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

Reward Modeling Evaluation on Reward-Bench

84.79Agreement

FairJudge-8B

38.499650.517362.53574.5527Feb 6, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2026.02
84.7958.1456.3456.94
2026.02
83.3457.2955.4856.33
2026.02
82.0855.9954.7155.34
2026.02
77.2553.1751.6752.11
2026.02
76.3854.9150.9652.8
2026.02
75.5550.4950.4150.41
2026.02
75.2358.2650.0353.7
2026.02
68.2446.6845.5446.05
2026.02
5354.5353.7751.3
2026.02
46.5741.4330.8935.27
2026.02
42.0739.5730.2925.73
2026.02
40.2836.1225.7128.36