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

Mathematical Reasoning on ASDiv Aug (test)

88.9Accuracy

SoftCoT

36.79650.32363.8577.377Feb 17, 2025Apr 17, 2025Jun 16, 2025Aug 15, 2025Oct 13, 2025Dec 12, 2025Feb 10, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2025.02
88.975.06
2025.02
88.6371.64
2025.02
87.1970.29
2025.02
86.9470.6
2025.02
86.9-
2025.02
86.8-
2026.02
77-
2026.02
74.9-
2026.02
72.2-
2026.02
70.7-
2026.02
70.3-
2026.02
69.8-
2026.02
69.6-
2026.02
67.2-
2026.02
61.9-
2026.02
55.5-
2026.02
54.1-
2026.02
53.9-
2026.02
52.5-
2026.02
46.2-
2026.02
44.8-
2026.02
42.5-
2026.02
40-
2026.02
39.3-
2026.02
38.8-