Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
GUI Agent on GUI-Odyssey
Loading...
90.74
Type Accuracy
Learn from GUI-Odyssey
73.1744
77.7347
82.295
86.8553
Jan 7, 2026
Type Accuracy
Success Rate (SR)
Task Success Rate (TSR)
Updated 4d ago
Evaluation Results
Method
Method
Links
Type Accuracy
Success Rate (SR)
Task Success Rate (TSR)
Learn from GUI-Odyssey
Base Model=OS-Atlas-Pr...
2026.01
90.74
76.06
462
CL from all three
Base Model=OS-Atlas-Pr...
2026.01
90.69
75.79
444
Agent-Dice
Base Model=OS-Atlas-Pr...
2026.01
89.27
72.28
210
Learn from AITZ
Base Model=OS-Atlas-Pr...
2026.01
83.33
60.19
54
Learn from AndroidControl
Base Model=OS-Atlas-Pr...
2026.01
74.68
40.8
24
Zero-Shot
Base Model=OS-Atlas-Pr...
2026.01
74.22
54.71
60
CL from AITZ and AndroidControl
Base Model=OS-Atlas-Pr...
2026.01
73.85
39.95
30
Feedback
Search any
task
Search any
task