AIME

text
+
+
+
+
About

AIME (American Invitational Mathematics Examination) is a rigorous AI mathematical reasoning benchmark based on the prestigious high school mathematics competition. Featuring 15 challenging problems requiring integer answers 0-999, it tests advanced mathematical reasoning across algebra, geometry, number theory, combinatorics, and probability. This benchmark evaluates AI models' ability to perform multi-step logical deduction and creative problem-solving.

+
+
+
+
Evaluation Stats
Total Models1
Organizations1
Verified Results0
Self-Reported1
+
+
+
+
Benchmark Details
Max Score1
Language
en
+
+
+
+
Performance Overview
Score distribution and top performers

Score Distribution

1 models
Top Score
57.5%
Average Score
57.5%
High Performers (80%+)
0

Top Organizations

#1Microsoft
1 model
57.5%
+
+
+
+
Leaderboard
1 models ranked by performance on AIME
LicenseLinks
Apr 30, 2025
MIT
57.5%
+
+
+
+
Resources