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

Mathematics on AIME 2024 (Accuracy and AMSR)

80Accuracy

ReasonCache

7.226.14563.9Jul 29, 2025
Updated 19d ago

Evaluation Results

MethodLinks
2025.07
8016.4
2025.07
800
2025.07
76.60
2025.07
73.30
2025.07
73.323.41
2025.07
7021.18
2025.07
66.625.1
2025.07
6020.98
2025.07
56.722.34
2025.07
56.720.3
2025.07
56.716.6
2025.07
56.718.5
2025.07
501.79
2025.07
202.56
2025.07
101