Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Reward Prediction on M3A trajectories
Loading...
91.4
Accuracy
PRORE
69.56
75.23
80.9
86.57
Sep 26, 2025
Accuracy
F1 Score
Updated 3d ago
Evaluation Results
Method
Method
Links
Accuracy
F1 Score
PRORE
Last N States=Proactive
2025.09
91.4
88.9
DigiRL
Last N States=Full
2025.09
82.6
80.8
Step-Critic
Last N States=Full
2025.09
82.6
79.6
DistRL
Last N States=Full
2025.09
81.7
79.6
WebRL
Last N States=1
2025.09
81.7
79.2
WebRL
Last N States=Full
2025.09
81.7
79.2
Step-Critic
Last N States=1
2025.09
81.7
79.4
DigiRL
Last N States=1
2025.09
74.8
73.4
DistRL
Last N States=1
2025.09
70.4
68.5
Feedback
Search any
task
Search any
task