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

Human Preference Alignment on In-Domain (test)

22.46Pick Score

TAFS-GRPO

21.648821.859422.0722.2806Feb 2, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2026.02
22.4627.68
2026.02
22.2627.72
2026.02
22.2327.67
2026.02
22.227.42
2026.02
22.1327.23
2026.02
21.9726.98
2026.02
21.6825.95