Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Reward Prediction on OSWorld Chrome
Loading...
93.5
Reward Accuracy
PRORE
82.164
85.107
88.05
90.993
Sep 26, 2025
Reward Accuracy
Updated 3d ago
Evaluation Results
Method
Method
Links
Reward Accuracy
PRORE
Evaluator Agent=Claude...
2025.09
93.5
WebRL
Evaluator Agent=Claude...
2025.09
87
StepCritic
Evaluator Agent=Claude...
2025.09
87
DigiRL
Evaluator Agent=Claude...
2025.09
84.8
DistRL
Evaluator Agent=Claude...
2025.09
82.6
Feedback
Search any
task
Search any
task