Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
GUI Agent on AITZ, AndroidControl, and GUI-Odyssey
Loading...
-0.38
Avg Z-Score
Zero-Shot
-0.4244
-0.1247
0.175
0.4747
Jan 7, 2026
Avg Z-Score
Updated 4d ago
Evaluation Results
Method
Method
Links
Avg Z-Score
Zero-Shot
Base Model=OS-Atlas-Pr...
2026.01
-0.38
Learn from AndroidControl
Base Model=OS-Atlas-Pr...
2026.01
-0.26
Learn from GUI-Odyssey
Base Model=OS-Atlas-Pr...
2026.01
-0.17
CL from AITZ and AndroidControl
Base Model=OS-Atlas-Pr...
2026.01
-0.14
Learn from AITZ
Base Model=OS-Atlas-Pr...
2026.01
0.09
CL from all three
Base Model=OS-Atlas-Pr...
2026.01
0.14
Agent-Dice
Base Model=OS-Atlas-Pr...
2026.01
0.73
Feedback
Search any
task
Search any
task