Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Reward Model Evaluation on RewardBench

0.001P-value

DPO

-0.00020.00790.0160.0241May 10, 2026
Updated 21d ago

Evaluation Results

MethodLinks
2026.05
0.0010.0010.78-
2026.05
0.0010.0010.82-
2026.05
0.0010.0010.85-
2026.05
0.0030.0090.72-
2026.05
0.0180.0360.67-
2026.05
0.0240.0410.64-
2026.05
0.0310.0480.62-