ego-conditioned driving", "measuredReadout": "Image / video generation quality", "source": { "table": "S1", "page": 5, "tableRow": 34 }, "auxiliary": false }, { "taskId": "S1-035", "benchmark": "EZS-Bench", "scope": "T1", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "EZSbench generation (Table 2)", "measuredReadout": "AQ, BC, IQ, MS, OC, SC, I2VB, I2VS; Quality Score (Table 2)", "source": { "table": "S1", "page": 5, "tableRow": 35 }, "auxiliary": false }, { "taskId": "S1-036", "benchmark": "H2R-Bench", "scope": "T1", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "Main 240 cases / no robot reference image", "measuredReadout": "M5 Video Quality", "source": { "table": "S1", "page": 5, "tableRow": 36 }, "auxiliary": false }, { "taskId": "S1-037", "benchmark": "H2R-Bench", "scope": "T1", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "dataResolution": "final-consistency-checklist", "taskBranch": "Robot-reference-image ablation", "measuredReadout": "M5 Video Quality", "source": { "table": "S1", "page": 5, "tableRow": 37 }, "auxiliary": false }, { "taskId": "S1-038", "benchmark": "HarnessEval-W", "scope": "T1", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Render Quality / Motion Quality case scores", "source": { "table": "S1", "page": 5, "tableRow": 38 }, "auxiliary": false }, { "taskId": "S1-039", "benchmark": "HTEWorld", "scope": "T1", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Visual / temporal continuity at chunk boundaries", "source": { "table": "S1", "page": 5, "tableRow": 39 }, "auxiliary": false }, { "taskId": "S1-040", "benchmark": "iWorld-Bench", "scope": "T1", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Image / video quality; brightness; sharp- ness", "source": { "table": "S1", "page": 5, "tableRow": 40 }, "auxiliary": false }, { "taskId": "S1-041", "benchmark": "MemoBench", "scope": "T1", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Visual quality; motion smoothness and other basic quality scores", "source": { "table": "S1", "page": 5, "tableRow": 41 }, "auxiliary": false }, { "taskId": "S1-042", "benchmark": "MIND", "scope": "T1", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Visual / temporal quality", "source": { "table": "S1", "page": 5, "tableRow": 42 }, "auxiliary": false }, { "taskId": "S1-043", "benchmark": "Omni-WorldBench", "scope": "T1", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskBranch": "T2V Transitions", "measuredReadout": "Imaging Quality; Temporal Flickering; Motion Smoothness; Dynamic Degree; Detect (cuts)", "source": { "table": "S1", "page": 5, "tableRow": 43 }, "auxiliary": false }, { "taskId": "S1-044", "benchmark": "Omni-WorldBench", "scope": "T1", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "IT2V Transitions", "measuredReadout": "Imaging Quality; Temporal Flickering; Motion Smoothness; Dynamic Degree; Detect (cuts)", "source": { "table": "S1", "page": 5, "tableRow": 44 }, "auxiliary": false }, { "taskId": "S1-045", "benchmark": "Omni-WorldBench", "scope": "T1", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "With Camera Transitions", "measuredReadout": "Imaging Quality; Temporal Flickering; Motion Smoothness; Dynamic Degree; Detect (cuts)", "source": { "table": "S1", "page": 5, "tableRow": 45 }, "auxiliary": false }, { "taskId": "S1-046", "benchmark": "OSCBench", "scope": "T1", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Visual-quality rubric", "source": { "table": "S1", "page": 5, "tableRow": 46 }, "auxiliary": false }, { "taskId": "S1-047", "benchmark": "PlayWorld", "scope": "T1", "protocol": "CL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Feedback-based test subset", "measuredReadout": "Basic visual / video quality", "source": { "table": "S1", "page": 5, "tableRow": 47 }, "auxiliary": false }, { "taskId": "S1-048", "benchmark": "RBench", "scope": "T1", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Visual quality; motion smoothness", "source": { "table": "S1", "page": 6, "tableRow": 48 }, "auxiliary": false }, { "taskId": "S1-049", "benchmark": "RigidBench", "scope": "T1", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "LPIPS; SSIM", "source": { "table": "S1", "page": 6, "tableRow": 49 }, "auxiliary": false }, { "taskId": "S1-050", "benchmark": "RoboTrustBench", "scope": "T1", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Visual-quality rubric", "source": { "table": "S1", "page": 6, "tableRow": 50 }, "auxiliary": false }, { "taskId": "S1-051", "benchmark": "SurgWMBench", "scope": "T1", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "Pure video generation (Table 1a)", "measuredReadout": "PSNR; SSIM; LPIPS", "source": { "table": "S1", "page": 6, "tableRow": 51 }, "auxiliary": false }, { "taskId": "S1-052", "benchmark": "SurgWMBench", "scope": "T1", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "Joint video / motion (Table 1b)", "measuredReadout": "PSNR; SSIM; LPIPS", "source": { "table": "S1", "page": 6, "tableRow": 52 }, "auxiliary": false }, { "taskId": "S1-053", "benchmark": "WBench", "scope": "T1", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Visual-quality / temporal-continuity components", "source": { "table": "S1", "page": 6, "tableRow": 53 }, "auxiliary": false }, { "taskId": "S1-054", "benchmark": "WMBench", "scope": "T1", "protocol": "CL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Direct diagnostics of policy- feedback rollouts WMES", "measuredReadout": "Visual / video diagnostic components of", "source": { "table": "S1", "page": 6, "tableRow": 54 }, "auxiliary": false }, { "taskId": "S1-055", "benchmark": "WMBench", "scope": "T1", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "I2V no-control baseline (Table 3)", "measuredReadout": "Dynamic Degree; Motion Smoothness; Flow Score; Photometric Consistency", "source": { "table": "S1", "page": 6, "tableRow": 55 }, "auxiliary": false }, { "taskId": "S1-056", "benchmark": "WMBench", "scope": "T1", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "40 s autoregressive diagnos- tics (Table 4)", "measuredReadout": "PSNR / FID / FVD per 8 s segment; temporal degradation", "source": { "table": "S1", "page": 6, "tableRow": 56 }, "auxiliary": false }, { "taskId": "S1-057", "benchmark": "WorldArena", "scope": "T1", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Visual / motion / content quality", "source": { "table": "S1", "page": 6, "tableRow": 57 }, "auxiliary": false }, { "taskId": "S1-058", "benchmark": "WorldArena 2.0", "scope": "T1", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Direct video diagnostics / RoboTwin-LIBERO", "measuredReadout": "Visual / motion / content quality", "source": { "table": "S1", "page": 6, "tableRow": 58 }, "auxiliary": false }, { "taskId": "S1-059", "benchmark": "WorldArena 2.0", "scope": "T1", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "Direct video diagnostics / real ALOHA", "measuredReadout": "Visual / motion / content quality", "source": { "table": "S1", "page": 6, "tableRow": 59 }, "auxiliary": false }, { "taskId": "S1-060", "benchmark": "WorldEcho", "scope": "T1", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Visual-quality gating", "source": { "table": "S1", "page": 6, "tableRow": 60 }, "auxiliary": false }, { "taskId": "S1-061", "benchmark": "WorldExam", "scope": "T1", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Static-scene general quality", "measuredReadout": "Aesthetic / imaging quality; photometric consistency; temporal flickering", "source": { "table": "S1", "page": 6, "tableRow": 61 }, "auxiliary": false }, { "taskId": "S1-062", "benchmark": "WorldExam", "scope": "T1", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskBranch": "Dynamic-interaction general quality", "measuredReadout": "Subject consistency; motion smoothness; aesthetic / imaging quality", "source": { "table": "S1", "page": 6, "tableRow": 62 }, "auxiliary": false }, { "taskId": "S1-063", "benchmark": "WorldMark", "scope": "T1", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Visual quality; temporal quality", "source": { "table": "S1", "page": 6, "tableRow": 63 }, "auxiliary": false }, { "taskId": "S1-064", "benchmark": "WorldRoamBench", "scope": "T1", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Visual / video quality scores", "source": { "table": "S1", "page": 6, "tableRow": 64 }, "auxiliary": false }, { "taskId": "S1-065", "benchmark": "WoW-World-Eval", "scope": "T1", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Fixed generated-video diagnostics", "measuredReadout": "Video Quality submetrics", "source": { "table": "S1", "page": 6, "tableRow": 65 }, "auxiliary": false }, { "taskId": "S1-066", "benchmark": "WR-Arena", "scope": "T1", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Content alignment; style consistency", "source": { "table": "S1", "page": 6, "tableRow": 66 }, "auxiliary": false }, { "taskId": "S1-067", "benchmark": "XEWorld", "scope": "T1", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Fixed test subset = closed-loop. Level: P = prediction-level; SPTC = scenario/prompt/task curation; data category; protocol and metric initial-world images with independently HCP describes this construction pipeline, Player decisions; unsupported origins of the 63 selected data codes. 240 cases are RWD; named branches: EZS-Bench uses s autoregressive branch remains OL. to RoG feedback that controls video", "measuredReadout": "Generated-video visual quality O = downstream outcome. Data: RWD HCP = hybrid construction. NR denotes △ level are classified separately. = cross-category specified long-horizon objectives, not a verified real/synthetic breakdown cases of a specific generator are not standard-track nonphysical VBench2 images are not resolved. the robot-reference-image ablation lacks its Table 2 suite; SurgWMBench lists separately Table and equation numbers inside cells refer extension. This coding does not, by itself,", "source": { "table": "S1", "page": 6, "tableRow": 67 }, "auxiliary": false }, { "taskId": "S2-001", "benchmark": "IntPhys", "scope": "T2", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Fixed test subset permanence,", "measuredReadout": "Absolute / relative classification for object shape and continuity", "source": { "table": "S2", "page": 7, "tableRow": 1 }, "auxiliary": false }, { "taskId": "S2-002", "benchmark": "EVA-Bench", "scope": "T2", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Fixed-condition generation baseline", "measuredReadout": "Goal Completion Estimation (GCE; normalized DreamSim similarity to the goal frame)", "source": { "table": "S2", "page": 7, "tableRow": 2 }, "auxiliary": false }, { "taskId": "S2-003", "benchmark": "EVA-Bench", "scope": "T2", "protocol": "CL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Generation with RoG adaptation", "measuredReadout": "Goal Completion Estimation (GCE; normalized DreamSim similarity to the goal frame)", "source": { "table": "S2", "page": 7, "tableRow": 3 }, "auxiliary": false }, { "taskId": "S2-004", "benchmark": "WorldSimBench", "scope": "T2", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskBranch": "Explicit / T2V", "measuredReadout": "Scenario Alignment; Perspectivity; Key Element", "source": { "table": "S2", "page": 7, "tableRow": 4 }, "auxiliary": false }, { "taskId": "S2-005", "benchmark": "WorldSimBench", "scope": "T2", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Explicit I2V / OE / Minecraft", "measuredReadout": "Scenario Alignment", "source": { "table": "S2", "page": 7, "tableRow": 5 }, "auxiliary": false }, { "taskId": "S2-006", "benchmark": "WorldSimBench", "scope": "T2", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "Explicit I2V / AD / nuScenes", "measuredReadout": "Perspectivity; Key Element", "source": { "table": "S2", "page": 7, "tableRow": 6 }, "auxiliary": false }, { "taskId": "S2-007", "benchmark": "WorldSimBench", "scope": "T2", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "Explicit I2V / RM / RH20T- P", "measuredReadout": "Perspectivity", "source": { "table": "S2", "page": 7, "tableRow": 7 }, "auxiliary": false }, { "taskId": "S2-008", "benchmark": "4DWorldBench", "scope": "T2", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskBranch": "Text-to-4D", "measuredReadout": "4D / geometric-consistency diagnostics", "source": { "table": "S2", "page": 7, "tableRow": 8 }, "auxiliary": false }, { "taskId": "S2-009", "benchmark": "4DWorldBench", "scope": "T2", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "Image-to-4D / physical WISA", "measuredReadout": "4D / geometric-consistency diagnostics", "source": { "table": "S2", "page": 7, "tableRow": 9 }, "auxiliary": false }, { "taskId": "S2-010", "benchmark": "4DWorldBench", "scope": "T2", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "dataResolution": "final-consistency-checklist", "taskBranch": "Image-to-4D / nonphysical VBench2", "measuredReadout": "4D / geometric-consistency diagnostics", "source": { "table": "S2", "page": 7, "tableRow": 10 }, "auxiliary": false }, { "taskId": "S2-011", "benchmark": "4DWorldBench", "scope": "T2", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Video-to-4D / mixed suite", "measuredReadout": "4D / geometric-consistency diagnostics", "source": { "table": "S2", "page": 7, "tableRow": 11 }, "auxiliary": false }, { "taskId": "S2-012", "benchmark": "AutumnBench", "scope": "T2", "protocol": "CL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "MFP with adaptive step/rewind queries after exploration", "measuredReadout": "Final masked-grid color MCQ accuracy", "source": { "table": "S2", "page": 7, "tableRow": 12 }, "auxiliary": false }, { "taskId": "S2-013", "benchmark": "AutumnBench", "scope": "T2", "protocol": "CL", "metric": "O", "data": "SBG", "dataStatus": "classified", "taskBranch": "Planning / target-subgrid state", "measuredReadout": "Exact target-subgrid color match after execution", "source": { "table": "S2", "page": 7, "tableRow": 13 }, "auxiliary": false }, { "taskId": "S2-014", "benchmark": "EWMBench", "scope": "T2", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "HSD spatial-trajectory alignment", "source": { "table": "S2", "page": 7, "tableRow": 14 }, "auxiliary": false }, { "taskId": "S2-015", "benchmark": "GameWorld Score", "scope": "T2", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Object consistency; scenario consistency", "source": { "table": "S2", "page": 7, "tableRow": 15 }, "auxiliary": false }, { "taskId": "S2-016", "benchmark": "Gen-ViRe", "scope": "T2", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Spatial-planning / obstacle-relation rubric", "source": { "table": "S2", "page": 7, "tableRow": 16 }, "auxiliary": false }, { "taskId": "S2-017", "benchmark": "IntPhys 2", "scope": "T2", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Paired accuracy for permanence, invari- ance and continuity", "source": { "table": "S2", "page": 7, "tableRow": 17 }, "auxiliary": false }, { "taskId": "S2-018", "benchmark": "LoopNav", "scope": "T2", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "SGCS: missing objects, substitutions and layout matching", "source": { "table": "S2", "page": 7, "tableRow": 18 }, "auxiliary": false }, { "taskId": "S2-019", "benchmark": "MVP", "scope": "T2", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Paired accuracy on spatial-relation minimal pairs", "source": { "table": "S2", "page": 7, "tableRow": 19 }, "auxiliary": false }, { "taskId": "S2-020", "benchmark": "PAI-Bench", "scope": "T2", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "PAI-C / spatial controls", "measuredReadout": "Depth si-RMSE; Seg mIoU; Edge F1", "source": { "table": "S2", "page": 7, "tableRow": 20 }, "auxiliary": false }, { "taskId": "S2-021", "benchmark": "PAI-Bench", "scope": "T2", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "PAI-U / Space QA", "measuredReadout": "Spatial-feasibility / relation QA accuracy", "source": { "table": "S2", "page": 7, "tableRow": 21 }, "auxiliary": false }, { "taskId": "S2-022", "benchmark": "PEDRA", "scope": "T2", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "I2V / ETH-UCY reference /", "measuredReadout": "3D Geometric Confidence; NN distance collision relations; EMD for reference- distribution terms", "source": { "table": "S2", "page": 7, "tableRow": 22 }, "auxiliary": false }, { "taskId": "S2-023", "benchmark": "PEDRA", "scope": "T2", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskBranch": "T2V / prompt-only", "measuredReadout": "3D Geometric Confidence; NN distance / collision relations; physical-unit statistics / reference ranges", "source": { "table": "S2", "page": 7, "tableRow": 23 }, "auxiliary": false }, { "taskId": "S2-024", "benchmark": "SmallWorlds", "scope": "T2", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Position / keypoint reprojection error", "source": { "table": "S2", "page": 8, "tableRow": 24 }, "auxiliary": false }, { "taskId": "S2-025", "benchmark": "VBench-2.0", "scope": "T2", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Dynamic spatial relations; multiview consistency", "source": { "table": "S2", "page": 8, "tableRow": 25 }, "auxiliary": false }, { "taskId": "S2-026", "benchmark": "WorldLens", "scope": "T2", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "Generation / reconstruction diagnostics", "measuredReadout": "Cross-view LoFTR confidence; reconstructed-depth AbsRel", "source": { "table": "S2", "page": 8, "tableRow": 26 }, "auxiliary": false }, { "taskId": "S2-027", "benchmark": "WorldScore", "scope": "T2", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskBranch": "T2V interface", "measuredReadout": "3D / photometric consistency", "source": { "table": "S2", "page": 8, "tableRow": 27 }, "auxiliary": false }, { "taskId": "S2-028", "benchmark": "WorldScore", "scope": "T2", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Image-conditioned interface", "measuredReadout": "3D / photometric consistency", "source": { "table": "S2", "page": 8, "tableRow": 28 }, "auxiliary": false }, { "taskId": "S2-029", "benchmark": "Apple-π", "scope": "T2", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Spatial-geometry / state consistency with references", "source": { "table": "S2", "page": 8, "tableRow": 29 }, "auxiliary": false }, { "taskId": "S2-030", "benchmark": "CausalSpatial", "scope": "T2", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "TPR, NSR and MCQ correctness for occlusion, compatibility and trajectories", "source": { "table": "S2", "page": 8, "tableRow": 30 }, "auxiliary": false }, { "taskId": "S2-031", "benchmark": "Chess-World-Model", "scope": "T2", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Human PGN held-out 10k / rule replay", "measuredReadout": "75-label exact-state / field accuracy", "source": { "table": "S2", "page": 8, "tableRow": 31 }, "auxiliary": false }, { "taskId": "S2-032", "benchmark": "Chess-World-Model", "scope": "T2", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Random legal self-play 10k / rule replay", "measuredReadout": "75-label exact-state / field accuracy", "source": { "table": "S2", "page": 8, "tableRow": 32 }, "auxiliary": false }, { "taskId": "S2-033", "benchmark": "ContactWorld", "scope": "T2", "protocol": "CL", "metric": "O", "data": "HCP", "dataStatus": "classified", "taskBranch": "Simulated execution / geometric goals", "measuredReadout": "Joint object / end-effector position-and- orientation threshold success", "source": { "table": "S2", "page": 8, "tableRow": 33 }, "auxiliary": false }, { "taskId": "S2-034", "benchmark": "CrashTwin", "scope": "T2", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Geometric rigidity; object-trajectory / spatial stability", "source": { "table": "S2", "page": 8, "tableRow": 34 }, "auxiliary": false }, { "taskId": "S2-035", "benchmark": "DrivingGen", "scope": "T2", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "Open-domain driving", "measuredReadout": "SLAM / reconstructed-trajectory and scene consistency", "source": { "table": "S2", "page": 8, "tableRow": 35 }, "auxiliary": false }, { "taskId": "S2-036", "benchmark": "DrivingGen", "scope": "T2", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "Ego-conditioned driving", "measuredReadout": "SLAM / reconstructed-trajectory and scene consistency", "source": { "table": "S2", "page": 8, "tableRow": 36 }, "auxiliary": false }, { "taskId": "S2-037", "benchmark": "EZS-Bench", "scope": "T2", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Scene / entity-state checklist judgments", "source": { "table": "S2", "page": 8, "tableRow": 37 }, "auxiliary": false }, { "taskId": "S2-038", "benchmark": "H2R-Bench", "scope": "T2", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "Main 240 cases / no robot reference image / predicates", "measuredReadout": "M4 Embodiment Correctness (structural temporal retention); M1 goal-state", "source": { "table": "S2", "page": 8, "tableRow": 38 }, "auxiliary": false }, { "taskId": "S2-039", "benchmark": "H2R-Bench", "scope": "T2", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "dataResolution": "final-consistency-checklist", "taskBranch": "Robot-reference-image ablation / predicates", "measuredReadout": "M4 Embodiment Correctness (structural temporal retention); M1 goal-state", "source": { "table": "S2", "page": 8, "tableRow": 39 }, "auxiliary": false }, { "taskId": "S2-040", "benchmark": "HarnessEval-W", "scope": "T2", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Revisit Consistency; protected anchor / state preservation", "source": { "table": "S2", "page": 8, "tableRow": 40 }, "auxiliary": false }, { "taskId": "S2-041", "benchmark": "HOCA-Bench", "scope": "T2", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskBranch": "Generated spatial / entity anomalies", "measuredReadout": "Tasks II/III category / anomaly- description accuracy; spatial-anomaly temporal mIoU, R@0.5", "source": { "table": "S2", "page": 8, "tableRow": 41 }, "auxiliary": false }, { "taskId": "S2-042", "benchmark": "HTEWorld", "scope": "T2", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Predicted versus reference state / spatial consistency", "source": { "table": "S2", "page": 8, "tableRow": 42 }, "auxiliary": false }, { "taskId": "S2-043", "benchmark": "iWorld-Bench", "scope": "T2", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Scene-return / spatial consistency", "source": { "table": "S2", "page": 8, "tableRow": 43 }, "auxiliary": false }, { "taskId": "S2-044", "benchmark": "MBench", "scope": "T2", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Entity / environment memory consistency", "source": { "table": "S2", "page": 8, "tableRow": 44 }, "auxiliary": false }, { "taskId": "S2-045", "benchmark": "MemoBench", "scope": "T2", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Geometry and reappearance consistency scores", "source": { "table": "S2", "page": 8, "tableRow": 45 }, "auxiliary": false }, { "taskId": "S2-046", "benchmark": "MIND", "scope": "T2", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Revisited-scene spatial reconstruction / consistency", "source": { "table": "S2", "page": 8, "tableRow": 46 }, "auxiliary": false }, { "taskId": "S2-047", "benchmark": "MiraBench", "scope": "T2", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Spatial-state / object-relation consistency", "source": { "table": "S2", "page": 9, "tableRow": 47 }, "auxiliary": false }, { "taskId": "S2-048", "benchmark": "Omni-WorldBench", "scope": "T2", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskBranch": "T2V presence", "measuredReadout": "InterStab-L revisit similarity; InterStab- N non-target stability; Object Control", "source": { "table": "S2", "page": 9, "tableRow": 48 }, "auxiliary": false }, { "taskId": "S2-049", "benchmark": "Omni-WorldBench", "scope": "T2", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "IT2V presence", "measuredReadout": "InterStab-L revisit similarity; InterStab- N non-target stability; Object Control", "source": { "table": "S2", "page": 9, "tableRow": 49 }, "auxiliary": false }, { "taskId": "S2-050", "benchmark": "Omni-WorldBench", "scope": "T2", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "With Camera presence", "measuredReadout": "InterStab-L revisit similarity; InterStab- N non-target stability; Object Control", "source": { "table": "S2", "page": 9, "tableRow": 50 }, "auxiliary": false }, { "taskId": "S2-051", "benchmark": "OSCBench", "scope": "T2", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Object-state change; scene-consistency rubric", "source": { "table": "S2", "page": 9, "tableRow": 51 }, "auxiliary": false }, { "taskId": "S2-052", "benchmark": "PDI-Bench", "scope": "T2", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Scale-depth alignment; 3D structural rigidity", "source": { "table": "S2", "page": 9, "tableRow": 52 }, "auxiliary": false }, { "taskId": "S2-053", "benchmark": "PlayWorld", "scope": "T2", "protocol": "CL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Feedback-based test subset", "measuredReadout": "Entity / world-state consistency VQA", "source": { "table": "S2", "page": 9, "tableRow": 53 }, "auxiliary": false }, { "taskId": "S2-054", "benchmark": "RBench", "scope": "T2", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Robot / object stability; spatial-relation scores", "source": { "table": "S2", "page": 9, "tableRow": 54 }, "auxiliary": false }, { "taskId": "S2-055", "benchmark": "RigidBench", "scope": "T2", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "IoU; Chamfer distance; depth / position / geometry errors", "source": { "table": "S2", "page": 9, "tableRow": 55 }, "auxiliary": false }, { "taskId": "S2-056", "benchmark": "RoboTrustBench", "scope": "T2", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Entity / spatiotemporal-consistency rubric", "source": { "table": "S2", "page": 9, "tableRow": 56 }, "auxiliary": false }, { "taskId": "S2-057", "benchmark": "ScratchWorld", "scope": "T2", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "F Value-aware changed-field (primary); 1 full-state field accuracy (diagnostic)", "source": { "table": "S2", "page": 9, "tableRow": 57 }, "auxiliary": false }, { "taskId": "S2-058", "benchmark": "STEVO-Bench", "scope": "T2", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskBranch": "Curated initial scenes / task YAML verifier", "measuredReadout": "Coherence / spatial-state consistency", "source": { "table": "S2", "page": 9, "tableRow": 58 }, "auxiliary": false }, { "taskId": "S2-059", "benchmark": "SurgWMBench", "scope": "T2", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "Teacher forcing / joint task", "measuredReadout": "Tool-point ADE / FDE", "source": { "table": "S2", "page": 9, "tableRow": 59 }, "auxiliary": false }, { "taskId": "S2-060", "benchmark": "SurgWMBench", "scope": "T2", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "Autoregressive rollout", "measuredReadout": "ADE / FDE at 5 / 10 / 15 steps", "source": { "table": "S2", "page": 9, "tableRow": 60 }, "auxiliary": false }, { "taskId": "S2-061", "benchmark": "SurgWMBench", "scope": "T2", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "Perturb-and-recover", "measuredReadout": "ADE / FDE and degradation after noise / random masking", "source": { "table": "S2", "page": 9, "tableRow": 61 }, "auxiliary": false }, { "taskId": "S2-062", "benchmark": "WBench", "scope": "T2", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Spatial-structure / entity-consistency components", "source": { "table": "S2", "page": 9, "tableRow": 62 }, "auxiliary": false }, { "taskId": "S2-063", "benchmark": "What-If World", "scope": "T2", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "A-P-O-E Environment consistency", "source": { "table": "S2", "page": 9, "tableRow": 63 }, "auxiliary": false }, { "taskId": "S2-064", "benchmark": "WMBench", "scope": "T2", "protocol": "CL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Direct diagnostics of policy- feedback rollouts", "measuredReadout": "Subject / scene consistency diagnostics", "source": { "table": "S2", "page": 9, "tableRow": 64 }, "auxiliary": false }, { "taskId": "S2-065", "benchmark": "WMBench", "scope": "T2", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "I2V no-control baseline (Table 3)", "measuredReadout": "Subject Consistency", "source": { "table": "S2", "page": 9, "tableRow": 65 }, "auxiliary": false }, { "taskId": "S2-066", "benchmark": "WorldArena", "scope": "T2", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "3D accuracy; perspective / depth consis- tency", "source": { "table": "S2", "page": 9, "tableRow": 66 }, "auxiliary": false }, { "taskId": "S2-067", "benchmark": "WorldArena 2.0", "scope": "T2", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Direct video diagnostics / RoboTwin-LIBERO", "measuredReadout": "3D accuracy; depth / perspective", "source": { "table": "S2", "page": 9, "tableRow": 67 }, "auxiliary": false }, { "taskId": "S2-068", "benchmark": "WorldArena 2.0", "scope": "T2", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "Direct video diagnostics / real ALOHA", "measuredReadout": "3D accuracy; depth / perspective", "source": { "table": "S2", "page": 9, "tableRow": 68 }, "auxiliary": false }, { "taskId": "S2-069", "benchmark": "WorldBench", "scope": "T2", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Intuitive-physics video generation", "measuredReadout": "Foreground mIoU; background RMSE on intuitive-physics generation (object / scene retention)", "source": { "table": "S2", "page": 9, "tableRow": 69 }, "auxiliary": false }, { "taskId": "S2-070", "benchmark": "WorldExam", "scope": "T2", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Scene Revisit", "measuredReadout": "Revisit PSNR / SSIM / LPIPS; 3D consis- tency", "source": { "table": "S2", "page": 10, "tableRow": 70 }, "auxiliary": false }, { "taskId": "S2-071", "benchmark": "WorldMark", "scope": "T2", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "World consistency; scene geometry", "source": { "table": "S2", "page": 10, "tableRow": 71 }, "auxiliary": false }, { "taskId": "S2-072", "benchmark": "WorldOlympiad", "scope": "T2", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "3D / body / state consistency; cross- segment spatial retention", "source": { "table": "S2", "page": 10, "tableRow": 72 }, "auxiliary": false }, { "taskId": "S2-073", "benchmark": "WorldRoamBench", "scope": "T2", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Scene / object spatial consistency", "source": { "table": "S2", "page": 10, "tableRow": 73 }, "auxiliary": false }, { "taskId": "S2-074", "benchmark": "WoW-World-Eval", "scope": "T2", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Fixed generated-video diagnostics", "measuredReadout": "Robot / object / scene consistency; trajectory position error", "source": { "table": "S2", "page": 10, "tableRow": 74 }, "auxiliary": false }, { "taskId": "S2-075", "benchmark": "XEWorld", "scope": "T2", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Fixed test subset = closed-loop. Level: P = prediction-level; SPTC = scenario/prompt/task curation; data category; protocol and metric initial-world images with independently HCP describes this construction pipeline, Player decisions; unsupported origins of the 63 selected data codes. 240 cases are RWD; SBG as an analysis under the survey's over rule-generated states. They to RoG feedback that controls video refers to adaptive step/rewind observation", "measuredReadout": "Morphology masks; structure / geometry reprojection consistency O = downstream outcome. Data: RWD HCP = hybrid construction. NR denotes △ level are classified separately. = cross-category specified long-horizon objectives, not a verified real/synthetic breakdown cases of a specific generator are not standard-track nonphysical VBench2 images are not resolved. the robot-reference-image ablation lacks controlled-world definition: human PGN are retained as separate branches. extension. This coding does not, by itself, queries over a fixed underlying trajectory;", "source": { "table": "S2", "page": 10, "tableRow": 75 }, "auxiliary": false }, { "taskId": "S3-001", "benchmark": "AutumnBench", "scope": "T3", "protocol": "CL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Long-prefix MFP with adaptive step/rewind queries after exploration", "measuredReadout": "Masked final-state accuracy after long action sequences", "source": { "table": "S3", "page": 11, "tableRow": 1 }, "auxiliary": false }, { "taskId": "S3-002", "benchmark": "AutumnBench", "scope": "T3", "protocol": "CL", "metric": "O", "data": "SBG", "dataStatus": "classified", "taskBranch": "Long-horizon goal planning", "measuredReadout": "Goal-reaching planning success", "source": { "table": "S3", "page": 11, "tableRow": 2 }, "auxiliary": false }, { "taskId": "S3-003", "benchmark": "LoopNav", "scope": "T3", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "SGCS / scene recovery at long revisit intervals", "source": { "table": "S3", "page": 11, "tableRow": 3 }, "auxiliary": false }, { "taskId": "S3-004", "benchmark": "SmallWorlds", "scope": "T3", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Long-horizon prediction error", "source": { "table": "S3", "page": 11, "tableRow": 4 }, "auxiliary": false }, { "taskId": "S3-005", "benchmark": "WorldPrediction", "scope": "T3", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Sequence-choice accuracy for 3-10-step Procedural Planning", "source": { "table": "S3", "page": 11, "tableRow": 5 }, "auxiliary": false }, { "taskId": "S3-006", "benchmark": "Chess-World-Model", "scope": "T3", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Human PGN held-out 10k / rule replay", "measuredReadout": "Multistep exact-trajectory / state accuracy", "source": { "table": "S3", "page": 11, "tableRow": 6 }, "auxiliary": false }, { "taskId": "S3-007", "benchmark": "Chess-World-Model", "scope": "T3", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Random legal self-play 10k / rule replay", "measuredReadout": "Multistep exact-trajectory / state accuracy", "source": { "table": "S3", "page": 11, "tableRow": 7 }, "auxiliary": false }, { "taskId": "S3-008", "benchmark": "ContactWorld", "scope": "T3", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "USB fixed latent prediction", "measuredReadout": "Latent rollout prediction MSE at 1-6 steps", "source": { "table": "S3", "page": 11, "tableRow": 8 }, "auxiliary": false }, { "taskId": "S3-009", "benchmark": "ContactWorld", "scope": "T3", "protocol": "CL", "metric": "O", "data": "HCP", "dataStatus": "classified", "taskBranch": "Simulated planning / goal- offset horizon", "measuredReadout": "Mean success at 12 / 24 / 36 / 48-step goal offsets", "source": { "table": "S3", "page": 11, "tableRow": 9 }, "auxiliary": false }, { "taskId": "S3-010", "benchmark": "ExPhy", "scope": "T3", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "ADE / FDE across horizons", "source": { "table": "S3", "page": 11, "tableRow": 10 }, "auxiliary": false }, { "taskId": "S3-011", "benchmark": "HarnessEval-W", "scope": "T3", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Drift Resistance; Revisit Consistency; Offscreen Evolution", "source": { "table": "S3", "page": 11, "tableRow": 11 }, "auxiliary": false }, { "taskId": "S3-012", "benchmark": "HTEWorld", "scope": "T3", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Late-stage state retention; cross-chunk consistency", "source": { "table": "S3", "page": 11, "tableRow": 12 }, "auxiliary": false }, { "taskId": "S3-013", "benchmark": "iWorld-Bench", "scope": "T3", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Memory-revisit consistency", "source": { "table": "S3", "page": 11, "tableRow": 13 }, "auxiliary": false }, { "taskId": "S3-014", "benchmark": "MBench", "scope": "T3", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Entity / environment / causal-memory retention; gated reliability", "source": { "table": "S3", "page": 11, "tableRow": 14 }, "auxiliary": false }, { "taskId": "S3-015", "benchmark": "MemoBench", "scope": "T3", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Long-term state / memory VQA after disappearance and reappearance", "source": { "table": "S3", "page": 11, "tableRow": 15 }, "auxiliary": false }, { "taskId": "S3-016", "benchmark": "MIND", "scope": "T3", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Memory-reconstruction score", "source": { "table": "S3", "page": 11, "tableRow": 16 }, "auxiliary": false }, { "taskId": "S3-017", "benchmark": "PlayWorld", "scope": "T3", "protocol": "CL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Feedback-based test subset", "measuredReadout": "Insight Evolution; long-term state- consistency VQA", "source": { "table": "S3", "page": 11, "tableRow": 17 }, "auxiliary": false }, { "taskId": "S3-018", "benchmark": "RBench", "scope": "T3", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Instruction-sequence / long-range completeness in multistage tasks", "source": { "table": "S3", "page": 11, "tableRow": 18 }, "auxiliary": false }, { "taskId": "S3-019", "benchmark": "RoboWM-Bench", "scope": "T3", "protocol": "OL", "metric": "O", "data": "HCP", "dataStatus": "classified", "taskBranch": "Reported video-to-action execution", "measuredReadout": "Multistep task / step execution success", "source": { "table": "S3", "page": 11, "tableRow": 19 }, "auxiliary": false }, { "taskId": "S3-020", "benchmark": "ScratchWorld", "scope": "T3", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Hidden-state accuracy after fixed action sequences", "source": { "table": "S3", "page": 11, "tableRow": 20 }, "auxiliary": false }, { "taskId": "S3-021", "benchmark": "WBench", "scope": "T3", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Multiturn long-term consistency; state retention", "source": { "table": "S3", "page": 11, "tableRow": 21 }, "auxiliary": false }, { "taskId": "S3-022", "benchmark": "WMBench", "scope": "T3", "protocol": "CL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Direct diagnostics of policy- feedback rollouts", "measuredReadout": "Rollout-fidelity / drift diagnostics up to 40 s", "source": { "table": "S3", "page": 11, "tableRow": 22 }, "auxiliary": false }, { "taskId": "S3-023", "benchmark": "WMBench", "scope": "T3", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "40 s autoregressive diagnos- tics (Table 4)", "measuredReadout": "PSNR / FID / FVD per 8 s segment; temporal degradation", "source": { "table": "S3", "page": 11, "tableRow": 23 }, "auxiliary": false }, { "taskId": "S3-024", "benchmark": "WorldMark", "scope": "T3", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "World consistency at 20 / 40 / 60 s", "source": { "table": "S3", "page": 12, "tableRow": 24 }, "auxiliary": false }, { "taskId": "S3-025", "benchmark": "WorldOlympiad", "scope": "T3", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Chunk / transition / global long-range consistency", "source": { "table": "S3", "page": 12, "tableRow": 25 }, "auxiliary": false }, { "taskId": "S3-026", "benchmark": "WorldRoamBench", "scope": "T3", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Departure / return and long-term mem- ory consistency", "source": { "table": "S3", "page": 12, "tableRow": 26 }, "auxiliary": false }, { "taskId": "S3-027", "benchmark": "WoW-World-Eval", "scope": "T3", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Fixed generated-video diagnostics", "measuredReadout": "Plan-DAG decomposition; long-horizon sequence correctness", "source": { "table": "S3", "page": 12, "tableRow": 27 }, "auxiliary": false }, { "taskId": "S3-028", "benchmark": "WR-Arena", "scope": "T3", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Fixed test subset = closed-loop. Level: P = prediction-level; SPTC = scenario/prompt/task curation; initial-world images with independently HCP describes this construction pipeline, Player decisions; unsupported memory judgments and executed rule-replay data are an analyst refers to adaptive step/rewind observation", "measuredReadout": "Additive penalty AP-lambda for rollout degradation O = downstream outcome. Data: RWD △ HCP = hybrid construction. = cross-category specified long-horizon objectives, not a verified real/synthetic breakdown cases of a specific generator are not standard-track goal success are different readouts. Autoregressive SBG coding under the controlled-world definition. queries over a fixed underlying trajectory;", "source": { "table": "S3", "page": 12, "tableRow": 28 }, "auxiliary": false }, { "taskId": "S4-001", "benchmark": "IntPhys", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Fixed test subset prediction", "measuredReadout": "Physical-feasibility classification from loss (absolute / relative)", "source": { "table": "S4", "page": 13, "tableRow": 1 }, "auxiliary": false }, { "taskId": "S4-002", "benchmark": "CLEVRER", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Object / collision-event prediction QA accuracy", "source": { "table": "S4", "page": 13, "tableRow": 2 }, "auxiliary": false }, { "taskId": "S4-003", "benchmark": "CoPhy", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "3D object-position prediction error; stability correctness", "source": { "table": "S4", "page": 13, "tableRow": 3 }, "auxiliary": false }, { "taskId": "S4-004", "benchmark": "PHYRE", "scope": "T4", "protocol": "CL", "metric": "O", "data": "SBG", "dataStatus": "classified", "taskBranch": "Feedback-enabled / online baseline", "measuredReadout": "AUCCESS", "source": { "table": "S4", "page": 13, "tableRow": 4 }, "auxiliary": false }, { "taskId": "S4-005", "benchmark": "PHYRE", "scope": "T4", "protocol": "OL", "metric": "O", "data": "SBG", "dataStatus": "classified", "taskBranch": "Fixed action-ranking baseline", "measuredReadout": "AUCCESS", "source": { "table": "S4", "page": 13, "tableRow": 5 }, "auxiliary": false }, { "taskId": "S4-006", "benchmark": "CRAFT", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "QA accuracy for collision, contact and basket-entry events", "source": { "table": "S4", "page": 13, "tableRow": 6 }, "auxiliary": false }, { "taskId": "S4-007", "benchmark": "Physion", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Object Contact Prediction accuracy", "source": { "table": "S4", "page": 13, "tableRow": 7 }, "auxiliary": false }, { "taskId": "S4-008", "benchmark": "ComPhy", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Option / question accuracy for mass, charge and physical prediction", "source": { "table": "S4", "page": 13, "tableRow": 8 }, "auxiliary": false }, { "taskId": "S4-009", "benchmark": "Physion++", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Contact-prediction accuracy under different property-observability conditions", "source": { "table": "S4", "page": 13, "tableRow": 9 }, "auxiliary": false }, { "taskId": "S4-010", "benchmark": "ContPhy", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Continuous-physics property and predic- tion QA accuracy", "source": { "table": "S4", "page": 13, "tableRow": 10 }, "auxiliary": false }, { "taskId": "S4-011", "benchmark": "PhyGenBench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Key physical events; physical order; naturalness scores", "source": { "table": "S4", "page": 13, "tableRow": 11 }, "auxiliary": false }, { "taskId": "S4-012", "benchmark": "VideoPhy", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Binary Physical Commonsense score", "source": { "table": "S4", "page": 13, "tableRow": 12 }, "auxiliary": false }, { "taskId": "S4-013", "benchmark": "WorldSimBench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskBranch": "Explicit / T2V", "measuredReadout": "Velocity; Trajectory; Embodied Interaction; Safety", "source": { "table": "S4", "page": 13, "tableRow": 13 }, "auxiliary": false }, { "taskId": "S4-014", "benchmark": "WorldSimBench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Explicit I2V / OE / Minecraft", "measuredReadout": "Velocity; Trajectory; Embodied Interaction", "source": { "table": "S4", "page": 13, "tableRow": 14 }, "auxiliary": false }, { "taskId": "S4-015", "benchmark": "WorldSimBench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "Explicit I2V / AD / nuScenes", "measuredReadout": "Trajectory; Safety", "source": { "table": "S4", "page": 13, "tableRow": 15 }, "auxiliary": false }, { "taskId": "S4-016", "benchmark": "WorldSimBench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "Explicit I2V / RM / RH20T- P", "measuredReadout": "Trajectory; Embodied Interaction", "source": { "table": "S4", "page": 13, "tableRow": 16 }, "auxiliary": false }, { "taskId": "S4-017", "benchmark": "WorldSimBench", "scope": "T4", "protocol": "CL", "metric": "O", "data": "HCP", "dataStatus": "classified", "taskBranch": "Implicit / task execution", "measuredReadout": "MineRL / CARLA / CALVIN task success and action completion", "source": { "table": "S4", "page": 13, "tableRow": 17 }, "auxiliary": false }, { "taskId": "S4-018", "benchmark": "4DWorldBench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskBranch": "Text-to-4D", "measuredReadout": "Physical-law / dynamics-consistency judgments", "source": { "table": "S4", "page": 13, "tableRow": 18 }, "auxiliary": false }, { "taskId": "S4-019", "benchmark": "4DWorldBench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "Image-to-4D / physical WISA", "measuredReadout": "Physical-law / dynamics-consistency judgments", "source": { "table": "S4", "page": 13, "tableRow": 19 }, "auxiliary": false }, { "taskId": "S4-020", "benchmark": "4DWorldBench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "Video-to-4D / physical WISA", "measuredReadout": "Physical-law / dynamics-consistency judgments", "source": { "table": "S4", "page": 13, "tableRow": 20 }, "auxiliary": false }, { "taskId": "S4-021", "benchmark": "DreamGen Bench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Physical alignment / video-level physical- success judgments", "source": { "table": "S4", "page": 13, "tableRow": 21 }, "auxiliary": false }, { "taskId": "S4-022", "benchmark": "EWMBench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Dynamic Consistency: velocity / accelera- tion distributions", "source": { "table": "S4", "page": 13, "tableRow": 22 }, "auxiliary": false }, { "taskId": "S4-023", "benchmark": "GameWorld Score", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Object / scenario consistency under Physical Rule Understanding", "source": { "table": "S4", "page": 13, "tableRow": 23 }, "auxiliary": false }, { "taskId": "S4-024", "benchmark": "Gen-ViRe", "scope": "T4", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Physical-continuity / interaction- feasibility rubric", "source": { "table": "S4", "page": 13, "tableRow": 24 }, "auxiliary": false }, { "taskId": "S4-025", "benchmark": "IntPhys 2", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Solidity / physical-feasibility discrimina- tion accuracy", "source": { "table": "S4", "page": 14, "tableRow": 25 }, "auxiliary": false }, { "taskId": "S4-026", "benchmark": "Morpheus", "scope": "T4", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "Original real-experiment initialization parameter", "measuredReadout": "PINN physical-law fit; conservation / residuals", "source": { "table": "S4", "page": 14, "tableRow": 26 }, "auxiliary": false }, { "taskId": "S4-027", "benchmark": "Morpheus", "scope": "T4", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "COSMOS-Transfer aug- mented initialization parameter", "measuredReadout": "PINN physical-law fit; conservation / residuals", "source": { "table": "S4", "page": 14, "tableRow": 27 }, "auxiliary": false }, { "taskId": "S4-028", "benchmark": "MVP", "scope": "T4", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Fixed test subset pairs", "measuredReadout": "Accuracy on physical-dynamics minimal", "source": { "table": "S4", "page": 14, "tableRow": 28 }, "auxiliary": false }, { "taskId": "S4-029", "benchmark": "PAI-Bench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskBranch": "PAI-G / T2V", "measuredReadout": "Physical-plausibility QA criteria within Domain Score", "source": { "table": "S4", "page": 14, "tableRow": 29 }, "auxiliary": false }, { "taskId": "S4-030", "benchmark": "PAI-Bench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "PAI-G / I2V", "measuredReadout": "Physical-plausibility QA criteria within Domain Score", "source": { "table": "S4", "page": 14, "tableRow": 30 }, "auxiliary": false }, { "taskId": "S4-031", "benchmark": "PAI-Bench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "PAI-U / Physical World QA", "measuredReadout": "Physical-law / object-property QA accuracy", "source": { "table": "S4", "page": 14, "tableRow": 31 }, "auxiliary": false }, { "taskId": "S4-032", "benchmark": "PAI-Bench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "PAI-U / physical constraints", "measuredReadout": "Action-affordance / physical-constraint QA accuracy", "source": { "table": "S4", "page": 14, "tableRow": 32 }, "auxiliary": false }, { "taskId": "S4-033", "benchmark": "PEDRA", "scope": "T4", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "I2V / ETH-UCY reference", "measuredReadout": "Velocity; acceleration; distance; collision; flow; EMD for reference-distribution terms", "source": { "table": "S4", "page": 14, "tableRow": 33 }, "auxiliary": false }, { "taskId": "S4-034", "benchmark": "PEDRA", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskBranch": "T2V / prompt-only", "measuredReadout": "Velocity; acceleration; distance; collision; flow; physical-unit statistics / reference ranges", "source": { "table": "S4", "page": 14, "tableRow": 34 }, "auxiliary": false }, { "taskId": "S4-035", "benchmark": "PhyCoBench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskBranch": "Generator scoring / human physical ranking", "measuredReadout": "Human physical ranking; PhyCoPredictor: inverse weighted flow / frame prediction MSE (Eq. 4)", "source": { "table": "S4", "page": 14, "tableRow": 35 }, "auxiliary": false }, { "taskId": "S4-036", "benchmark": "Physics-IQ", "scope": "T4", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Spatial / spatiotemporal IoU; weighted IoU; MSE", "source": { "table": "S4", "page": 14, "tableRow": 36 }, "auxiliary": false }, { "taskId": "S4-037", "benchmark": "PhyWorldBench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskBranch": "Fixed test subset physics", "measuredReadout": "CAP physical commonsense / anti- adherence", "source": { "table": "S4", "page": 14, "tableRow": 37 }, "auxiliary": false }, { "taskId": "S4-038", "benchmark": "SmallWorlds", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Energy / position / velocity diagnostics", "source": { "table": "S4", "page": 14, "tableRow": 38 }, "auxiliary": false }, { "taskId": "S4-039", "benchmark": "T2VPhysBench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Four-level physical-law adherence", "source": { "table": "S4", "page": 14, "tableRow": 39 }, "auxiliary": false }, { "taskId": "S4-040", "benchmark": "T2VWorldBench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Physical-realism rating", "source": { "table": "S4", "page": 14, "tableRow": 40 }, "auxiliary": false }, { "taskId": "S4-041", "benchmark": "VACT", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Rule consistency in physical- commonsense scenarios", "source": { "table": "S4", "page": 14, "tableRow": 41 }, "auxiliary": false }, { "taskId": "S4-042", "benchmark": "VBench-2.0", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Physical state-change / dynamics consis- tency", "source": { "table": "S4", "page": 14, "tableRow": 42 }, "auxiliary": false }, { "taskId": "S4-043", "benchmark": "VideoPhy-2", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "≥ Five-level PC; joint success with SA 4 ≥ and PC 4", "source": { "table": "S4", "page": 14, "tableRow": 43 }, "auxiliary": false }, { "taskId": "S4-044", "benchmark": "VMBench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "PAS physical adherence; related physical diagnostics", "source": { "table": "S4", "page": 14, "tableRow": 44 }, "auxiliary": false }, { "taskId": "S4-045", "benchmark": "WorldLens", "scope": "T4", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "Generation / reconstruction diagnostics", "measuredReadout": "Human / evaluator Physical Plausibility ratings (H.2)", "source": { "table": "S4", "page": 14, "tableRow": 45 }, "auxiliary": false }, { "taskId": "S4-046", "benchmark": "WorldModelBench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskBranch": "T2V", "measuredReadout": "Binary scores on five physical laws", "source": { "table": "S4", "page": 14, "tableRow": 46 }, "auxiliary": false }, { "taskId": "S4-047", "benchmark": "WorldModelBench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "I2V", "measuredReadout": "Binary scores on five physical laws", "source": { "table": "S4", "page": 14, "tableRow": 47 }, "auxiliary": false }, { "taskId": "S4-048", "benchmark": "ACWM-Phys", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Masked MSE; prediction error in physical scenes", "source": { "table": "S4", "page": 15, "tableRow": 48 }, "auxiliary": false }, { "taskId": "S4-049", "benchmark": "Apple-π", "scope": "T4", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Physical diagnostics rescaled to the requested physical time", "source": { "table": "S4", "page": 15, "tableRow": 49 }, "auxiliary": false }, { "taskId": "S4-050", "benchmark": "CaliBench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskBranch": "Nine curated initial scenes / analytic distributions power", "measuredReadout": "Scorability; mnTV; chi-squared statistic; / confidence intervals", "source": { "table": "S4", "page": 15, "tableRow": 50 }, "auxiliary": false }, { "taskId": "S4-051", "benchmark": "CausalSpatial", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "TPR / NSR for collision and physical feasibility questions", "source": { "table": "S4", "page": 15, "tableRow": 51 }, "auxiliary": false }, { "taskId": "S4-052", "benchmark": "ContactWorld", "scope": "T4", "protocol": "CL", "metric": "O", "data": "HCP", "dataStatus": "classified", "taskBranch": "Simulated contact tasks / tactile ablations", "measuredReadout": "Contact-task success; success changes under modality ablations", "source": { "table": "S4", "page": 15, "tableRow": 52 }, "auxiliary": false }, { "taskId": "S4-053", "benchmark": "CrashTwin", "scope": "T4", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Momentum and energy residuals; collision diagnostics", "source": { "table": "S4", "page": 15, "tableRow": 53 }, "auxiliary": false }, { "taskId": "S4-054", "benchmark": "CRONOS", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Motion similarity; VLM physical score; thresholded success rate", "source": { "table": "S4", "page": 15, "tableRow": 54 }, "auxiliary": false }, { "taskId": "S4-055", "benchmark": "DrivingGen", "scope": "T4", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "Open-domain driving", "measuredReadout": "Physical-plausibility / motion-plausibility judgments", "source": { "table": "S4", "page": 15, "tableRow": 55 }, "auxiliary": false }, { "taskId": "S4-056", "benchmark": "DrivingGen", "scope": "T4", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "Ego-conditioned driving", "measuredReadout": "Physical-plausibility / motion-plausibility judgments", "source": { "table": "S4", "page": 15, "tableRow": 56 }, "auxiliary": false }, { "taskId": "S4-057", "benchmark": "ExPhy", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "ADE / FDE; normalized MAE of mass, friction and restitution", "source": { "table": "S4", "page": 15, "tableRow": 57 }, "auxiliary": false }, { "taskId": "S4-058", "benchmark": "EZS-Bench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Physical feasibility and interaction checklist judgments", "source": { "table": "S4", "page": 15, "tableRow": 58 }, "auxiliary": false }, { "taskId": "S4-059", "benchmark": "GAUGE", "scope": "T4", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "Video world model", "measuredReadout": "Dynamic Error; physical-parameter deviation; period / energy diagnostics", "source": { "table": "S4", "page": 15, "tableRow": 59 }, "auxiliary": false }, { "taskId": "S4-060", "benchmark": "GAUGE", "scope": "T4", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Numerical physics-engine comparator*", "measuredReadout": "Motion-capture versus reconstructed- simulation trajectory / physical-parameter deviations", "source": { "table": "S4", "page": 15, "tableRow": 60 }, "auxiliary": true }, { "taskId": "S4-061", "benchmark": "H2R-Bench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "Main 240 cases / no robot reference image", "measuredReadout": "M3 Functional Contact Transfer", "source": { "table": "S4", "page": 15, "tableRow": 61 }, "auxiliary": false }, { "taskId": "S4-062", "benchmark": "H2R-Bench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "dataResolution": "final-consistency-checklist", "taskBranch": "Robot-reference-image ablation", "measuredReadout": "M3 Functional Contact Transfer", "source": { "table": "S4", "page": 15, "tableRow": 62 }, "auxiliary": false }, { "taskId": "S4-063", "benchmark": "HarnessEval-W", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Physical Observation / Physical Transition item scores", "source": { "table": "S4", "page": 15, "tableRow": 63 }, "auxiliary": false }, { "taskId": "S4-064", "benchmark": "HOCA-Bench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Task I / matched real and generated", "measuredReadout": "Plausibility Check F1", "source": { "table": "S4", "page": 15, "tableRow": 64 }, "auxiliary": false }, { "taskId": "S4-065", "benchmark": "HOCA-Bench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskBranch": "Generated anomalies: Tasks II-IV / advanced probes", "measuredReadout": "Domain / description accuracy; physical explanations (0-100); temporal mIoU / R@0.5; multi-anomaly F1 / Exact Match", "source": { "table": "S4", "page": 15, "tableRow": 65 }, "auxiliary": false }, { "taskId": "S4-066", "benchmark": "HTEWorld", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Stagewise motion / physical-state consis- tency", "source": { "table": "S4", "page": 15, "tableRow": 66 }, "auxiliary": false }, { "taskId": "S4-067", "benchmark": "KineBench", "scope": "T4", "protocol": "CL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Robot-centric kinematic diagnosis", "measuredReadout": "SPARC; Maruyama manipulability", "source": { "table": "S4", "page": 15, "tableRow": 67 }, "auxiliary": false }, { "taskId": "S4-068", "benchmark": "KineBench", "scope": "T4", "protocol": "CL", "metric": "O", "data": "HCP", "dataStatus": "classified", "taskBranch": "Physical-manipulation execution", "measuredReadout": "Execution success on 20 physical- manipulation tasks", "source": { "table": "S4", "page": 15, "tableRow": 68 }, "auxiliary": false }, { "taskId": "S4-069", "benchmark": "MBench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Hidden-process evolution criteria in causal memory", "source": { "table": "S4", "page": 15, "tableRow": 69 }, "auxiliary": false }, { "taskId": "S4-070", "benchmark": "MemoBench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Physical plausibility VQA subdimensions", "source": { "table": "S4", "page": 15, "tableRow": 70 }, "auxiliary": false }, { "taskId": "S4-071", "benchmark": "MiraBench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Physical constraints; interaction correct- ness", "source": { "table": "S4", "page": 15, "tableRow": 71 }, "auxiliary": false }, { "taskId": "S4-072", "benchmark": "Omni-WorldBench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskBranch": "T2V", "measuredReadout": "InterCov effect coverage; InterOrder event order; InterStab-N non-target physical stability", "source": { "table": "S4", "page": 16, "tableRow": 72 }, "auxiliary": false }, { "taskId": "S4-073", "benchmark": "Omni-WorldBench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "IT2V", "measuredReadout": "InterCov effect coverage; InterOrder event order; InterStab-N non-target physical stability", "source": { "table": "S4", "page": 16, "tableRow": 73 }, "auxiliary": false }, { "taskId": "S4-074", "benchmark": "Omni-WorldBench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "With Camera", "measuredReadout": "InterCov effect coverage; InterOrder event order; InterStab-N non-target physical stability", "source": { "table": "S4", "page": 16, "tableRow": 74 }, "auxiliary": false }, { "taskId": "S4-075", "benchmark": "PDI-Bench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "3D motion consistency; nonphysical acceleration / angle jumps; rigidity residuals", "source": { "table": "S4", "page": 16, "tableRow": 75 }, "auxiliary": false }, { "taskId": "S4-076", "benchmark": "PhyGround", "scope": "T4", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "250 TI2V cases / expected outcomes specified (13", "measuredReadout": "1-5 scores on 2-4 applicable laws per case laws); PTV; Object Persistence and supplementary readouts", "source": { "table": "S4", "page": 16, "tableRow": 76 }, "auxiliary": false }, { "taskId": "S4-077", "benchmark": "PhysicsMind", "scope": "T4", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Fixed VQA", "measuredReadout": "Physical-property / commonsense MCQ accuracy", "source": { "table": "S4", "page": 16, "tableRow": 77 }, "auxiliary": false }, { "taskId": "S4-078", "benchmark": "PhysicsMind", "scope": "T4", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Fixed video prediction", "measuredReadout": "Geometry; torque-related terminal states; inertia-related velocity / acceleration measures", "source": { "table": "S4", "page": 16, "tableRow": 78 }, "auxiliary": false }, { "taskId": "S4-079", "benchmark": "Physion-Eval", "scope": "T4", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "Generator physical diagnos- tics physical", "measuredReadout": "Expert ratings of generated glitches / realism", "source": { "table": "S4", "page": 16, "tableRow": 79 }, "auxiliary": false }, { "taskId": "S4-080", "benchmark": "Physion-Eval", "scope": "T4", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Human / model critic- pool* validation", "measuredReadout": "Source-blinded realism / physical- anomaly judgments", "source": { "table": "S4", "page": 16, "tableRow": 80 }, "auxiliary": true }, { "taskId": "S4-081", "benchmark": "PlayWorld", "scope": "T4", "protocol": "CL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Feedback-based test subset", "measuredReadout": "Physical plausibility VQA", "source": { "table": "S4", "page": 16, "tableRow": 81 }, "auxiliary": false }, { "taskId": "S4-082", "benchmark": "RBench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Physical semantics; contact / physical- constraint scores", "source": { "table": "S4", "page": 16, "tableRow": 82 }, "auxiliary": false }, { "taskId": "S4-083", "benchmark": "ReactSim-Bench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Fixed test subset violations;", "measuredReadout": "Agent-agent collision; off-road / direction kinematic infeasibility", "source": { "table": "S4", "page": 16, "tableRow": 83 }, "auxiliary": false }, { "taskId": "S4-084", "benchmark": "RigidBench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "ATE / ATE3D; trajectory-based physical- consistency proxies", "source": { "table": "S4", "page": 16, "tableRow": 84 }, "auxiliary": false }, { "taskId": "S4-085", "benchmark": "RoboTrustBench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Physical-interaction / plausibility rubric", "source": { "table": "S4", "page": 16, "tableRow": 85 }, "auxiliary": false }, { "taskId": "S4-086", "benchmark": "RoboWM-Bench", "scope": "T4", "protocol": "OL", "metric": "O", "data": "HCP", "dataStatus": "classified", "taskBranch": "Reported video-to-action execution", "measuredReadout": "Step / task success on physically exe- cutable tasks", "source": { "table": "S4", "page": 16, "tableRow": 86 }, "auxiliary": false }, { "taskId": "S4-087", "benchmark": "STEVO-Bench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskBranch": "Curated initial scenes / task YAML", "measuredReadout": "Physics / state-evolution progress verifier", "source": { "table": "S4", "page": 16, "tableRow": 87 }, "auxiliary": false }, { "taskId": "S4-088", "benchmark": "WBench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Physical-fidelity components", "source": { "table": "S4", "page": 16, "tableRow": 88 }, "auxiliary": false }, { "taskId": "S4-089", "benchmark": "What-If World", "scope": "T4", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "A-P-O-E Physical plausibility", "source": { "table": "S4", "page": 16, "tableRow": 89 }, "auxiliary": false }, { "taskId": "S4-090", "benchmark": "WMBench", "scope": "T4", "protocol": "CL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Direct diagnostics of policy- feedback rollouts", "measuredReadout": "Dynamic / physical-fidelity diagnostics", "source": { "table": "S4", "page": 16, "tableRow": 90 }, "auxiliary": false }, { "taskId": "S4-091", "benchmark": "WorldArena", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Physics adherence", "source": { "table": "S4", "page": 16, "tableRow": 91 }, "auxiliary": false }, { "taskId": "S4-092", "benchmark": "WorldArena 2.0", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Direct video diagnostics / RoboTwin-LIBERO", "measuredReadout": "Physics adherence; interaction quality", "source": { "table": "S4", "page": 16, "tableRow": 92 }, "auxiliary": false }, { "taskId": "S4-093", "benchmark": "WorldArena 2.0", "scope": "T4", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "Direct video diagnostics / real ALOHA", "measuredReadout": "Physics adherence; interaction quality", "source": { "table": "S4", "page": 16, "tableRow": 93 }, "auxiliary": false }, { "taskId": "S4-094", "benchmark": "WorldBench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Intuitive / parametric physics generation /", "measuredReadout": "Intuitive-physics generation mIoU; gravity friction / viscosity estimation error; QA is separate appendix evidence", "source": { "table": "S4", "page": 17, "tableRow": 94 }, "auxiliary": false }, { "taskId": "S4-095", "benchmark": "WorldExam", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskBranch": "Physical Reaction", "measuredReadout": "Physical-reaction checklist: expected collision, gravity and friction dynamics", "source": { "table": "S4", "page": 17, "tableRow": 95 }, "auxiliary": false }, { "taskId": "S4-096", "benchmark": "WorldOlympiad", "scope": "T4", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Physical-plausibility / dynamics rubric", "source": { "table": "S4", "page": 17, "tableRow": 96 }, "auxiliary": false }, { "taskId": "S4-097", "benchmark": "WorldRoamBench", "scope": "T4", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Physics validity after control gating", "source": { "table": "S4", "page": 17, "tableRow": 97 }, "auxiliary": false }, { "taskId": "S4-098", "benchmark": "WorldSimProbe", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Object-interaction dynamics diagnostics", "source": { "table": "S4", "page": 17, "tableRow": 98 }, "auxiliary": false }, { "taskId": "S4-099", "benchmark": "WoW-World-Eval", "scope": "T4", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Video-physics diagnostics", "measuredReadout": "Physical commonsense; trajectory-physics diagnostics", "source": { "table": "S4", "page": 17, "tableRow": 99 }, "auxiliary": false }, { "taskId": "S4-100", "benchmark": "WoW-World-Eval", "scope": "T4", "protocol": "OL", "metric": "O", "data": "HCP", "dataStatus": "classified", "taskBranch": "GC-IDM real execution: physical feasibility", "measuredReadout": "Real-world success across nine tasks", "source": { "table": "S4", "page": 17, "tableRow": 100 }, "auxiliary": false }, { "taskId": "S4-101", "benchmark": "XEWorld", "scope": "T4", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Fixed test subset = closed-loop. Level: P = prediction-level; SPTC = scenario/prompt/task curation; data category; protocol and metric initial-world images with independently HCP describes this construction pipeline, Player decisions; unsupported 240 cases are RWD; critic-validation pool and evaluation track. readouts, not Kendall/Spearman language QA is separate appendix", "measuredReadout": "Object trajectories versus simulated reference motion O = downstream outcome. Data: RWD HCP = hybrid construction. NR denotes △ level are classified separately. = cross-category specified long-horizon objectives, not a verified real/synthetic breakdown cases of a specific generator are not standard-track the robot-reference-image ablation lacks GAUGE numerical-engine comparison are Generator scores and evaluator-validation statistics judge-validation correlations. PhyGround evidence, not an additional readout on", "source": { "table": "S4", "page": 17, "tableRow": 101 }, "auxiliary": false }, { "taskId": "S5-001", "benchmark": "CLEVRER", "scope": "T5", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Fixed test subset question", "measuredReadout": "Explanatory / predictive / counterfactual accuracy", "source": { "table": "S5", "page": 18, "tableRow": 1 }, "auxiliary": false }, { "taskId": "S5-002", "benchmark": "CoPhy", "scope": "T5", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Fixed test subset prediction", "measuredReadout": "Post-intervention 3D position / stability for counterfactual D", "source": { "table": "S5", "page": 18, "tableRow": 2 }, "auxiliary": false }, { "taskId": "S5-003", "benchmark": "CRAFT", "scope": "T5", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Causal and counterfactual QA accuracy", "source": { "table": "S5", "page": 18, "tableRow": 3 }, "auxiliary": false }, { "taskId": "S5-004", "benchmark": "Physion", "scope": "T5", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "OCP accuracy for physical-event chains", "source": { "table": "S5", "page": 18, "tableRow": 4 }, "auxiliary": false }, { "taskId": "S5-005", "benchmark": "Causal-VidQA", "scope": "T5", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "Fixed test subset questions", "measuredReadout": "Answer and rationale accuracy for explanation, prediction and counterfactual", "source": { "table": "S5", "page": 18, "tableRow": 5 }, "auxiliary": false }, { "taskId": "S5-006", "benchmark": "ComPhy", "scope": "T5", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Counterfactual QA accuracy under mass / charge changes", "source": { "table": "S5", "page": 18, "tableRow": 6 }, "auxiliary": false }, { "taskId": "S5-007", "benchmark": "ACQUIRED", "scope": "T5", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Counterfactual answer accuracy; pairwise accuracy", "source": { "table": "S5", "page": 18, "tableRow": 7 }, "auxiliary": false }, { "taskId": "S5-008", "benchmark": "ContPhy", "scope": "T5", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Counterfactual QA and goal-directed action-choice accuracy", "source": { "table": "S5", "page": 18, "tableRow": 8 }, "auxiliary": false }, { "taskId": "S5-009", "benchmark": "MMWorld", "scope": "T5", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Causal / counterfactual MCQ accuracy", "source": { "table": "S5", "page": 18, "tableRow": 9 }, "auxiliary": false }, { "taskId": "S5-010", "benchmark": "AutumnBench", "scope": "T5", "protocol": "CL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Change Detection", "measuredReadout": "Change-time localization score", "source": { "table": "S5", "page": 18, "tableRow": 10 }, "auxiliary": false }, { "taskId": "S5-011", "benchmark": "CausalVQA", "scope": "T5", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "Fixed test subset planning", "measuredReadout": "Paired score on causal, counterfactual and MCQs", "source": { "table": "S5", "page": 18, "tableRow": 11 }, "auxiliary": false }, { "taskId": "S5-012", "benchmark": "MVP", "scope": "T5", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Accuracy on causal / counterfactual minimal pairs", "source": { "table": "S5", "page": 18, "tableRow": 12 }, "auxiliary": false }, { "taskId": "S5-013", "benchmark": "PAI-Bench", "scope": "T5", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "PAI-U / Time-causality QA", "measuredReadout": "Causality-question accuracy within Time", "source": { "table": "S5", "page": 18, "tableRow": 13 }, "auxiliary": false }, { "taskId": "S5-014", "benchmark": "PAI-Bench", "scope": "T5", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "PAI-U / Predicting Action Effects", "measuredReadout": "Task-state judgment; next-plausible-action QA accuracy", "source": { "table": "S5", "page": 18, "tableRow": 14 }, "auxiliary": false }, { "taskId": "S5-015", "benchmark": "Physics-IQ", "scope": "T5", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "IoU / MSE for physical-event continua- tion", "source": { "table": "S5", "page": 18, "tableRow": 15 }, "auxiliary": false }, { "taskId": "S5-016", "benchmark": "T2VWorldBench", "scope": "T5", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskBranch": "Causality prompt subset", "measuredReadout": "Five-level realism / consistency ratings and domain mean on Causality prompts", "source": { "table": "S5", "page": 18, "tableRow": 16 }, "auxiliary": false }, { "taskId": "S5-017", "benchmark": "VACT", "scope": "T5", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Causal-rule / generation consistency", "source": { "table": "S5", "page": 18, "tableRow": 17 }, "auxiliary": false }, { "taskId": "S5-018", "benchmark": "WorldPrediction", "scope": "T5", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "World Modelling: action-choice accuracy between two states", "source": { "table": "S5", "page": 18, "tableRow": 18 }, "auxiliary": false }, { "taskId": "S5-019", "benchmark": "CausalSpatial", "scope": "T5", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "TPR / NSR for hypothetical action consequences", "source": { "table": "S5", "page": 18, "tableRow": 19 }, "auxiliary": false }, { "taskId": "S5-020", "benchmark": "CRONOS", "scope": "T5", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Fixed test subset physical-factor", "measuredReadout": "Sensitivity comparisons under visual / interventions", "source": { "table": "S5", "page": 18, "tableRow": 20 }, "auxiliary": false }, { "taskId": "S5-021", "benchmark": "HarnessEval-W", "scope": "T5", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Expected post-intervention dynamics in Physical Transition", "source": { "table": "S5", "page": 18, "tableRow": 21 }, "auxiliary": false }, { "taskId": "S5-022", "benchmark": "HOCA-Bench", "scope": "T5", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskBranch": "Task IV / normative counter- factual explanations", "measuredReadout": "Judge score (0-100) for four-part expla- nations, including violated laws and expected normal outcomes", "source": { "table": "S5", "page": 18, "tableRow": 22 }, "auxiliary": false }, { "taskId": "S5-023", "benchmark": "MiraBench", "scope": "T5", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Criteria comparing normal / failed action consequences", "source": { "table": "S5", "page": 18, "tableRow": 23 }, "auxiliary": false }, { "taskId": "S5-024", "benchmark": "PhysicsMind", "scope": "T5", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Fixed VQA", "measuredReadout": "Physical / causal MCQ accuracy", "source": { "table": "S5", "page": 19, "tableRow": 24 }, "auxiliary": false }, { "taskId": "S5-025", "benchmark": "PhysicsMind", "scope": "T5", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Fixed video prediction physical", "measuredReadout": "Terminal-state / trajectory criteria under conditions", "source": { "table": "S5", "page": 19, "tableRow": 25 }, "auxiliary": false }, { "taskId": "S5-026", "benchmark": "PlayWorld", "scope": "T5", "protocol": "CL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Feedback-based test subset", "measuredReadout": "Action-consequence / autonomous state- evolution VQA", "source": { "table": "S5", "page": 19, "tableRow": 26 }, "auxiliary": false }, { "taskId": "S5-027", "benchmark": "RBench", "scope": "T5", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Action-consequence and physical- semantic criteria in reasoning tasks", "source": { "table": "S5", "page": 19, "tableRow": 27 }, "auxiliary": false }, { "taskId": "S5-028", "benchmark": "ReactSim-Bench", "scope": "T5", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Factual / deviating fixed AV trajectories", "measuredReadout": "Factual / deviating-condition differences in Agent-AV collision and risky TTC", "source": { "table": "S5", "page": 19, "tableRow": 28 }, "auxiliary": false }, { "taskId": "S5-029", "benchmark": "RoboTrustBench", "scope": "T5", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Fixed test subset plausibility", "measuredReadout": "Action-precondition / consequence / rubric", "source": { "table": "S5", "page": 19, "tableRow": 29 }, "auxiliary": false }, { "taskId": "S5-030", "benchmark": "ScratchWorld", "scope": "T5", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "Event F1; post-intervention difference matching", "source": { "table": "S5", "page": 19, "tableRow": 30 }, "auxiliary": false }, { "taskId": "S5-031", "benchmark": "What-If World", "scope": "T5", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "Fixed test subset", "measuredReadout": "A-P-O-E counterfactual Outcome differ- ence", "source": { "table": "S5", "page": 19, "tableRow": 31 }, "auxiliary": false }, { "taskId": "S5-032", "benchmark": "WorldExam", "scope": "T5", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskBranch": "World Reactivity / reaction tasks", "measuredReadout": "Scene-conditioned reaction checklist: initiating action given, consequences unspecified", "source": { "table": "S5", "page": 19, "tableRow": 32 }, "auxiliary": false }, { "taskId": "S5-033", "benchmark": "WorldSimProbe", "scope": "T5", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Fixed test subset /", "measuredReadout": "Object effects of non-contact interventions action perturbations", "source": { "table": "S5", "page": 19, "tableRow": 33 }, "auxiliary": false }, { "taskId": "S5-034", "benchmark": "WoW-World-Eval", "scope": "T5", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Fixed generated-video diagnostics", "measuredReadout": "Task-DAG dependencies, preconditions and causal order", "source": { "table": "S5", "page": 19, "tableRow": 34 }, "auxiliary": false }, { "taskId": "S5-035", "benchmark": "WR-Arena", "scope": "T5", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Fixed test subset = closed-loop. Level: P = prediction-level; SPTC = scenario/prompt/task curation; initial-world images with independently HCP describes this construction pipeline, Player decisions; unsupported imply realized interventions. Counterfactual evidence limits. HOCA-Bench judges is the benchmark's own understanding", "measuredReadout": "Counterfactual / action-effect correctness; stepwise next-observation correctness O = downstream outcome. Data: RWD △ HCP = hybrid construction. = cross-category specified long-horizon objectives, not a verified real/synthetic breakdown cases of a specific generator are not standard-track explanation, observed-event reasoning normative explanations; T2VWorldBench track, not this survey's Functional", "source": { "table": "S5", "page": 19, "tableRow": 35 }, "auxiliary": false }, { "taskId": "S6-001", "benchmark": "ACT-Bench", "scope": "S5", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "Pre-specified Fixed test subset", "measuredReadout": "Instruction Execution Correctness; Trajec- tory Alignment; ADE/FDE", "source": { "table": "S6", "page": 20, "tableRow": 1 }, "auxiliary": false }, { "taskId": "S6-002", "benchmark": "PhyGenBench", "scope": "S5", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskBranch": "Pre-specified Fixed test subset", "measuredReadout": "Object presence; action / prompt- adherence checks", "source": { "table": "S6", "page": 20, "tableRow": 2 }, "auxiliary": false }, { "taskId": "S6-003", "benchmark": "StoryEval", "scope": "S5", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskBranch": "Pre-specified Sequential-event video judgments with", "measuredReadout": "Sequential-event completion: description then event judgments; completion rate unanimous voting", "source": { "table": "S6", "page": 20, "tableRow": 3 }, "auxiliary": false }, { "taskId": "S6-004", "benchmark": "TC-Bench", "scope": "S5", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskBranch": "Pre-specified T2V / transition completion", "measuredReadout": "Transition Completion; state-change assertions", "source": { "table": "S6", "page": 20, "tableRow": 4 }, "auxiliary": false }, { "taskId": "S6-005", "benchmark": "TC-Bench", "scope": "S5", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "Pre-specified I2V / transition completion", "measuredReadout": "Transition Completion; state-change assertions", "source": { "table": "S6", "page": 20, "tableRow": 5 }, "auxiliary": false }, { "taskId": "S6-006", "benchmark": "VideoPhy", "scope": "S5", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskBranch": "Pre-specified Fixed test subset", "measuredReadout": "Binary Semantic Adherence score", "source": { "table": "S6", "page": 20, "tableRow": 6 }, "auxiliary": false }, { "taskId": "S6-007", "benchmark": "4DWorldBench", "scope": "S5", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskBranch": "Pre-specified Text-to-4D", "measuredReadout": "Condition-adherence judgments", "source": { "table": "S6", "page": 20, "tableRow": 7 }, "auxiliary": false }, { "taskId": "S6-008", "benchmark": "4DWorldBench", "scope": "S5", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "Pre-specified Image-to-4D / physical WISA", "measuredReadout": "Condition-adherence judgments", "source": { "table": "S6", "page": 20, "tableRow": 8 }, "auxiliary": false }, { "taskId": "S6-009", "benchmark": "4DWorldBench", "scope": "S5", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "dataResolution": "final-consistency-checklist", "taskBranch": "Pre-specified Image-to-4D / nonphysical VBench2", "measuredReadout": "Condition-adherence judgments", "source": { "table": "S6", "page": 20, "tableRow": 9 }, "auxiliary": false }, { "taskId": "S6-010", "benchmark": "4DWorldBench", "scope": "S5", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Pre-specified Video-to-4D / mixed suite", "measuredReadout": "Condition-adherence judgments", "source": { "table": "S6", "page": 20, "tableRow": 10 }, "auxiliary": false }, { "taskId": "S6-011", "benchmark": "DreamGen Bench", "scope": "S5", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Pre-specified Fixed test subset", "measuredReadout": "Instruction adherence; video action- completion scores", "source": { "table": "S6", "page": 20, "tableRow": 11 }, "auxiliary": false }, { "taskId": "S6-012", "benchmark": "EWMBench", "scope": "S5", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "Pre-specified Fixed test subset", "measuredReadout": "NDTW and HSD relative to target end- effector trajectories", "source": { "table": "S6", "page": 20, "tableRow": 12 }, "auxiliary": false }, { "taskId": "S6-013", "benchmark": "GameWorld Score", "scope": "S5", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Pre-specified Fixed test subset", "measuredReadout": "Keyboard / mouse action controllability", "source": { "table": "S6", "page": 20, "tableRow": 13 }, "auxiliary": false }, { "taskId": "S6-014", "benchmark": "MagicBench", "scope": "S5", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "Pre-specified Fixed initial-image / trajec- tory generation", "measuredReadout": "Mask / box IoU for control alignment", "source": { "table": "S6", "page": 20, "tableRow": 14 }, "auxiliary": false }, { "taskId": "S6-015", "benchmark": "MoveBench", "scope": "S5", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "Pre-specified Fixed initial-image / trajec- paper tory generation", "measuredReadout": "Trajectory L2 distance, denoted EPE in the", "source": { "table": "S6", "page": 20, "tableRow": 15 }, "auxiliary": false }, { "taskId": "S6-016", "benchmark": "PAI-Bench", "scope": "S5", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "Pre-specified PAI-C / multisignal condi- tional generation", "measuredReadout": "Blur SSIM; Edge F1; Depth si-RMSE; Seg mIoU", "source": { "table": "S6", "page": 20, "tableRow": 16 }, "auxiliary": false }, { "taskId": "S6-017", "benchmark": "PAI-Bench", "scope": "S5", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskBranch": "Pre-specified PAI-G / T2V", "measuredReadout": "Condition / content adherence within PAI-G semantic alignment", "source": { "table": "S6", "page": 20, "tableRow": 17 }, "auxiliary": false }, { "taskId": "S6-018", "benchmark": "PAI-Bench", "scope": "S5", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "Pre-specified PAI-G / I2V", "measuredReadout": "Condition / content adherence within PAI-G semantic alignment", "source": { "table": "S6", "page": 20, "tableRow": 18 }, "auxiliary": false }, { "taskId": "S6-019", "benchmark": "PhyWorldBench", "scope": "S5", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskBranch": "Pre-specified Fixed test subset", "measuredReadout": "CAP semantic adherence", "source": { "table": "S6", "page": 20, "tableRow": 19 }, "auxiliary": false }, { "taskId": "S6-020", "benchmark": "VACT", "scope": "S5", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskBranch": "Pre-specified Fixed test subset", "measuredReadout": "Text consistency; condition-realization rate", "source": { "table": "S6", "page": 20, "tableRow": 20 }, "auxiliary": false }, { "taskId": "S6-021", "benchmark": "VBench-2.0", "scope": "S5", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskBranch": "Pre-specified Fixed test subset", "measuredReadout": "Motion order; complex plot; camera control", "source": { "table": "S6", "page": 20, "tableRow": 21 }, "auxiliary": false }, { "taskId": "S6-022", "benchmark": "VideoPhy-2", "scope": "S5", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskBranch": "Pre-specified Fixed test subset", "measuredReadout": "Five-level SA; joint SA / PC pass rate", "source": { "table": "S6", "page": 21, "tableRow": 22 }, "auxiliary": false }, { "taskId": "S6-023", "benchmark": "WorldModelBench", "scope": "S5", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskBranch": "Pre-specified T2V", "measuredReadout": "Instruction-following score", "source": { "table": "S6", "page": 21, "tableRow": 23 }, "auxiliary": false }, { "taskId": "S6-024", "benchmark": "WorldModelBench", "scope": "S5", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Pre-specified I2V", "measuredReadout": "Instruction-following score", "source": { "table": "S6", "page": 21, "tableRow": 24 }, "auxiliary": false }, { "taskId": "S6-025", "benchmark": "WorldScore", "scope": "S5", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskBranch": "Pre-specified T2V interface", "measuredReadout": "Camera-control error; object / content alignment", "source": { "table": "S6", "page": 21, "tableRow": 25 }, "auxiliary": false }, { "taskId": "S6-026", "benchmark": "WorldScore", "scope": "S5", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Pre-specified Image-conditioned interface", "measuredReadout": "Camera-control error; object / content alignment", "source": { "table": "S6", "page": 21, "tableRow": 26 }, "auxiliary": false }, { "taskId": "S6-027", "benchmark": "Chess-World-Model", "scope": "S5", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Pre-specified Human PGN held-out 10k / rule replay", "measuredReadout": "Exact state update after a given legal move", "source": { "table": "S6", "page": 21, "tableRow": 27 }, "auxiliary": false }, { "taskId": "S6-028", "benchmark": "Chess-World-Model", "scope": "S5", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Pre-specified Random legal self-play 10k / rule replay", "measuredReadout": "Exact state update after a given legal move", "source": { "table": "S6", "page": 21, "tableRow": 28 }, "auxiliary": false }, { "taskId": "S6-029", "benchmark": "DrivingGen", "scope": "S5", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "Pre-specified Ego-conditioned driving only", "measuredReadout": "Ego-conditioned trajectory-following error", "source": { "table": "S6", "page": 21, "tableRow": 29 }, "auxiliary": false }, { "taskId": "S6-030", "benchmark": "EZS-Bench", "scope": "S5", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Pre-specified Fixed test subset", "measuredReadout": "Text-specified action-task checklist completion", "source": { "table": "S6", "page": 21, "tableRow": 30 }, "auxiliary": false }, { "taskId": "S6-031", "benchmark": "H2R-Bench", "scope": "S5", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "Pre-specified Main 240 cases / no robot reference image", "measuredReadout": "M1 Goal-State Completion; M2 Action- Event Completion; M4 requested- embodiment adherence", "source": { "table": "S6", "page": 21, "tableRow": 31 }, "auxiliary": false }, { "taskId": "S6-032", "benchmark": "H2R-Bench", "scope": "S5", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "dataResolution": "final-consistency-checklist", "taskBranch": "Pre-specified Robot-reference-image ablation", "measuredReadout": "M1 Goal-State Completion; M2 Action- Event Completion; M4 requested- embodiment adherence", "source": { "table": "S6", "page": 21, "tableRow": 32 }, "auxiliary": false }, { "taskId": "S6-033", "benchmark": "HarnessEval-W", "scope": "S5", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskBranch": "Pre-specified Fixed test subset", "measuredReadout": "Viewpoint trajectory and intended change in Exploratory / Intentional Transition", "source": { "table": "S6", "page": 21, "tableRow": 33 }, "auxiliary": false }, { "taskId": "S6-034", "benchmark": "KineBench", "scope": "S5", "protocol": "CL", "metric": "O", "data": "HCP", "dataStatus": "classified", "taskBranch": "Pre-specified Specified manipulation-task execution", "measuredReadout": "Execution success for specified tasks / instructions", "source": { "table": "S6", "page": 21, "tableRow": 34 }, "auxiliary": false }, { "taskId": "S6-035", "benchmark": "MBench", "scope": "S5", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "Pre-specified Fixed test subset", "measuredReadout": "Trigger coverage; conditional-action realization reliability", "source": { "table": "S6", "page": 21, "tableRow": 35 }, "auxiliary": false }, { "taskId": "S6-036", "benchmark": "MemoBench", "scope": "S5", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Pre-specified Fixed test subset", "measuredReadout": "Rotation / camera-trajectory adherence scores", "source": { "table": "S6", "page": 21, "tableRow": 36 }, "auxiliary": false }, { "taskId": "S6-037", "benchmark": "MiraBench", "scope": "S5", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Pre-specified Fixed test subset", "measuredReadout": "Task Completion Rate; action adherence", "source": { "table": "S6", "page": 21, "tableRow": 37 }, "auxiliary": false }, { "taskId": "S6-038", "benchmark": "Omni-WorldBench", "scope": "S5", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskBranch": "Pre-specified T2V", "measuredReadout": "Object Control; Content Alignment", "source": { "table": "S6", "page": 21, "tableRow": 38 }, "auxiliary": false }, { "taskId": "S6-039", "benchmark": "Omni-WorldBench", "scope": "S5", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Pre-specified IT2V", "measuredReadout": "Object Control; Content Alignment", "source": { "table": "S6", "page": 21, "tableRow": 39 }, "auxiliary": false }, { "taskId": "S6-040", "benchmark": "Omni-WorldBench", "scope": "S5", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Pre-specified With Camera", "measuredReadout": "Object Control; Content Alignment; Camera Control rotation / translation error", "source": { "table": "S6", "page": 21, "tableRow": 40 }, "auxiliary": false }, { "taskId": "S6-041", "benchmark": "OSCBench", "scope": "S5", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskBranch": "Pre-specified Fixed test subset", "measuredReadout": "Semantic / state change; prompt adher- ence", "source": { "table": "S6", "page": 21, "tableRow": 41 }, "auxiliary": false }, { "taskId": "S6-042", "benchmark": "RBench", "scope": "S5", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "Pre-specified Fixed test subset", "measuredReadout": "Instruction / action-sequence adherence; action magnitude", "source": { "table": "S6", "page": 21, "tableRow": 42 }, "auxiliary": false }, { "taskId": "S6-043", "benchmark": "RoboTrustBench", "scope": "S5", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Pre-specified Fixed test subset", "measuredReadout": "Instruction-adherence / task-completion rubric", "source": { "table": "S6", "page": 22, "tableRow": 43 }, "auxiliary": false }, { "taskId": "S6-044", "benchmark": "ScratchWorld", "scope": "S5", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Pre-specified Fixed test subset", "measuredReadout": "F Value-aware changed-field (primary); 1 full-state field accuracy (diagnostic)", "source": { "table": "S6", "page": 22, "tableRow": 44 }, "auxiliary": false }, { "taskId": "S6-045", "benchmark": "STEVO-Bench", "scope": "S5", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskBranch": "Pre-specified Curated initial scenes / task YAML", "measuredReadout": "Observation / action control verifier", "source": { "table": "S6", "page": 22, "tableRow": 45 }, "auxiliary": false }, { "taskId": "S6-046", "benchmark": "What-If World", "scope": "S5", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "Pre-specified Fixed test subset", "measuredReadout": "A-P-O-E Intervention Adherence", "source": { "table": "S6", "page": 22, "tableRow": 46 }, "auxiliary": false }, { "taskId": "S6-047", "benchmark": "WorldArena", "scope": "S5", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Pre-specified Fixed test subset", "measuredReadout": "Instruction following; action following", "source": { "table": "S6", "page": 22, "tableRow": 47 }, "auxiliary": false }, { "taskId": "S6-048", "benchmark": "WorldEcho", "scope": "S5", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Pre-specified Fixed test subset", "measuredReadout": "SE(3) NDTW action-following error", "source": { "table": "S6", "page": 22, "tableRow": 48 }, "auxiliary": false }, { "taskId": "S6-049", "benchmark": "WorldExam", "scope": "S5", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Pre-specified Camera Control", "measuredReadout": "Translation Error; Rotation Error", "source": { "table": "S6", "page": 22, "tableRow": 49 }, "auxiliary": false }, { "taskId": "S6-050", "benchmark": "WorldExam", "scope": "S5", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskBranch": "Pre-specified Subject Control", "measuredReadout": "Checklist for specified-subject action / direction adherence", "source": { "table": "S6", "page": 22, "tableRow": 50 }, "auxiliary": false }, { "taskId": "S6-051", "benchmark": "WorldSimProbe", "scope": "S5", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Pre-specified Fixed test subset", "measuredReadout": "Action perturbation and control response across trajectories", "source": { "table": "S6", "page": 22, "tableRow": 51 }, "auxiliary": false }, { "taskId": "S6-052", "benchmark": "WoW-World-Eval", "scope": "S5", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Pre-specified Video instruction adherence", "measuredReadout": "Instruction understanding; action-object sequence alignment", "source": { "table": "S6", "page": 22, "tableRow": 52 }, "auxiliary": false }, { "taskId": "S6-053", "benchmark": "WoW-World-Eval", "scope": "S5", "protocol": "OL", "metric": "O", "data": "HCP", "dataStatus": "classified", "taskBranch": "Pre-specified GC-IDM real execution: action achievement", "measuredReadout": "Real-world success across nine tasks", "source": { "table": "S6", "page": 22, "tableRow": 53 }, "auxiliary": false }, { "taskId": "S6-054", "benchmark": "XEWorld", "scope": "S5", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Pre-specified Fixed test subset", "measuredReadout": "URDF forward-kinematics reprojection; action-condition alignment", "source": { "table": "S6", "page": 22, "tableRow": 54 }, "auxiliary": false }, { "taskId": "S6-055", "benchmark": "WorldSimBench", "scope": "S6", "protocol": "OL", "metric": "P", "data": "SPTC", "dataStatus": "classified", "taskBranch": "Interactive action Explicit / T2V", "measuredReadout": "Instruction Alignment", "source": { "table": "S6", "page": 22, "tableRow": 55 }, "auxiliary": false }, { "taskId": "S6-056", "benchmark": "WorldSimBench", "scope": "S6", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Interactive action Explicit I2V / OE / Minecraft", "measuredReadout": "Instruction Alignment", "source": { "table": "S6", "page": 22, "tableRow": 56 }, "auxiliary": false }, { "taskId": "S6-057", "benchmark": "WorldSimBench", "scope": "S6", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "Interactive action Explicit I2V / AD / nuScenes", "measuredReadout": "Instruction Alignment", "source": { "table": "S6", "page": 22, "tableRow": 57 }, "auxiliary": false }, { "taskId": "S6-058", "benchmark": "WorldSimBench", "scope": "S6", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "Interactive action Explicit I2V / RM / RH20T- P", "measuredReadout": "Instruction Alignment", "source": { "table": "S6", "page": 22, "tableRow": 58 }, "auxiliary": false }, { "taskId": "S6-059", "benchmark": "WorldSimBench", "scope": "S6", "protocol": "CL", "metric": "O", "data": "HCP", "dataStatus": "classified", "taskBranch": "Interactive action Implicit / task execution", "measuredReadout": "MineRL / CARLA / CALVIN task success and action completion", "source": { "table": "S6", "page": 22, "tableRow": 59 }, "auxiliary": false }, { "taskId": "S6-060", "benchmark": "ACWM-Phys", "scope": "S6", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Interactive action Fixed test subset prediction", "measuredReadout": "Action-conditioned Masked MSE / error", "source": { "table": "S6", "page": 22, "tableRow": 60 }, "auxiliary": false }, { "taskId": "S6-061", "benchmark": "HTEWorld", "scope": "S6", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Interactive action Fixed test subset", "measuredReadout": "Instruction retrieval; action-stage align- ment", "source": { "table": "S6", "page": 22, "tableRow": 61 }, "auxiliary": false }, { "taskId": "S6-062", "benchmark": "iWorld-Bench", "scope": "S6", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Interactive action Fixed test subset", "measuredReadout": "Camera-trajectory / action-following scores", "source": { "table": "S6", "page": 22, "tableRow": 62 }, "auxiliary": false }, { "taskId": "S6-063", "benchmark": "MIND", "scope": "S6", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Interactive action Fixed test subset", "measuredReadout": "Action adherence", "source": { "table": "S6", "page": 22, "tableRow": 63 }, "auxiliary": false }, { "taskId": "S6-064", "benchmark": "PlayWorld", "scope": "S6", "protocol": "CL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Interactive action Feedback-based test subset", "measuredReadout": "Action error and adherence under Agent Player feedback", "source": { "table": "S6", "page": 22, "tableRow": 64 }, "auxiliary": false }, { "taskId": "S6-065", "benchmark": "ReactSim-Bench", "scope": "S6", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Interactive action Fixed AV trajectory / TTC autoregressive other agents", "measuredReadout": "Other agents’ Agent-AV collision / risky under fixed AV actions", "source": { "table": "S6", "page": 23, "tableRow": 65 }, "auxiliary": false }, { "taskId": "S6-066", "benchmark": "RoboWM-Bench", "scope": "S6", "protocol": "OL", "metric": "O", "data": "HCP", "dataStatus": "classified", "taskBranch": "Interactive action Reported video-to-action execution", "measuredReadout": "Video-to-action execution / task achieve- ment", "source": { "table": "S6", "page": 23, "tableRow": 66 }, "auxiliary": false }, { "taskId": "S6-067", "benchmark": "WBench", "scope": "S6", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Interactive action Fixed test subset", "measuredReadout": "Fixed action-switch / response-adherence components", "source": { "table": "S6", "page": 23, "tableRow": 67 }, "auxiliary": false }, { "taskId": "S6-068", "benchmark": "WMBench", "scope": "S6", "protocol": "CL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Interactive action Direct diagnostics of policy- feedback rollouts", "measuredReadout": "Trajectory Accuracy; control consistency", "source": { "table": "S6", "page": 23, "tableRow": 68 }, "auxiliary": false }, { "taskId": "S6-069", "benchmark": "WMBench", "scope": "S6", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "Interactive action I2V no-control baseline (Table 3)", "measuredReadout": "Trajectory Accuracy relative to expected trajectories (no-control baseline)", "source": { "table": "S6", "page": 23, "tableRow": 69 }, "auxiliary": false }, { "taskId": "S6-070", "benchmark": "WorldArena 2.0", "scope": "S6", "protocol": "OL", "metric": "P", "data": "SBG", "dataStatus": "classified", "taskBranch": "Interactive action Direct video diagnostics / RoboTwin-LIBERO", "measuredReadout": "Instruction following; action-response sensitivity", "source": { "table": "S6", "page": 23, "tableRow": 70 }, "auxiliary": false }, { "taskId": "S6-071", "benchmark": "WorldArena 2.0", "scope": "S6", "protocol": "OL", "metric": "P", "data": "RWD", "dataStatus": "classified", "taskBranch": "Interactive action Direct video diagnostics / real ALOHA", "measuredReadout": "Instruction following; action-response sensitivity", "source": { "table": "S6", "page": 23, "tableRow": 71 }, "auxiliary": false }, { "taskId": "S6-072", "benchmark": "WorldMark", "scope": "S6", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Interactive action Fixed test subset", "measuredReadout": "WASD control alignment", "source": { "table": "S6", "page": 23, "tableRow": 72 }, "auxiliary": false }, { "taskId": "S6-073", "benchmark": "WorldOlympiad", "scope": "S6", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Interactive action Fixed test subset", "measuredReadout": "Action-prompt following; interaction consistency", "source": { "table": "S6", "page": 23, "tableRow": 73 }, "auxiliary": false }, { "taskId": "S6-074", "benchmark": "WorldRoamBench", "scope": "S6", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Interactive action Fixed test subset", "measuredReadout": "Control fidelity; validity gate", "source": { "table": "S6", "page": 23, "tableRow": 74 }, "auxiliary": false }, { "taskId": "S6-075", "benchmark": "WR-Arena", "scope": "S6", "protocol": "OL", "metric": "P", "data": "HCP", "dataStatus": "classified", "taskBranch": "Interactive action Fixed test subset = closed-loop. Level: P = prediction-level; SPTC = scenario/prompt/task curation; data category; protocol and metric initial-world images with independently HCP describes this construction pipeline, Player decisions; unsupported origins of the 63 selected data codes. 240 cases are RWD; are preserved as organizational actions and fixed AV trajectories can", "measuredReadout": "Simulation fidelity given actions O = downstream outcome. Data: RWD HCP = hybrid construction. NR denotes △ level are classified separately. = cross-category specified long-horizon objectives, not a verified real/synthetic breakdown cases of a specific generator are not standard-track nonphysical VBench2 images are not resolved. the robot-reference-image ablation lacks labels; membership in Interactive Action be evaluated OL. PAI-C denotes the source", "source": { "table": "S6", "page": 23, "tableRow": 75 }, "auxiliary": false }, { "taskId": "S7-001", "benchmark": "WorldArena", "scope": "S7", "protocol": "OL", "metric": "O", "data": "HCP", "dataStatus": "classified", "taskBranch": "Data engine Policy training with gener- ated data", "measuredReadout": "pi0.5 training-data gain / task success", "source": { "table": "S7", "page": 24, "tableRow": 1 }, "auxiliary": false }, { "taskId": "S7-002", "benchmark": "WorldArena 2.0", "scope": "S7", "protocol": "OL", "metric": "O", "data": "HCP", "dataStatus": "classified", "taskBranch": "Data engine Generated data for policy training", "measuredReadout": "Policy task success after training with generated data", "source": { "table": "S7", "page": 24, "tableRow": 2 }, "auxiliary": false }, { "taskId": "S7-003", "benchmark": "WMBench", "scope": "S8", "protocol": "CL", "metric": "O", "data": "HCP", "dataStatus": "classified", "taskBranch": "Policy evaluator Policy-evaluation reliability", "measuredReadout": "World-model / real success; ranking correlation", "source": { "table": "S7", "page": 24, "tableRow": 3 }, "auxiliary": false }, { "taskId": "S7-004", "benchmark": "WorldArena", "scope": "S8", "protocol": "CL", "metric": "O", "data": "HCP", "dataStatus": "classified", "taskBranch": "Policy evaluator Policy interaction with the model environment", "measuredReadout": "Success correlation with actual RoboTwin simulator execution", "source": { "table": "S7", "page": 24, "tableRow": 4 }, "auxiliary": false }, { "taskId": "S7-005", "benchmark": "EVA-Bench", "scope": "S9", "protocol": "OL", "metric": "O", "data": "HCP", "dataStatus": "classified", "taskBranch": "Planner CALVIN / without RoG", "measuredReadout": "Simulation task success (Table 5)", "source": { "table": "S7", "page": 24, "tableRow": 5 }, "auxiliary": false }, { "taskId": "S7-006", "benchmark": "EVA-Bench", "scope": "S9", "protocol": "CL", "metric": "O", "data": "HCP", "dataStatus": "classified", "taskBranch": "Planner CALVIN / EVA with RoG", "measuredReadout": "Simulation task success (Table 5)", "source": { "table": "S7", "page": 24, "tableRow": 6 }, "auxiliary": false }, { "taskId": "S7-007", "benchmark": "WorldSimBench", "scope": "S9", "protocol": "CL", "metric": "O", "data": "HCP", "dataStatus": "classified", "taskBranch": "Planner Implicit / planner execution", "measuredReadout": "Simulator task success", "source": { "table": "S7", "page": 24, "tableRow": 7 }, "auxiliary": false }, { "taskId": "S7-008", "benchmark": "AutumnBench", "scope": "S9", "protocol": "CL", "metric": "O", "data": "SBG", "dataStatus": "classified", "taskBranch": "Planner Autumn goal planning", "measuredReadout": "Goal-reaching success", "source": { "table": "S7", "page": 24, "tableRow": 8 }, "auxiliary": false }, { "taskId": "S7-009", "benchmark": "World-in-World", "scope": "S9", "protocol": "CL", "metric": "O", "data": "HCP", "dataStatus": "classified", "taskBranch": "Planner Feedback-based test subset", "measuredReadout": "Task success rate; mean plan length", "source": { "table": "S7", "page": 24, "tableRow": 9 }, "auxiliary": false }, { "taskId": "S7-010", "benchmark": "WorldLens", "scope": "S9", "protocol": "OL", "metric": "O", "data": "HCP", "dataStatus": "classified", "taskBranch": "Planner Open-Loop Adherence (A.2)", "measuredReadout": "PDMS", "source": { "table": "S7", "page": 24, "tableRow": 10 }, "auxiliary": false }, { "taskId": "S7-011", "benchmark": "WorldLens", "scope": "S9", "protocol": "CL", "metric": "O", "data": "HCP", "dataStatus": "classified", "taskBranch": "Planner Closed-Loop Adherence (A.3-A.4)", "measuredReadout": "Route Completion; ADS", "source": { "table": "S7", "page": 24, "tableRow": 11 }, "auxiliary": false }, { "taskId": "S7-012", "benchmark": "ContactWorld", "scope": "S9", "protocol": "CL", "metric": "O", "data": "HCP", "dataStatus": "classified", "taskBranch": "Planner MPC / 12 simulated tasks", "measuredReadout": "Task success under joint goal-pose thresholds", "source": { "table": "S7", "page": 24, "tableRow": 12 }, "auxiliary": false }, { "taskId": "S7-013", "benchmark": "ContactWorld", "scope": "S9", "protocol": "CL", "metric": "O", "data": "HCP", "dataStatus": "classified", "taskBranch": "Planner MPC / real valve", "measuredReadout": "Valve success: at least 80% of target rotation, without contact loss or premature release", "source": { "table": "S7", "page": 24, "tableRow": 13 }, "auxiliary": false }, { "taskId": "S7-014", "benchmark": "KineBench", "scope": "S9", "protocol": "CL", "metric": "O", "data": "HCP", "dataStatus": "classified", "taskBranch": "Planner ManiSkill3 planner execu- tion", "measuredReadout": "Execution success, reported separately for four suites", "source": { "table": "S7", "page": 24, "tableRow": 14 }, "auxiliary": false }, { "taskId": "S7-015", "benchmark": "RoboWM-Bench", "scope": "S9", "protocol": "OL", "metric": "O", "data": "HCP", "dataStatus": "classified", "taskBranch": "Planner Reported video-to-action execution", "measuredReadout": "Task success after action decoding", "source": { "table": "S7", "page": 24, "tableRow": 15 }, "auxiliary": false }, { "taskId": "S7-016", "benchmark": "WorldArena", "scope": "S9", "protocol": "CL", "metric": "O", "data": "HCP", "dataStatus": "classified", "taskBranch": "Planner IDM action execution", "measuredReadout": "RoboTwin task success", "source": { "table": "S7", "page": 24, "tableRow": 16 }, "auxiliary": false }, { "taskId": "S7-017", "benchmark": "WorldArena 2.0", "scope": "S9", "protocol": "CL", "metric": "O", "data": "HCP", "dataStatus": "classified", "taskBranch": "Planner Cross-platform action planning / execution", "measuredReadout": "Planner task success", "source": { "table": "S7", "page": 24, "tableRow": 17 }, "auxiliary": false }, { "taskId": "S7-018", "benchmark": "WorldArena 2.0", "scope": "S9", "protocol": "CL", "metric": "O", "data": "HCP", "dataStatus": "classified", "taskBranch": "Planner UniVTAC visuotactile action head", "measuredReadout": "Insert HDMI / Lift Bottle task success", "source": { "table": "S7", "page": 24, "tableRow": 18 }, "auxiliary": false }, { "taskId": "S7-019", "benchmark": "WoW-World-Eval", "scope": "S9", "protocol": "OL", "metric": "O", "data": "HCP", "dataStatus": "classified", "taskBranch": "Planner GC-IDM real execution", "measuredReadout": "Real-world success across nine tasks", "source": { "table": "S7", "page": 25, "tableRow": 19 }, "auxiliary": false }, { "taskId": "S7-020", "benchmark": "WR-Arena", "scope": "S9", "protocol": "CL", "metric": "O", "data": "HCP", "dataStatus": "classified", "taskBranch": "Planner Open-ended planning / Agibot15", "measuredReadout": "Human trajectory-level completion", "source": { "table": "S7", "page": 25, "tableRow": 20 }, "auxiliary": false }, { "taskId": "S7-021", "benchmark": "WR-Arena", "scope": "S9", "protocol": "CL", "metric": "O", "data": "HCP", "dataStatus": "classified", "taskBranch": "Planner Structured planning / LanguageTable47", "measuredReadout": "Human goal-achievement judgments", "source": { "table": "S7", "page": 25, "tableRow": 21 }, "auxiliary": false }, { "taskId": "S7-022", "benchmark": "WorldArena 2.0", "scope": "S10", "protocol": "CL", "metric": "O", "data": "HCP", "dataStatus": "classified", "taskBranch": "Training environment RoboTwin online RL = closed-loop. Level: P = prediction-level; SPTC = scenario/prompt/task curation; are HCP because generated data validation; its fixed video diagnostics the authors' explicit description reproduced. CL is coded from the authors' description loop. Feedback scheduling is not levels are distinct. Policy-ranking or training. Executed task outcomes replanning. to RoG feedback that controls video", "measuredReadout": "Policy success on adjust-bottle / click-bell tasks O = downstream outcome. Data: RWD △ HCP = hybrid construction. = cross-category or learned-environment rollouts are connected remain SBG. of the RoboTwin action-planner track. The of history- and prediction-conditioned detailed. This task remains separate from cross-platform agreement assesses evaluator reliability; it is not can be measured after a fixed plan (OL), and extension. This coding does not, by itself,", "source": { "table": "S7", "page": 25, "tableRow": 22 }, "auxiliary": false } ], "taskRecordCounts": { "targetTasks": 401, "auxiliary": 2, "displayCombinations": 369, "classifiedData": 401, "unresolvedData": 0, "protocolMetric": { "OL/P": 346, "OL/O": 12, "CL/P": 17, "CL/O": 26 }, "data": { "RWD": 89, "SBG": 88, "SPTC": 71, "HCP": 153 } }, "evaluationRecordFingerprint": "1a1b225a2d62e0d70637aef1e9c283b2a532b8f90e8152d62e864228ef7efc8e", "taskRecordFingerprint": "e81cb0fb6c38954457cb903f73d207c9e734a8f72108e6b9b6a15f2aace8e27d", "sourceArchive": "Main_Manuscript_LaTeX.zip", "sourceArchiveSha256": "dad0477f487c44f847dd7a988677178f65025329d491810fe0ad76bb6738bd9a", "codingChecklist": "网页逐项修改清单(1).md", "codingChecklistSha256": "b6ec17d6c68186f62aab9edb4194be8377ea6d71e232a1a5bf53a1ff815be1a4" }