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

Mathematical Reasoning on AIME 2024 (ACC, Tokens)

6.57ACC

IOA

-1,560.2628-1,153.4889-746.715-339.9411Aug 5, 2025Sep 5, 2025Oct 7, 2025Nov 8, 2025Dec 10, 2025Jan 11, 2026Feb 12, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.02
6.57-
2026.02
5.87-
2026.02
5.83-
2026.02
5.58-
2026.02
5.08-
2026.02
4.95-
2026.02
4.91-
2026.02
4.74-
2026.02
4.48-
2026.02
4.39-
2026.02
4.32-
2026.02
3.88-
2026.02
3.82-
2026.02
3.37-
2026.02
3.02-
2026.02
2.95-
2026.02
2.71-
2026.02
2.53-
2026.02
2.12-
2026.02
1.82-
2025.08
07.2
2025.08
-26016.5
2025.08
-620-12.9
2025.08
-620-57
2025.08
-1,230-27.5
2025.08
-1,500-34.6