Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
GUI Task Execution on AITZ
Loading...
66.64
Success Rate
Atlas-Pro-7B
40.068
46.9665
53.865
60.7635
Jan 27, 2026
Success Rate
Grounding Rate
Updated 4d ago
Evaluation Results
Method
Method
Links
Success Rate
Grounding Rate
Atlas-Pro-7B
Method Category=Specia...
2026.01
66.64
62.18
UI-Venus-Navi-7B
Method Category=Specia...
2026.01
60.27
70.23
MAGNET
Method Category=Agenti...
2026.01
52.77
57.35
InfiGUI-R1-3B
Method Category=Specia...
2026.01
49.49
55.34
GUI-R1-7B
Method Category=Specia...
2026.01
44.22
57.21
MAGNET
Method Category=Agenti...
2026.01
43.5
43.78
Agent-S
Method Category=Agenti...
2026.01
42.98
42.87
COAT
Method Category=Agenti...
2026.01
41.09
39.28
Feedback
Search any
task
Search any
task