Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Reward Prediction on 10-task benchmark Overall
Loading...
0.02
Demo L (MSE)
SARM2
0.01652
0.04001
0.0635
0.08699
Jun 9, 2026
Demo L (MSE)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Demo L (MSE)
SARM2
standard_full=true
2026.06
0.02
SARM2
Multi-Goal=excluded
2026.06
0.026
SARM2
Spectral Embedding=exc...
2026.06
0.034
RW
2026.06
0.036
Robometer
Fine-tuning=true
2026.06
0.043
Robometer
Fine-tuning=false
2026.06
0.093
TR
2026.06
0.107
Feedback
Search any
task
Search any
task
