AIME 2024 (avg@8)
Math · 2024-02-07
AIME 2024 accuracy averaged across eight sampled solutions per problem, separated from single-attempt results.
Top models (higher is better)
| Model | Score |
|---|---|
| Opus 4.5 | 99.6 |
| Gemini 3.1 Pro Preview | 99.2 |
| Gemini 3 Pro Preview | 99.2 |
| Grok 4.20 | 98.8 |
| Opus 4.6 | 97.5 |
| Kimi K2.5 | 97.5 |
| GPT-5.2 | 97.1 |
| GPT-5.4 | 97.1 |
| Opus 4.7 | 96.7 |
| Muse Spark | 96.7 |
| Gemini 3 Flash Preview | 95.8 |
| GPT-5.4 Mini | 95.8 |
| Qwen3.6 Plus (2026-04-02) | 95.4 |
| GLM-4.7 | 95.0 |
| GLM 4.6 | 94.6 |
| GPT-5 | 94.2 |
| Grok 4 Fast | 94.2 |
| GPT-5.1 | 93.8 |
| Sonnet 4.6 | 93.3 |
| GLM-5 | 93.3 |
| Grok 4 | 93.3 |
| Grok 4.1 Fast | 93.3 |
| Qwen3.5-Flash | 93.3 |
| gpt-oss-120b | 93.1 |
| GPT-5 Mini | 92.9 |
| GLM-5.1 | 92.1 |
| MiniMax M2.7 | 91.7 |
| Sonnet 4.5 | 90.7 |
| MiniMax M2.5 | 89.2 |
| o3-mini | 89.2 |
| Grok 3 Mini | 88.8 |
| Gemini 3.1 Flash-Lite Preview | 88.3 |
| Qwen3.5 Plus (2026-02-15) | 88.3 |
| DeepSeek-V3.2 | 87.5 |
| Gemini 2.5 Pro Experimental 03-25 | 87.5 |
| o3 | 87.2 |
| GLM-4.5 | 87.1 |
| Magistral Medium 1.2 | 87.1 |
| gpt-oss-20b | 86.7 |
| Kimi K2 Thinking | 85.8 |