AIME 2025
Math · 2025-02-12
AIME 2025 combines problems from the 2025 American Invitational Mathematics Examination contests. Scores are reported as answer accuracy.
Top models (higher is better)
| Model | Score |
|---|---|
| GPT-5.2 | 100.0 |
| Opus 4.6 | 99.8 |
| Gemini 2.5 Deep Think | 99.2 |
| GPT-5-Codex | 98.7 |
| Step 3.5 Flash | 98.3 |
| Gemini 3 Flash Preview | 97.5 |
| GLM-5 | 96.7 |
| MiMo-V2-Flash | 96.3 |
| Kimi K2.5 | 95.8 |
| Gemini 3 Pro Preview | 95.7 |
| GPT-5.1-Codex | 95.7 |
| Sonnet 4.6 | 95.6 |
| GLM-4.7 | 95.0 |
| KAT-Coder-Pro V1 | 94.7 |
| Nova 2 Lite | 94.3 |
| Opus 4.5 | 92.8 |
| O4 Mini | 92.7 |
| Grok 4 | 91.7 |
| GPT-5.1-Codex mini | 91.7 |
| GPT-5 | 91.7 |
| Nemotron 3 Nano 30B A3B | 91.0 |
| Qwen3 235B A22B Thinking 2507 | 91.0 |
| K-EXAONE 236B-A23B | 90.3 |
| DeepSeek-V3.1-Terminus | 89.7 |
| Nova 2 Omni (Preview) | 89.7 |
| Ring-1T | 89.3 |
| DeepSeek-R1-0528 | 89.2 |
| o3 | 89.2 |
| Nova 2 Pro (Preview) | 89.0 |
| Qwen3 VL 235B A22B Thinking | 88.3 |
| Apriel-1.6-15B-Thinker | 88.0 |
| INTELLECT-3 | 88.0 |
| Gemini 2.5 Pro | 88.0 |
| Apriel-1.5-15B-Thinker | 87.5 |
| Gemini 2.5 Pro Experimental 03-25 | 86.7 |
| o3-mini | 86.7 |
| GLM-4.6V | 85.3 |
| ERNIE 5.0 | 85.0 |
| GPT-5 Mini | 85.0 |
| Qwen3 VL 32B Thinking | 84.7 |