Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Web Task Completion on Gomail
Loading...
96
Accuracy
JIT-Planner
61.68
70.59
79.5
88.41
May 20, 2026
Accuracy
Updated 13d ago
Evaluation Results
Method
Method
Links
Accuracy
JIT-Planner
2026.05
96
Anthropic CUA
2026.05
85
Browser-Use
cache=true
2026.05
80
OpenAI CUA
2026.05
78
Browser-Use
cache=false
2026.05
63
Feedback
Search any
task
Search any
task