Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
GUI Agent Navigation on GUI-Act-Web (test)
Loading...
89.9
Type Accuracy
GUI-R1-3B
53.5
62.95
72.4
81.85
Mar 5, 2026
Type Accuracy
GR
SR
Updated 1mo ago
Evaluation Results
Method
Method
Links
Type Accuracy
GR
SR
GUI-R1-3B
Setting=RL Fine-Tuning
2026.03
89.9
87.4
76.3
WebFactory-3B
Setting=RL Fine-Tuning
2026.03
89
82.1
84.2
GPT-4o
Setting=Zero-Shot
2026.03
77.1
45
41.8
QwenVL2.5-3B
Setting=Zero-Shot
2026.03
54.9
63.5
55.6
Feedback
Search any
task
Search any
task