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

Mathematical Reasoning on AIME 25

94.5Accuracy

APRM

51.3462.54573.7584.955Nov 28, 2025Nov 30, 2025Dec 3, 2025Dec 6, 2025Dec 9, 2025Dec 12, 2025Dec 15, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.11
94.5
2025.11
93.6
2025.11
92.8
2025.11
91.9
2025.11
91.6
2025.11
91.5
2025.11
91.3
2025.11
91
2025.11
90.6
2025.11
90.4
2025.11
90.4
2025.11
89.2
2025.11
89.1
2025.11
88
2025.11
87.9
86.46
2025.11
85.5
82.81
2025.11
71.4
2025.11
69.9
2025.11
69.9
2025.11
65.7
2025.11
62.6
2025.11
61.4
2025.11
55.4
2025.11
53