Beyond AIME

math

Beyond AIME is a difficult mathematical reasoning benchmark designed to test deeper reasoning chains and harder decomposition than standard AIME-style problem sets.

Leaderboard

Showing 3 of 3 results

Sarvam-105B

69.1%

i
Mistral Medium 3.5

66.9%

i
Sarvam-30B

58.3%

i