mlsanityData to 14 Oct 2026

WorldScore: A Unified Evaluation Benchmark for World Generation

arXiv 2504.00983 ↗First posted 1 Apr 2025cs.GR cs.AI cs.CVcited by 156

Not on the map. Why?

Cited by 81 in World models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We introduce the WorldScore benchmark, the first unified benchmark for world generation. We decompose world generation into a sequence of next-scene generation tasks with explicit camera trajectory-based layout specifications, enabling unified evaluation of diverse approaches from 3D and 4D scene generation to video generation models. The WorldScore benchmark encompasses a curated dataset of 3,000 test examples that span diverse worlds: static and dynamic, indoor and outdoor, photorealistic and stylized. The WorldScore metrics evaluate generated worlds through three key aspects: controllability, quality, and dynamics. Through extensive evaluation of 19 representative models, including both open-source and closed-source ones, we reveal key insights and challenges for each category of models. Our dataset, evaluation code, and leaderboard can be found at https://haoyi-duan.github.io/WorldScore/

Key facts. Cited by 156 papers in the map (data through 14 Oct 2026). Builds on 79 of its 100 references that are in the map. First posted on arXiv 1 Apr 2025.

Builds on

79 of 100 references.

References · 79

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  4. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  5. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  6. 2022Scalable Diffusion Models with Transformerscited by 6,054
  7. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  8. 2017Neural Discrete Representation Learningcited by 4,712
  9. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,588
  10. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,332
  11. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,253
  12. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,988
38 more
  1. 2024SAM 2: Segment Anything in Images and Videoscited by 2,863
  2. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,626
  3. 2021CLIPScore: A Reference-free Evaluation Metric for Image Captioningcited by 2,424
  4. 2024CogVideoX: Text-to-Video Diffusion Models with An Expert Transformercited by 2,261
  5. 2014Conditional Generative Adversarial Netscited by 2,162
  6. 2023VBench: Comprehensive Benchmark Suite for Video Generative Modelscited by 1,822
  7. 2022Make-A-Video: Text-to-Video Generation without Text-Video Datacited by 1,742
  8. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,495
  9. 2017Matterport3D: Learning from RGB-D Data in Indoor Environmentscited by 1,376
  10. 2024Depth Anything: Unleashing the Power of Large-Scale Unlabeled Datacited by 1,360
  11. 2021Alias-Free Generative Adversarial Networkscited by 1,184
  12. 2021MUSIQ: Multi-scale Image Quality Transformercited by 1,081
  13. 2022Exploring CLIP for Assessing the Look and Feel of Imagescited by 991
  14. 2022CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformerscited by 985
  15. 2025Cosmos World Foundation Model Platform for Physical AIcited by 864
  16. 2021DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Camerascited by 687
  17. 2023ModelScope Text-to-Video Technical Reportcited by 658
  18. 2023ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depthcited by 657
  19. 2020Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understandingcited by 604
  20. 2024LTX-Video: Realtime Video Latent Diffusioncited by 581
  21. 2023MotionCtrl: A Unified and Flexible Motion Controller for Video Generationcited by 580
  22. 2024VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Modelscited by 579
  23. 2023Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levelscited by 503
  24. 2015A Neural Algorithm of Artistic Stylecited by 483
  25. 2023DynamiCrafter: Animating Open-domain Images with Video Diffusion Priorscited by 471
  26. 2024CameraCtrl: Enabling Camera Control for Text-to-Video Generationcited by 460
  27. 2023LAVIE: High-Quality Video Generation with Cascaded Latent Diffusion Modelscited by 349
  28. 2024OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generationcited by 341
  29. 2023EvalCrafter: Benchmarking and Evaluating Large Video Generation Modelscited by 340
  30. 2023VideoFusion: Decomposed Diffusion Models for High-Quality Video Generationcited by 331
  31. 2023Text2Room: Extracting Textured 3D Meshes from 2D Text-to-Image Modelscited by 245
  32. 2019DIODE: A Dense Indoor and Outdoor DEpth Datasetcited by 240
  33. 2023LucidDreamer: Domain-free Generation of 3D Gaussian Splatting Scenescited by 231
  34. 2024How Far is Video Generation from World Model: A Physical Law Perspectivecited by 212
  35. 2023Text-To-4D Dynamic Scene Generationcited by 205
  36. 2024WonderWorld: Interactive 3D Scene Generation from a Single Imagecited by 202
  37. 2023DreamGaussian4D: Generative 4D Gaussian Splattingcited by 194
  38. 20234D-fy: Text-to-4D Generation Using Hybrid Score Distillation Samplingcited by 185

50 most cited of 79 All 79 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 46; 2026: 110.

156 papers.

Sort:

By area:

  1. 2025World Simulation with Video Foundation Models for Physical AIcited by 200
  2. 2025DreamGen: Unlocking Generalization in Robot Learning through Video World Modelscited by 179
  3. 2025WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modelingcited by 170
  4. 2025Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modelingcited by 96
  5. 2025Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Modelscited by 90
  6. 2026WorldArena: A Unified Benchmark for Evaluating Perception and Functional Utility of Embodied World Modelscited by 76
  7. 2025OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generationcited by 73
  8. 20253D and 4D World Modeling: A Surveycited by 67
  9. 2025WoW: Towards a World omniscient World model Through Embodied Interactioncited by 67
  10. 2025GigaWorld-0: World Models as Data Engine to Empower Embodied AIcited by 62
  11. 2026World Action Models: The Next Frontier in Embodied AIcited by 50
  12. 2025World-in-World: World Models in a Closed-Loop Worldcited by 47
38 more
  1. 2026Lyra 2.0: Explorable Generative 3D Worldscited by 44
  2. 2026HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worldscited by 44
  3. 2025NewtonGen: Physics-Consistent and Controllable Text-to-Video Generation via Neural Newtonian Dynamicscited by 41
  4. 2025Spatia: Video Generation with Updatable Spatial Memorycited by 40
  5. 2026DreamX-World 1.0: A General-Purpose Interactive World Modelcited by 40
  6. 2025FantasyWorld: Geometry-Consistent World Modeling via Unified Video and 3D Predictioncited by 38
  7. 2025PAN: A World Model for General, Actionable, and Long-Horizon World Simulationcited by 36
  8. 2025Matrix-3D: Omnidirectional Explorable 3D World Generationcited by 35
  9. 2026MIND: Benchmarking Memory Consistency and Action Control in World Modelscited by 35
  10. 2025PAI-Bench: A Comprehensive Benchmark For Physical AIcited by 34
  11. 2025VideoHallu: Evaluating and Mitigating Multi-modal Hallucinations on Synthetic Video Understandingcited by 32
  12. 2025FlashWorld: High-quality 3D Scene Generation within Secondscited by 32
  13. 2026LiveWorld: Simulating Out-of-Sight Dynamics in Generative Video World Modelscited by 28
  14. 2026Out of Sight but Not Out of Mind: Hybrid Memory for Dynamic Video World Modelscited by 26
  15. 2026WorldMark: A Unified Benchmark Suite for Interactive Video World Modelscited by 26
  16. 20253D Scene Generation: A Surveycited by 24
  17. 2025T2AV-Compass: Towards Unified Evaluation for Text-to-Audio-Video Generationcited by 24
  18. 2025WorldLens: Full-Spectrum Evaluations of Driving World Models in Real Worldcited by 23
  19. 2026MultiWorld: Scalable Multi-Agent Multi-View Video World Modelscited by 23
  20. 2026RealWonder: Real-Time Physical Action-Conditioned Video Generationcited by 22
  21. 2026DrivingGen: A Comprehensive Benchmark for Generative Video World Models in Autonomous Drivingcited by 21
  22. 2026INSPATIO-WORLD: A Real-Time 4D World Simulator via Spatiotemporal Autoregressive Modelingcited by 21
  23. 2025WorldPrediction: A Benchmark for High-level World Modeling and Long-horizon Procedural Planningcited by 20
  24. 2025TiViBench: Benchmarking Think-in-Video Reasoning for Video Generative Modelscited by 19
  25. 2025Taming Video Models for 3D and 4D Generation via Zero-Shot Camera Controlcited by 18
  26. 2026WorldStereo: Bridging Camera-Guided Video Generation and Scene Reconstruction via 3D Geometric Memoriescited by 18
  27. 2026Omni-WorldBench: Towards a Comprehensive Interaction-Centric Evaluation for World Modelscited by 18
  28. 2026MBench: A Comprehensive Benchmark on Memory Capability for Video World Modelscited by 18
  29. 2025I2-NeRF: Learning Neural Radiance Fields Under Physically-Grounded Media Interactionscited by 17
  30. 2026Latent Spatial Memory for Video World Modelscited by 17
  31. 2025TeleWorld: Towards Dynamic Multimodal Synthesis with a 4D World Modelcited by 16
  32. 2025Simulating the Visual World with Artificial Intelligence: A Roadmapcited by 15
  33. 2026Addressable Memory for Video World Modelscited by 15
  34. 2026Physion-Eval: Evaluating Physical Realism in Generated Video via Human Reasoningcited by 14
  35. 2026iWorld-Bench: A Benchmark for Interactive World Models with a Unified Action Generation Frameworkcited by 14
  36. 2025VoxDet: Rethinking 3D Semantic Occupancy Prediction as Dense Object Detectioncited by 13
  37. 2025Environment Scaling for Interactive Agentic Experience Collection: A Surveycited by 13
  38. 2025RULER-Bench: Probing Rule-based Reasoning Abilities of Next-level Video Generation Models for Vision Foundation Intelligencecited by 13

50 most cited of 156 All 156 (JSON)