VideoGUI Benchmark

What is VideoGUI?

VideoGUI is designed to evaluate GUI assistants on visual-centric GUI tasks. Sourced from high-quality web instructional videos, it focuses on tasks involving…

Released

2024-06-14

Evaluates

创作, Creation, NeurIPS 2024, 智能体, Agent, 任务执行, Task Execution, 视频理解, Video Understanding, 不支持, Unsupported

Openness

unknown

Importer

OpenCompass Hub

Reported scores

0

Source provenance

• Original evidence https://hub.opencompass.org.cn/dataset-detail/VideoGUI

VideoGUI paper and code

• Paper https://arxiv.org/abs/2406.10227
• Code https://github.com/showlab/videogui

Which sources cite VideoGUI?

• VideoGUI

Related 创作, Creation, NeurIPS 2024, 智能体, Agent, 任务执行, Task Execution, 视频理解, Video Understanding, 不支持, Unsupported benchmarks

• A-Bench
• A-OKVQA
• AbsPyramid
• ActionAtlas
• Ada-LEval
• AECBench
• AFQMC
• AgentBoard