Atlas

Benchmarks

← All benchmarks

AIME 2024

Math · 2024-02-07

AIME 2024 evaluates mathematical reasoning on problems from the 2024 American Invitational Mathematics Examination. Scores are reported as answer accuracy.

Top models (higher is better)

ModelScore
Claude 3.5 Sonnet (Oct 2024)16.0
Haiku 3.55.3
Loading Atlas data…