Model Library / Benchmarks / AIME 2025

Math

AIME 2025

American Invitational Mathematics Examination — competition-level multi-step quantitative reasoning.

Features measured

Reasoning

Use cases unlocked

Math & quantitative reasoning STEM tutoring

Leaderboard

Higher is better · accuracy %

Bars scaled from 60 so close scores stay legible — the figure at right is the actual accuracy %.

Benchmark source ↗

← All benchmarks