# WorldLens: Full-Spectrum Evaluations of Driving World Models in Real World

arXiv: https://arxiv.org/abs/2512.10958 · HTML: https://mlsanity.com/paper/2512.10958/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Placed in Video-generation world models and simulators, one of 11 directions in World models.
- Builds on 44 of its 148 references that are in the map.
- First posted on arXiv 11 Dec 2025.

## Placed in

- World models / [Video-generation world models and simulators](https://mlsanity.com/wm/video-generation-world-models-and-simulators/)
- End-to-end autonomous driving / [Generative simulation for driving](https://mlsanity.com/driving/generative-simulation-for-driving/)

## Builds on (most cited first, 30 of 44)

- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [The Kinetics Human Action Video Dataset](https://mlsanity.com/paper/1705.06950/) (2017)
- [Imagen Video: High Definition Video Generation with Diffusion Models](https://mlsanity.com/paper/2210.02303/) (2022)
- [Towards Accurate Generative Models of Video: A New Metric & Challenges](https://mlsanity.com/paper/1812.01717/) (2018)
- [Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks](https://mlsanity.com/paper/2401.14159/) (2024)
- [VideoGPT: Video Generation using VQ-VAE and Transformers](https://mlsanity.com/paper/2104.10157/) (2021)
- [GAIA-1: A Generative World Model for Autonomous Driving](https://mlsanity.com/paper/2309.17080/) (2023)
- [Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion](https://mlsanity.com/paper/2506.08009/) (2025)
- [NuPlan: A closed-loop ML-based planning benchmark for autonomous vehicles](https://mlsanity.com/paper/2106.11810/) (2021)
- [Visual Transformers: Token-based Image Representation and Processing for Computer Vision](https://mlsanity.com/paper/2006.03677/) (2020)
- [VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness](https://mlsanity.com/paper/2503.21755/) (2025)
- [How Far is Video Generation from World Model: A Physical Law Perspective](https://mlsanity.com/paper/2411.02385/) (2024)
- [Self-Forcing++: Towards Minute-Scale High-Quality Video Generation](https://mlsanity.com/paper/2510.02283/) (2025)
- [GAIA-2: A Controllable Multi-View Generative World Model for Autonomous Driving](https://mlsanity.com/paper/2503.20523/) (2025)
- [WorldScore: A Unified Evaluation Benchmark for World Generation](https://mlsanity.com/paper/2504.00983/) (2025)
- [OASIS: Open Agent Social Interaction Simulations with One Million Agents](https://mlsanity.com/paper/2411.11581/) (2024)
- [ADriver-I: A General World Model for Autonomous Driving](https://mlsanity.com/paper/2311.13549/) (2023)
- [BEVControl: Accurately Controlling Street-view Elements with Multi-perspective Consistency via BEV Sketch Layout](https://mlsanity.com/paper/2308.01661/) (2023)
- [Controllable Video Generation: A Survey](https://mlsanity.com/paper/2507.16869/) (2025)
- [MineWorld: a Real-Time and Open-Source Interactive World Model on Minecraft](https://mlsanity.com/paper/2504.08388/) (2025)
- [DrivingGPT: Unifying Driving World Modeling and Planning with Multi-modal Autoregressive Transformers](https://mlsanity.com/paper/2412.18607/) (2024)
- [Cosmos-Drive-Dreams: Scalable Synthetic Driving Data Generation with World Foundation Models](https://mlsanity.com/paper/2506.09042/) (2025)
- [3D and 4D World Modeling: A Survey](https://mlsanity.com/paper/2509.07996/) (2025)
- [Vchitect-2.0: Parallel Transformer for Scaling Up Video Diffusion Models](https://mlsanity.com/paper/2501.08453/) (2025)
- [VBench++: Comprehensive and Versatile Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2411.13503/) (2024)
- [A Survey on Long Video Generation: Challenges, Methods, and Prospects](https://mlsanity.com/paper/2403.16407/) (2024)
- [DreamForge: Motion-Aware Autoregressive Video Generation for Multi-View Driving Scenes](https://mlsanity.com/paper/2409.04003/) (2024)
- [VaViM and VaVAM: Autonomous Driving through Video Generative Modeling](https://mlsanity.com/paper/2502.15672/) (2025)
- [VChain: Chain-of-Visual-Thought for Reasoning in Video Generation](https://mlsanity.com/paper/2510.05094/) (2025)

## Built on by (most cited first, 23 of 23)

- [WorldArena: A Unified Benchmark for Evaluating Perception and Functional Utility of Embodied World Models](https://mlsanity.com/paper/2602.08971/) (2026)
- [WBench: A Comprehensive Multi-turn Benchmark for Interactive Video World Model Evaluation](https://mlsanity.com/paper/2605.25874/) (2026)
- [Bridging Scene Generation and Planning: Driving with World Model via Unifying Vision and Motion Representation](https://mlsanity.com/paper/2603.14948/) (2026)
- [Language-Conditioned World Modeling for Visual Navigation](https://mlsanity.com/paper/2603.26741/) (2026)
- [WorldRoamBench: An Open-World Benchmark for Long-Horizon Stability of Interactive World Models](https://mlsanity.com/paper/2606.31672/) (2026)
- [Is Your Driving World Model an All-Around Player?](https://mlsanity.com/paper/2605.10858/) (2026)
- [SPIRAL: Self-Evolving Action-Conditioned Video Generation via Reflective Planning Agents](https://mlsanity.com/paper/2603.08403/) (2026)
- [MME-CoF-Pro: Evaluating Reasoning Coherence in Video Generative Models with Text and Visual Hints](https://mlsanity.com/paper/2603.20194/) (2026)
- [CausalDrive: Real-time Causal World Models for Autonomous Driving](https://mlsanity.com/paper/2606.15341/) (2026)
- [Forging Spatial Intelligence: A Roadmap of Multi-Modal Data Pre-Training for Autonomous Systems](https://mlsanity.com/paper/2512.24385/) (2025)
- [IRIS: A Real-World Benchmark for Inverse Recovery and Identification of Physical Dynamic Systems from Monocular Video](https://mlsanity.com/paper/2603.16432/) (2026)
- [From Articulated Kinematics to Routed Visual Control for Action-Conditioned Surgical Video Generation](https://mlsanity.com/paper/2605.08712/) (2026)
- [WorldExam: Benchmarking World Models from Apparent Appearance to Inherent Reactivity](https://mlsanity.com/paper/2608.02603/) (2026)
- [World Models as Group Actions](https://mlsanity.com/paper/2605.24578/) (2026)
- [OmniLiDAR: A Unified Diffusion Framework for Multi-Domain 3D LiDAR Generation](https://mlsanity.com/paper/2605.13815/) (2026)
- [StressDream: Steering Video World Models for Robust Policy Evaluation and Improvement](https://mlsanity.com/paper/2606.00267/) (2026)
- [Semantic-Aware, Physics-Informed, Geometry-Grounded Weather Video Synthesis](https://mlsanity.com/paper/2606.29020/) (2026)
- [OccDirector: Language-Guided Behavior and Interaction Generation in 4D Occupancy Space](https://mlsanity.com/paper/2604.22240/) (2026)
- [SPVC: Structured and Panoptic Video Fixing for Cross-Dataset Driving Scene Rendering](https://mlsanity.com/paper/2608.17420/) (2026)
- [DreamStream: Towards Policy-Oriented Generative Simulation for End-to-End Driving](https://mlsanity.com/paper/2609.26792/) (2026)
- [VehDyn: A Driving World Model Benchmark for Vehicle Dynamics](https://mlsanity.com/paper/2609.33264/) (2026)
- [CRISP: Fixing Flying Pixels in Latent LiDAR Generation via Diffusion Decoding](https://mlsanity.com/paper/2610.11376/) (2026)
- [VITAL: From Visual Motion to Precise Action](https://mlsanity.com/paper/2610.20604/) (2026)

## Abstract (arXiv)

Generative world models are reshaping embodied AI, enabling agents to synthesize realistic 4D driving environments that look convincing but often fail physically or behaviorally. Despite rapid progress, the field still lacks a unified way to assess whether generated worlds preserve geometry, obey physics, or support reliable control. We introduce WorldLens, a full-spectrum benchmark evaluating how well a model builds, understands, and behaves within its generated world. It spans five aspects -- Generation, Reconstruction, Action-Following, Downstream Task, and Human Preference -- jointly covering visual realism, geometric consistency, physical plausibility, and functional reliability. Across these dimensions, no existing world model excels universally: those with strong textures often violate physics, while geometry-stable ones lack behavioral fidelity. To align objective metrics with human judgment, we further construct WorldLens-26K, a large-scale dataset of human-annotated videos with numerical scores and textual rationales, and develop WorldLens-Agent, an evaluation model distilled from these annotations to enable scalable, explainable scoring. Together, the benchmark, dataset, and agent form a unified ecosystem for measuring world fidelity -- standardizing how future models are judged not only by how real they look, but by how real they behave.