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

Math Reasoning on AIME25 (Accuracy)

94.6AIME25 Accuracy

GPT-5

-0.35224.29948.9573.601Jan 7, 2026Jan 24, 2026Feb 11, 2026Mar 1, 2026Mar 18, 2026Apr 5, 2026Apr 23, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.01
94.6
2026.01
86.7
2026.04
66.7
2026.04
63.3
2026.04
60
2026.04
56.7
2026.04
50
2026.04
50
2026.04
50
2026.04
43.3
2026.01
40
2026.04
40
2026.01
33.3
2026.01
33.3
2026.04
33.3
2026.01
23.3
2026.04
23.3
2026.04
23.3
2026.01
13.3
2026.01
13.3
2026.01
10
2026.01
6.7
2026.01
6.7
2026.01
6.7
2026.01
3.3
2026.01
3.3
2026.01
3.3
2026.01
3.3