Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Reward Modeling on MT Bench

76.8Accuracy

BT-BNRM

68.79270.87172.9575.029Feb 11, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2026.02
76.8
2026.02
75.2
2026.02
73.3
2026.02
69.1