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

Reasoning on Average (MATH500, AMC23, AIME24, AIME25, GPQA-d)

87.2Accuracy

DDC

66.08871.56977.0582.531May 14, 2026
Updated 19d ago

Evaluation Results

MethodLinks
2026.05
87.24.9
2026.05
87.116.4
2026.05
86.75.7
2026.05
86.119
2026.05
85.248.5
2026.05
85.217.1
2026.05
85.228.5
2026.05
8523.2
2026.05
84.741.1
2026.05
84.413.7
2026.05
83.44.9
2026.05
81.45.1
2026.05
81.315.8
2026.05
81.324
2026.05
80.838.4
2026.05
80.519.1
2026.05
79.113.1
2026.05
75.828.3
2026.05
74.845
2026.05
74.814.9
2026.05
70.18
2026.05
69.436.3
2026.05
6950.4
2026.05
6769.3
2026.05
66.928.4