General Knowledge on MMLU (EM)
91.8EMOpenAI-o1-1217
Evaluation results
| Method | Links | |
|---|---|---|
| OpenAI-o1-12172025.01 | 91.8 | |
| DeepSeek-R1Architecture=MoE, Activated Params=37B, Total Params=671B2025.01 | 90.8 | |
| DeepSeek-V3Architecture=MoE, Activated Params=37B, Total Params=671B2025.01 | 88.5 | |
| Claude-3.5-Sonnet-10222025.01 | 88.3 | |
| GPT-4o-05132025.01 | 87.2 | |
| OpenAI-o1-mini2025.01 | 85.2 |