A Comprehensive Multi-turn Benchmark for Interactive Video World Model Evaluation
Fudan University
Meituan LongCat Team
*Equal contribution †Corresponding author: hhding@fudan.edu.cn
Interactive world models are advancing rapidly, yet no unified standard exists for systematic evaluation. WBench fills this gap with 289 multi-turn cases across 5 dimensions — evaluating 45 models with 22 metrics validated against human judgments. We find that no single model dominates all dimensions.
Click column headers to sort. Scores 0–100, higher is better. # = per-metric rank.
22 metrics across 5 dimensions. All scores normalized to 0–100, higher is better.
Same case, different models — see how metrics capture quality differences.
Astra
LingBot-World
MatrixGame 3.0
Kling 3.0
Happy Oyster
Genie 3
LongCat-Video
MatrixGame 3.0
YUME 1.5
Kling 3.0
LongCat-Video
Wan 2.7
LongCat-Video
Wan 2.7
HY-GameCraft
HY-World 1.5
Fantasy-World
Kairos 3.0
Genie 3
LTX 2.3
HY-Video 1.5289 cases, 4 interaction types, 6 scene categories, 5 subject types.
Browse all 289 cases. Hover images with mask badge to see subject segmentation overlay.
If you find our work useful, please consider citing:
@article{ying2026wbenchcomprehensivemultiturnbenchmark,
title={WBench: A Comprehensive Multi-turn Benchmark for Interactive Video World Model Evaluation},
author={Ying, Kaining and Hu, Hengrui and Ren, Siyu and Li, Jiamu and Chen, Fengjiao and Wang, Ziwen and Cao, Xuezhi and Cai, Xunliang and Ding, Henghui},
journal={arXiv preprint arXiv:2605.25874},
year={2026}
}