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

Mathematical Reasoning on AMC OpenR1-Math Harder

88.2Accuracy

Qwen-4B

81.33683.11884.986.682Feb 11, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2026.02
88.2
2026.02
87.8
2026.02
81.6