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

Helpfulness preference labeling accuracy on Ultra-Creative

73.7Accuracy (Bench)

Few-Shot

70.16471.0827272.918Feb 14, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2026.02
73.758.615.1
2026.02
73.557.815.7
2026.02
73.554.718.8
2026.02
73.456.217.2
2026.02
73.459.613.8
2026.02
73.458.514.9
2026.02
73.460.512.9
2026.02
72.859.113.7
2026.02
72.759.313.4
2026.02
72.154.517.6
2026.02
7257.314.7
2026.02
71.55813.5
2026.02
71.558.213.3
2026.02
715813
2026.02
70.360.110.2