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

Mathematical Problem Solving on AIME 24 (mean@32 accuracy)

60.4Mean@32 Accuracy

Teacher Model

-0.85615.04730.9546.853Jun 21, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
60.4
2026.06
58.7
2026.06
58.7
2026.06
56.5
2026.06
56.3
2026.06
35.2
2026.06
35.2
2026.06
34
2026.06
33.4
2026.06
23.1
2026.06
13.6
2026.06
13.4
2026.06
12.4
2026.06
11.8
2026.06
11.1
2026.06
1.5