WBench-examples

<div align="center"> <h1>WBench-examples</h1> [](https://meituan-longcat.github.io/WBench/) [](https://arxiv.org/abs/2605.25874) [](https://github.com/meituan-longcat/WBench) [](https://huggingface.co/datasets/meituan-longcat/WBench) [](https://modelscope.cn/datasets/meituan-longcat/WBench-examples) </div> Reference video submissions for [**WBench**](https://github.com/meituan-longcat/WBench), a benchmark for interactive video world models. Each folder is a ready-to-evaluate submission package — drop it into `work_dirs/` and run the WBench pipeline. ## Contents | Folder | Model | Type | Split | Videos | |:---|:---|:---|:---|:---:| | `hyworld1.5/` | HY-World 1.5 (Tencent) | camera | navi | 158 | | `kling3/` | Kling 3.0 (Kling AI) | text | full | 289 | ``` <model>/ ├── meta.json # model metadata ├── turns.json # per-video turn boundaries └── videos/ └── case_<id>_combined.mp4 # combined multi-turn clip ``` ## Usage ```bash # evaluate a package with the WBench pipeline git clone https://github.com/meituan-longcat/WBench cp -r kling3 WBench/work_dirs/ cd WBench && python main.py --model kling3 ``` See the [submission format](https://github.com/meituan-longcat/WBench/blob/main/docs/SUBMISSION.md) for how to build your own package. ## Citation ```bibtex @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} } ```