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

Reward Modeling on UltraFeedback Cleaned

92.36Total Score

VRM

53.235263.392673.5583.7074Mar 5, 2026
Updated 2mo ago

Evaluation Results

MethodLinks
2026.03
92.36
2026.03
88.98
2026.03
82.28
2026.03
75.71
2026.03
70.67
2026.03
60.69
2026.03
59.16
2026.03
54.74