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

Mathematical Reasoning on GSM8K (test) (Accuracy, Avg.)

85.81Accuracy

SoftCoT

81.639682.722383.80584.8877Feb 17, 2025
Updated 4d ago

Evaluation Results

MethodLinks
2025.02
85.8175.06
2025.02
84.8571.64
2025.02
84.1270.6
2025.02
83.770.29
2025.02
82.49-
2025.02
81.8-