ScreenSpot-Pro: GUI Grounding for Professional High-Resolution Computer Use

📢 Updates

(Feb 21 2025) We’re excited to see our work acknowledged and used as a benchmark in several great projects: Omniparser v2, Qwen2.5-VL, UI-TARS, UGround, AGUVIS, ...

Set Up

Before you begin, ensure your environment variables are set:

• OPENAI_API_KEY: Your OpenAI API key.

Evaluation

Use the shell scripts to launch the evaluation.

bash run_ss_pro.sh

or

bash run_ss_pro_cn.sh

Citation

Please consider citing if you find our work useful:

@misc{li2024screenspot-pro,
      title={ScreenSpot-Pro: GUI Grounding for Professional High-Resolution Computer Use}, 
      author={Kaixin Li and Ziyang Meng and Hongzhan Lin and Ziyang Luo and Yuchen Tian and Jing Ma and Zhiyong Huang and Tat-Seng Chua},
      year={2025},
}