Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Reward Prediction on S2 10-task benchmark unconventional
Loading...
0.031
Demo L MSE
SARM2
0.02744
0.05147
0.0755
0.09953
Jun 9, 2026
Demo L MSE
Updated 1mo ago
Evaluation Results
Method
Method
Links
Demo L MSE
SARM2
standard_full=true
2026.06
0.031
SARM2
Multi-Goal=excluded
2026.06
0.038
SARM2
Spectral Embedding=exc...
2026.06
0.04
RW
2026.06
0.044
Robometer
Fine-tuning=true
2026.06
0.052
Robometer
Fine-tuning=false
2026.06
0.113
TR
2026.06
0.12
Feedback
Search any
task
Search any
task
