---
title: README
emoji: 🌍
colorFrom: blue
colorTo: gray
sdk: static
pinned: false
---
[**🤗 Demo**](https://huggingface.co/spaces/WildVision/vision-arena) | [**🤗 Paper**](https://huggingface.co/papers/2406.11069) | [**📖 arXiv**](https://arxiv.org/abs/2406.11069) | [**GitHub**](https://github.com/orgs/WildVision-AI/repositories)


We are a team from AI2, UCSB, and UWaterloo, UCSC, UWM and we are working on benchmarking vision language models. 

Compare VLMs at [WildVision-Arena](https://huggingface.co/spaces/WildVision/vision-arena) and [WildVision-Bench](https://huggingface.co/datasets/WildVision/wildvision-arena-data).

**More chat and vote data will be updated reguarly. Eval script is released here [WildVision-Bench](https://github.com/WildVision-AI/WildVision-Bench)**

Contact: Bill Yuchen Lin (yuchenl@allenai.org) and Yujie Lu (yujielu@ucsb.edu) 


Citation: If you found this huggingface space useful, please consider cite us:

```
@misc{lu2024wildvision,
      title={WildVision: Evaluating Vision-Language Models in the Wild with Human Preferences}, 
      author={Yujie Lu and Dongfu Jiang and Wenhu Chen and William Yang Wang and Yejin Choi and Bill Yuchen Lin},
      year={2024},
      eprint={2406.11069},
      archivePrefix={arXiv},
      primaryClass={id='cs.CV' full_name='Computer Vision and Pattern Recognition' is_active=True alt_name=None in_archive='cs' is_general=False description='Covers image processing, computer vision, pattern recognition, and scene understanding. Roughly includes material in ACM Subject Classes I.2.10, I.4, and I.5.'}
}
```