Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
GUI Automation on Average (AC-Real-TSR, MiniWob++, AndroidWorld)
Loading...
38.7
Success Rate (SR)
UI-Copilot-7B
6.044
14.522
23
31.478
Apr 15, 2026
Success Rate (SR)
Updated 3d ago
Evaluation Results
Method
Method
Links
Success Rate (SR)
UI-Copilot-7B
2026.04
38.7
UI-S1-7B
2026.04
37.1
UI-TARS-7B
2026.04
35.2
Qwen2.5VL-7B
2026.04
28.6
UI-R1-7B
2026.04
23.7
AgentCPM-GUI-8B
2026.04
21.6
OS-Atlas-7B
2026.04
18.6
UI-Copilot-3B
2026.04
16.2
OS-Genesis-7B
2026.04
13.4
UI-R1-3B
2026.04
12.8
ShowUI-2B
2026.04
11.7
Qwen2.5VL-3B
2026.04
10.2
Qwen2VL-2B
2026.04
7.3
Feedback
Search any
task
Search any
task