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

Utility assessment on MMLU-Pro

16.5Personalization Bias (PB)

Identity-Robust Generation

-0.772115.814232.4348.986Jan 14, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2026.01
16.5
2026.01
19.6
2026.01
25.2
2026.01
35
2026.01
36.6
2026.01
49
2026.01
52.3
2026.01
60.8
2026.01
448.3