# WBench: A Comprehensive Multi-turn Benchmark for Interactive Video World Model Evaluation

arXiv: https://arxiv.org/abs/2605.25874 · HTML: https://mlsanity.com/paper/2605.25874/

## Key facts

- Cited by 39 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 50 of its 84 references that are in the map.
- First posted on arXiv 25 May 2026.

## Placed in

- World models / [Video-generation world models and simulators](https://mlsanity.com/wm/video-generation-world-models-and-simulators/)

## Builds on (most cited first, 30 of 50)

- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [HunyuanVideo: A Systematic Framework For Large Video Generative Models](https://mlsanity.com/paper/2412.03603/) (2024)
- [World Models](https://mlsanity.com/paper/1803.10122/) (2018)
- [Towards Accurate Generative Models of Video: A New Metric & Challenges](https://mlsanity.com/paper/1812.01717/) (2018)
- [WorldSimBench: Towards Video Generation Models as World Simulators](https://mlsanity.com/paper/2410.18072/) (2024)
- [Depth Anything 3: Recovering the Visual Space from Any Views](https://mlsanity.com/paper/2511.10647/) (2025)
- [Movie Gen: A Cast of Media Foundation Models](https://mlsanity.com/paper/2410.13720/) (2024)
- [GAIA-1: A Generative World Model for Autonomous Driving](https://mlsanity.com/paper/2309.17080/) (2023)
- [LTX-Video: Realtime Video Latent Diffusion](https://mlsanity.com/paper/2501.00103/) (2024)
- [Learning Interactive Real-World Simulators](https://mlsanity.com/paper/2310.06114/) (2023)
- [DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data](https://mlsanity.com/paper/2306.09344/) (2023)
- [VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness](https://mlsanity.com/paper/2503.21755/) (2025)
- [VideoPhy: Evaluating Physical Commonsense for Video Generation](https://mlsanity.com/paper/2406.03520/) (2024)
- [HPSv3: Towards Wide-Spectrum Human Preference Score](https://mlsanity.com/paper/2508.03789/) (2025)
- [Matrix-game 2.0: An open-source real-time and streaming interactive world model](https://mlsanity.com/paper/2508.13009/) (2025)
- [Towards World Simulator: Crafting Physical Commonsense-Based Benchmark for Video Generation](https://mlsanity.com/paper/2410.05363/) (2024)
- [Seedance 2.0: Advancing Video Generation for World Complexity](https://mlsanity.com/paper/2604.14148/) (2026)
- [Advancing Open-source World Models](https://mlsanity.com/paper/2601.20540/) (2026)
- [VideoPhy-2: A Challenging Action-Centric Physical Commonsense Evaluation in Video Generation](https://mlsanity.com/paper/2503.06800/) (2025)
- [WorldModelBench: Judging Video Generation Models As World Models](https://mlsanity.com/paper/2502.20694/) (2025)
- [IRASim: A Fine-Grained World Model for Robot Manipulation](https://mlsanity.com/paper/2406.14540/) (2024)
- [Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memory](https://mlsanity.com/paper/2604.08995/) (2026)
- [Hunyuan-GameCraft: High-dynamic Interactive Game Video Generation with Hybrid History Condition](https://mlsanity.com/paper/2506.17201/) (2025)
- [LongCat-Video Technical Report](https://mlsanity.com/paper/2510.22200/) (2025)
- [Yume-1.5: A Text-Controlled Interactive World Generation Model](https://mlsanity.com/paper/2512.22096/) (2025)
- [Yume: An Interactive World Generation Model](https://mlsanity.com/paper/2507.17744/) (2025)

## Built on by (most cited first, 30 of 39)

- [DreamX-World 1.0: A General-Purpose Interactive World Model](https://mlsanity.com/paper/2606.16993/) (2026)
- [Alaya-EVOKE: From Linear-Scaling Supervision to Endless World](https://mlsanity.com/paper/2608.13546/) (2026)
- [EchoWM: Open and Enterable Omnimodal World Models](https://mlsanity.com/paper/2608.23189/) (2026)
- [Current World Models Lack a Persistent State Core](https://mlsanity.com/paper/2606.20545/) (2026)
- [WorldRoamBench: An Open-World Benchmark for Long-Horizon Stability of Interactive World Models](https://mlsanity.com/paper/2606.31672/) (2026)
- [WorldOlympiad: Can Your World Model Survive a Triathlon?](https://mlsanity.com/paper/2606.11129/) (2026)
- [AlayaWorld: Interactive Long-Horizon World Modeling - Full Technical Report (v1.1)](https://mlsanity.com/paper/2608.13492/) (2026)
- [A Definition and Roadmap for World Models](https://mlsanity.com/paper/2607.06401/) (2026)
- [PlayWorld: Benchmarking World Models with Agent Players over Long-Horizon Objectives](https://mlsanity.com/paper/2608.13552/) (2026)
- [WorldExam: Benchmarking World Models from Apparent Appearance to Inherent Reactivity](https://mlsanity.com/paper/2608.02603/) (2026)
- [HarnessEval-W: Agentifying the Evaluation of Visual Worlds](https://mlsanity.com/paper/2608.16859/) (2026)
- [Long-Horizon Audio-Visual Generation for Persistent Stories and Interactive Worlds](https://mlsanity.com/paper/2608.23383/) (2026)
- [Zing-0.5: Toward Playable Worlds with Real-Time Joint Action and Text Control](https://mlsanity.com/paper/2609.17909/) (2026)
- [WorldCycle: Self-Verifiable Reinforcement Learning for Long-Horizon Video World Models](https://mlsanity.com/paper/2608.04964/) (2026)
- [CaliBench: Are the Stochastic Dynamics of Video World Models Physically Calibrated?](https://mlsanity.com/paper/2608.16829/) (2026)
- [Astronex-World 1.0: Real-Time Interactive World Model Foundation](https://mlsanity.com/paper/2609.20034/) (2026)
- [HelloWorld: Enabling Socially Interactive Characters in Video World Models](https://mlsanity.com/paper/2608.05070/) (2026)
- [RoboPhys-3D: A Comprehensive Embodied World Model Evaluation via 3D Reconstruction](https://mlsanity.com/paper/2608.28718/) (2026)
- [Search-to-World: Evaluation of 3D World Delivery from User Request through Web Search](https://mlsanity.com/paper/2609.07605/) (2026)
- [LynnReal-Omni: Native multi-modal Video Generation for Agentic Visual Workflows](https://mlsanity.com/paper/2609.15863/) (2026)
- [Precise Editing and Flexible Referencing for Interactable Worlds](https://mlsanity.com/paper/2609.34470/) (2026)
- [Einstein World Models](https://mlsanity.com/paper/2606.26969/) (2026)
- [From Generation to Simulation: How Far Are World Models from Being True Simulators?](https://mlsanity.com/paper/2608.23070/) (2026)
- [Beyond Visual Quality: Evaluating Physical Consistency under Ego-Motion with EgoGenEval](https://mlsanity.com/paper/2609.11172/) (2026)
- [HappyWorld-Bench](https://mlsanity.com/paper/2609.24308/) (2026)
- [VehDyn: A Driving World Model Benchmark for Vehicle Dynamics](https://mlsanity.com/paper/2609.33264/) (2026)
- [OPIS: An Input-Grounded Benchmark for Multi-Object Memory in Video World Models](https://mlsanity.com/paper/2609.35052/) (2026)
- [WorldPlay2: Extending Real-Time Interactive World Models in Control and Horizon](https://mlsanity.com/paper/2609.35560/) (2026)
- [HelixWorld: A Real-time Interactive Audio-Visual World Model](https://mlsanity.com/paper/2609.38123/) (2026)
- [LOCI: Spatial Linear Memory for Streaming World Models](https://mlsanity.com/paper/2609.40222/) (2026)

## Abstract (arXiv)

Interactive world models are advancing rapidly, yet existing benchmarks cover only part of the required competencies, leaving no unified standard for systematic evaluation. To fill this gap, we introduce WBench, a comprehensive multi-turn benchmark for interactive world model evaluation along five dimensions, namely video quality, setting adherence, interaction adherence, consistency, and physics compliance. WBench contains 289 test cases and 1,058 interaction turns, where each case specifies a world setting and a multi-turn interaction sequence, covering diverse scenes, styles, subjects, and both first- and third-person perspectives, together with four interaction types, including navigation, subject action, event editing, and perspective switching. For navigation, WBench unifies text, 6-DoF pose, and discrete-action control, enabling evaluation of models with different native input interfaces. Evaluation uses 22 automatic sub-metrics that combine specialist vision models with large multimodal models, and all metrics are validated against human judgments. Across 20 state-of-the-art models, we find that no single model performs strongly across all dimensions. We provide detailed diagnostic insights into the characteristic strengths, weaknesses, and open challenges of each model. Code and data are available at https://github.com/meituan-longcat/WBench.