AIME 2025
general
text
About
AIME 2025 benchmark
Evaluation Stats
Total Models36
Organizations10
Verified Results0
Self-Reported36
Benchmark Details
Max Score1
Language
en
Performance Overview
Score distribution and top performers
Score Distribution
36 models
Top Score
100.0%
Average Score
65.4%
High Performers (80%+)
14Top Organizations
#1xAI
4 models
94.0%
#2DeepSeek
1 model
87.5%
#3OpenAI
7 models
76.7%
#4Alibaba
3 models
75.1%
#5Microsoft
2 models
70.5%
Leaderboard
Top 20 models ranked by performance
1
100.0%
Raw: 1
Self-reported
6
91.1%
Raw: 0.911
Self-reported
7
90.8%
Raw: 0.908
Self-reported
88.0%
Raw: 0.88
Self-reported
87.5%
Raw: 0.875
Self-reported
11
85.2%
Raw: 0.852
Self-reported
12
83.0%
Raw: 0.83
Self-reported
81.5%
Raw: 0.815
Self-reported
80.2%
Raw: 0.802
Self-reported
78.0%
Raw: 0.78
Self-reported
75.5%
Raw: 0.755
Self-reported
72.5%
Raw: 0.725
Self-reported
72.0%
Raw: 0.72
Self-reported
20
70.9%
Raw: 0.709
Self-reported
Showing top 20 of 36 models