MMBench-GUI: Hierarchical Multi-Platform Evaluation Framework for GUI Agents
Abstract
We introduce MMBench-GUI, a hierarchical benchmark for evaluating GUI automation agents across Windows, macOS, Linux, iOS, Android, and Web platforms. It comprises four levels: GUI Content Understanding, Element Grounding, Task Automation, and Task Collaboration, covering essential skills for GUI agents. In addition, we propose a novel Efficiency-Quality Area (EQA) metric to assess GUI agent execution efficiency in online automation scenarios. Through MMBench-GUI, we identify accurate visual grounding as a critical determinant of overall task success, emphasizing the substantial benefits of modular frameworks that integrate specialized grounding modules. Furthermore, to achieve reliable GUI automation, an agent requires strong task planning and cross-platform generalization abilities, with long-context memory, a broad action space, and long-term reasoning playing a critical role. More important, task efficiency remains a critically underexplored dimension, and all models suffer from substantial inefficiencies, with excessive redundant steps even when tasks are ultimately completed. The integration of precise localization, effective planning, and early stopping strategies is indispensable to enable truly efficient and scalable GUI automation. Our benchmark code, evaluation data, and running environment will be publicly available at https://github.com/open-compass/MMBench-GUI.
Cite
@article{arxiv.2507.19478,
title = {MMBench-GUI: Hierarchical Multi-Platform Evaluation Framework for GUI Agents},
author = {Xuehui Wang and Zhenyu Wu and JingJing Xie and Zichen Ding and Bowen Yang and Zehao Li and Zhaoyang Liu and Qingyun Li and Xuan Dong and Zhe Chen and Weiyun Wang and Xiangyu Zhao and Jixuan Chen and Haodong Duan and Tianbao Xie and Chenyu Yang and Shiqian Su and Yue Yu and Yuan Huang and Yiqian Liu and Xiao Zhang and Yanting Zhang and Xiangyu Yue and Weijie Su and Xizhou Zhu and Wei Shen and Jifeng Dai and Wenhai Wang},
journal= {arXiv preprint arXiv:2507.19478},
year = {2025}
}
Comments
in progress