AIME 2025
text
+
+
+
+
About
The AIME 2025 benchmark tests AI models using 15 complex mathematical problems from the 2025 American Invitational Mathematics Examination. This rigorous evaluation measures advanced mathematical reasoning, problem-solving, and logical inference across algebra, geometry, and number theory. Each answer is an integer from 000-999, requiring precise step-by-step solutions. The benchmark represents one of the most challenging tests for AI mathematical capabilities.
+
+
+
+
Evaluation Stats
Total Models45
Organizations11
Verified Results0
Self-Reported45
+
+
+
+
Benchmark Details
Max Score1
Language
en
+
+
+
+
Performance Overview
Score distribution and top performers
Score Distribution
45 models
Top Score
100.0%
Average Score
67.6%
High Performers (80%+)
18Top Organizations
#1xAI
4 models
94.0%
#2Zhipu AI
1 model
93.9%
#3Alibaba Cloud / Qwen Team
7 models
77.9%
#4OpenAI
7 models
76.7%
#5DeepSeek
3 models
75.5%
+
+
+
+
Leaderboard
45 models ranked by performance on AIME 2025
| License | Links | ||||
|---|---|---|---|---|---|
| Jul 9, 2025 | Proprietary | 100.0% | |||
| Aug 7, 2025 | Proprietary | 94.6% | |||
| Sep 30, 2025 | MIT | 93.9% | |||
| Feb 17, 2025 | Proprietary | 93.3% | |||
| Apr 16, 2025 | Proprietary | 92.7% | |||
| Jul 25, 2025 | Apache 2.0 | 92.3% | |||
| Jul 9, 2025 | Proprietary | 91.7% | |||
| Aug 7, 2025 | Proprietary | 91.1% | |||
| Feb 17, 2025 | Proprietary | 90.8% | |||
| Sep 29, 2025 | MIT | 89.3% |
Showing 1 to 10 of 45 models
...