Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Web interaction on Mind2Web (overall)
Loading...
30.87
Action Accuracy
Evolving-RL
7.9068
13.8684
19.83
25.7916
May 11, 2026
Action Accuracy
Success Rate
Updated 21d ago
Evaluation Results
Method
Method
Links
Action Accuracy
Success Rate
Evolving-RL
Skill injection=true
2026.05
30.87
1.99
Evolving-RL
Skill injection=false
2026.05
28.05
1.57
GRPO
Skill injection=false
2026.05
22.83
1.42
GRPO
Skill injection=true
2026.05
22.73
1.43
Memento
2026.05
13.84
0.75
Base Model
Skill injection=true
2026.05
13.41
0.42
ReasoningBank
2026.05
12.79
0.52
Base Model
Skill injection=false
2026.05
8.79
0.34
Feedback
Search any
task
Search any
task