Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Reward Prediction on V-Droid trajectories
Loading...
93.1
Accuracy
PRORE
70.428
76.314
82.2
88.086
Sep 26, 2025
Accuracy
F1 Score
Updated 3d ago
Evaluation Results
Method
Method
Links
Accuracy
F1 Score
PRORE
Last N States=Proactive
2025.09
93.1
93.4
Step-Critic
Last N States=Full
2025.09
89.6
91
DistRL
Last N States=Full
2025.09
87
88.9
WebRL
Last N States=Full
2025.09
85.2
87
Step-Critic
Last N States=1
2025.09
85.2
87
DigiRL
Last N States=Full
2025.09
84.5
87.1
WebRL
Last N States=1
2025.09
82.6
85.1
DigiRL
Last N States=1
2025.09
76.5
80.3
DistRL
Last N States=1
2025.09
71.3
76.9
Feedback
Search any
task
Search any
task