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

Math Problem Solving on GSM8K (Accuracy)

91.5Accuracy

TaH+

43.76456.15768.5580.943Nov 11, 2025
Updated 23d ago

Evaluation Results

MethodLinks
2025.11
91.5-
2025.11
90.9-
2025.11
90.5-
2025.11
90.4-
2025.11
85.8-
2025.11
85.3-
2025.11
84.5-
2025.11
82.1-
2025.11
79.6-
2025.11
79.3-
2025.11
71.2-
2025.11
68.8-
2025.11
64.4-
2025.11
62.5-
2025.11
61.3-
2025.11
54.6-
2025.11
45.6-
2026.05
-86.3
2026.05
-53.1
2026.05
-9
2026.05
-61
2026.05
-69
2026.05
-86.8
2026.05
-94.3
2026.05
-77.9
2026.05
-85.7
2026.05
-81.6
2026.05
-90.7
2026.05
-75.1
2026.05
-94.4
2026.05
-51.5
2026.05
-92.5
2026.05
-73.3