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

Personalized Reward Modeling on BESPOKE-Meta OOD

75.48Binary Preference Accuracy

P-CHECK

49.469656.222362.97569.7277Jan 6, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2026.01
75.48
2026.01
62.43
2026.01
61.35
2026.01
57.75
2026.01
55.46
2026.01
55.23
2026.01
54.67
2026.01
54.23
2026.01
53.54
2026.01
53.45
2026.01
52.89
2026.01
52.04
2026.01
51.49
2026.01
51.49
2026.01
51.35
2026.01
51.33
2026.01
50.83
2026.01
50.47