WBench: A Comprehensive Multi-turn Benchmark for Interactive Video World Model Evaluation
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 naviga...
| Authors | Kaining Ying, Hengrui Hu, Siyu Ren et al. |
|---|---|
| Primary category | cs.CV |
| Published | 25 May 2026 |
| Last updated at source | 25 May 2026 |
Connected in the knowledge graph
- meituan-longcat/WBench-examplesDataset · cited by
- meituan-longcat/WBenchDataset · cited by
Models and datasets referencing this paper
- meituan-longcat/WBenchDataset
- meituan-longcat/WBench-examplesDataset
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.