Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Mathematical Reasoning on GSM8K (Score, #Strategy)

92.9Score

Prompting

40.58854.16967.7581.331Dec 9, 2025
Updated 3mo ago

Evaluation Results

MethodLinks
2025.12
92.94
2025.12
92.12
2025.12
922
2025.12
91.71
2025.12
90.90
2025.12
90.50
2025.12
90.54
2025.12
86.33
2025.12
84.41
2025.12
83.91
2025.12
81.84
2025.12
77.70
2025.12
77.70
2025.12
77.15
2025.12
46.93
2025.12
44.40
2025.12
43.70
2025.12
42.63