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

Reward Modeling on Overall Performance (test)

80.2Overall

CE-RM-4B

55.55261.95168.3574.749Jan 28, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2026.01
80.2
2026.01
79.2
2026.01
77.4
2026.01
73.8
2026.01
73.7
2026.01
71.7
2026.01
71.2
2026.01
69.7
2026.01
56.5