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

Mathematical Reasoning on AIME24 (ACC, mean@8)

35Accuracy

DiPO

5.963213.501621.0428.5784Apr 15, 2026
Updated 3d ago

Evaluation Results

MethodLinks
2026.04
3535
2026.04
33.7533.75
2026.04
31.6731.67
2026.04
31.6731.67
2026.04
30.0830.08
2026.04
29.1729.17
2026.04
26.6726.67
2026.04
26.6726.67
2026.04
26.6726.67
2026.04
26.2526.25
2026.04
22.9222.92
2026.04
20.4220.42
2026.04
20.4220.42
2026.04
2020
2026.04
2020
2026.04
9.589.58
2026.04
8.338.33
2026.04
7.087.08