Medical Question Answering on AfriMed
92AccuracyDeepSeek R1
Evaluation results
| Method | Links | |
|---|---|---|
| DeepSeek R1Size category=Large Models2025.07 | 92 | |
| MedGemma 27BSize category=Small Models, test-time scaling=true2025.07 | 84 | |
| Gemini 2.5 FlashSize category=Large Models2025.07 | 84 | |
| Gemini 2.5 ProSize category=Large Models2025.07 | 84 | |
| o3Size category=Large Models2025.07 | 84 | |
| GPT-4oSize category=Large Models2025.07 | 80 | |
| Gemma 3 27BSize category=Small Models2025.07 | 72 | |
| MedGemma 4BSize category=Small Models2025.07 | 52 | |
| Gemma 3 4BSize category=Small Models2025.07 | 48 |