AIME 2024

Math% accuracy

American Invitational Mathematics Examination, 2024 problems.

At a glance

🏆 Top score
o3OpenAI96.7 % accuracy
Total results
7
Models tested
7
Providers
4
Verified · Self-reported
1 · 6
Average
73.57 % accuracy
Median
79.8 % accuracy
Range
48 – 96.7 % accuracy
Latest result
Jun 1, 2025

Score distribution

1
0
1
1
0
0
1
2
0
1
48.072.396.7
7 results across 10 score bands

Methodology

15 integer-answer problems per exam. Score is percentage of correct answers over the set.

Limitations

Very small problem count per year; high variance. Reasoning-tuned models often dominate.

By provider

  • OpenAI· 4 models
    96.7 % accuracy
    o3
    Average: 75.82 % accuracyBest: 96.7 % accuracy
  • xAI· 1 model
    83.9 % accuracy
    Grok 3
    Average: 83.9 % accuracyBest: 83.9 % accuracy
  • DeepSeek· 1 model
    79.8 % accuracy
    DeepSeek R1
    Average: 79.8 % accuracyBest: 79.8 % accuracy
  • Anthropic· 1 model
    48 % accuracy
    Claude Opus 4
    Average: 48 % accuracyBest: 48 % accuracy

Full leaderboard

Showing 7 of 7
#ModelProviderScore (% accuracy)
1o3OpenAI
96.7
2Grok 3xAI
83.9
3o1OpenAI
83.3
4DeepSeek R1DeepSeek
79.8
5o3-miniOpenAI
63.3
6GPT-5OpenAI
60
7Claude Opus 4Anthropic
48

Comments

Sign in to leave a comment.