Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
GUI Agent Automation on AndroidWorld (AW) (Online)
Loading...
25.1
Success Rate
VeriGUI-7B
5.34
10.47
15.6
20.73
Apr 7, 2026
Success Rate
Updated 11d ago
Evaluation Results
Method
Method
Links
Success Rate
VeriGUI-7B
Category=Ours
2026.04
25.1
UI-S1-7B
Category=Open-source 7B
2026.04
22.7
Qwen2.5-VL-7B
Category=Open-source 7B
2026.04
14.9
VeriGUI-3B
Category=Ours
2026.04
12.6
UI-R1-3B
Category=Open-source 3B
2026.04
10.9
Qwen2.5-VL-3B
Category=Open-source 3B
2026.04
6.1
Feedback
Search any
task
Search any
task