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

Personalized Reward Modeling on Chatbot Arena Personalized

75.92Accuracy

P-GenRM

50.928857.416963.90570.3931Jan 6, 2026Jan 12, 2026Jan 18, 2026Jan 24, 2026Jan 30, 2026Feb 5, 2026Feb 12, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2026.02
75.92
2026.02
74.3
2026.02
73.42
2026.02
72.68
2026.02
72.05
2026.02
71.12
2026.02
69.78
2026.02
67.21
2026.02
65.55
2026.02
63.14
2026.02
62.2
2026.01
61.56
2026.02
61.07
2026.02
59.4
2026.02
59.02
2026.01
58.83
2026.02
58.65
2026.02
58.53
2026.02
58.5
2026.01
58.15
2026.02
58.12
2026.02
57.87
2026.02
57.61
2026.02
57.31
2026.02
57.05
2026.02
57.02
2026.01
56.42
2026.02
56.37
2026.01
55.84
2026.01
55.03
2026.01
53.89
2026.01
53.77
2026.01
53.56
2026.01
53.36
2026.01
53.32
2026.01
52.76
2026.01
52.41
2026.01
52.34
2026.01
52.29
2026.01
52.23
2026.01
52.01
2026.01
51.89