# American Invitational Mathematics Examination 2024 (AIME 2024)

> The 2024 edition of AIME, maintaining the same format of 15 challenging mathematics problems with integer answers from 000 to 999.

Canonical page: https://benchlm.ai/benchmarks/aime2024

- Category: [Mathematics](/math)
- Last updated: October 17, 2026

## About AIME 2024

- Year: 2024
- Tasks: 15 problems
- Format: Integer answers 000-999
- Difficulty: High school olympiad level
- Paper: [American Invitational Mathematics Examination](https://www.maa.org/math-competitions/aime)

AIME 2024 continues the tradition of challenging mathematical reasoning problems. These problems test deep understanding of mathematical concepts and creative problem-solving abilities.

AIME 2024 is currently displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Leaderboard (26 models)

| Rank | Model | Creator | Score |
|------|-------|---------|-------|
| 1 | [GPT-OSS 120B](/models/gpt-oss-120b) | OpenAI | 95.8% |
| 2 | [DeepSeek V3.1 (Reasoning)](/models/deepseek-v3-1-reasoning) | DeepSeek | 93.1% |
| 3 | [GPT-OSS 20B](/models/gpt-oss-20b) | OpenAI | 92.1% |
| 4 | [Gemini 2.5 Pro](/models/gemini-2-5-pro) | Google | 92% |
| 5 | [DeepSeek-R1-0528](/models/deepseek-r1-0528) | DeepSeek | 91.4% |
| 6 | [Ministral 3 14B (Reasoning)](/models/ministral-3-14b-reasoning) | Mistral | 89.8% |
| 7 | [Grok 3 Mini](/models/grok-3-mini) | xAI | 89.5% |
| 8 | [o3-mini](/models/o3-mini) | OpenAI | 87.3% |
| 9 | [MiniMax M1 80k](/models/minimax-m1-80k) | MiniMax | 86% |
| 10 | [Qwen3 235B-A22B (Reasoning)](/models/qwen3-235b-a22b-reasoning) | Alibaba | 85.7% |
| 11 | [Qwen3 32B (Reasoning)](/models/qwen3-32b-reasoning) | Alibaba | 81.4% |
| 12 | [Phi-4-reasoning-plus](/models/phi-4-reasoning-plus) | Microsoft | 81.3% |
| 13 | [DeepSeek-R1](/models/deepseek-r1) | DeepSeek | 79.8% |
| 14 | [QwQ-32B](/models/qwq-32b) | Alibaba | 79.5% |
| 15 | [Phi-4-reasoning](/models/phi-4-reasoning) | Microsoft | 75.3% |
| 16 | [Magistral Medium](/models/magistral-medium) | Mistral | 73.6% |
| 17 | [Magistral Small](/models/magistral-small) | Mistral | 70.7% |
| 18 | [Kimi K2](/models/kimi-k2) | Moonshot AI | 69.6% |
| 19 | [DeepSeek V3.1](/models/deepseek-v3-1) | DeepSeek | 66.3% |
| 20 | [Claude 3.7 Sonnet Thinking](/models/claude-3-7-sonnet-thinking) | Anthropic | 61.3% |
| 21 | [Grok 3 [Beta]](/models/grok-3-beta) | xAI | 52.2% |
| 22 | [Qwen3 235B-A22B](/models/qwen3-235b-a22b) | Alibaba | 40.1% |
| 23 | [DeepSeek V3](/models/deepseek-v3) | DeepSeek | 39.2% |
| 24 | [Qwen3 32B](/models/qwen3-32b) | Alibaba | 31% |
| 25 | [Claude 3.7 Sonnet](/models/claude-3-7-sonnet) | Anthropic | 23.3% |
| 26 | [Claude 3.5 Haiku](/models/claude-3-5-haiku) | Anthropic | 5.3% |

## FAQ

### What does AIME 2024 measure?

The 2024 edition of AIME, maintaining the same format of 15 challenging mathematics problems with integer answers from 000 to 999.

### Which model scores highest on AIME 2024?

GPT-OSS 120B by OpenAI currently leads with a score of 95.8% on AIME 2024.

### How many models are evaluated on AIME 2024?

26 AI models have published results on AIME 2024 in the BenchLM catalog.

### Does AIME 2024 affect BenchLM's overall score?

Not directly. AIME 2024 is still displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Compare Top Models on AIME 2024

- [GPT-OSS 120B vs DeepSeek V3.1 (Reasoning)](/compare/deepseek-v3-1-reasoning-vs-gpt-oss-120b)
- [DeepSeek V3.1 (Reasoning) vs GPT-OSS 20B](/compare/deepseek-v3-1-reasoning-vs-gpt-oss-20b)
- [GPT-OSS 20B vs Gemini 2.5 Pro](/compare/gemini-2-5-pro-vs-gpt-oss-20b)
- [Gemini 2.5 Pro vs DeepSeek-R1-0528](/compare/deepseek-r1-0528-vs-gemini-2-5-pro)

## Related Reading

- [AIME 2024 benchmark explainer](/blog/posts/aime-hmmt-competition-math)