Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Math Reasoning on AIME25 (Accuracy)

94.6AIME25 Accuracy

GPT-5

-0.35224.29948.9573.601Jan 7, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2026.01
94.6
2026.01
86.7
2026.01
40
2026.01
33.3
2026.01
33.3
2026.01
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