Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
GUI agent task on OSWORLD noisy (Trained (86))
Loading...
88.4
Pass@8 Success Rate
UI-TARS-1.5-7B + ENVS
61.776
68.688
75.6
82.512
Jun 22, 2026
Pass@8 Success Rate
Updated 1mo ago
Evaluation Results
Method
Method
Links
Pass@8 Success Rate
UI-TARS-1.5-7B + ENVS
Model=UI-TARS-1.5-7B +...
2026.06
88.4
UI-TARS-1.5-7B
Model=UI-TARS-1.5-7B,...
2026.06
66.3
UI-TARS-1.5-7B + ARPO
Model=UI-TARS-1.5-7B +...
2026.06
62.8
Feedback
Search any
task
Search any
task