Medical Question Answering on MedQA US (test)
90.02AccuracyMedChain-Agents
Evaluation results
| Method | Links | |
|---|---|---|
| MedChain-AgentsCategory=Multi-Agents2026.03 | 90.02 | |
| ClinicalAgentsCategory=Multi-Agents2026.03 | 89.95 | |
| DeepSeek-R1Category=Single LLM2026.03 | 89.87 | |
| RAGCategory=Single Agent2026.03 | 89.63 | |
| ReActCategory=Single Agent2026.03 | 89.47 | |
| MDAgentsCategory=Multi-Agents2026.03 | 89.32 | |
| ColaCareCategory=Multi-Agents2026.03 | 89.32 | |
| ReConcileCategory=Multi-Agents2026.03 | 89.24 | |
| Few-shot + CoTCategory=Single Agent2026.03 | 89.16 | |
| GPT-5.2Category=Single LLM2026.03 | 88.45 | |
| Llama-4-Maverick-17BCategory=Single LLM2026.03 | 87.98 | |
| MedAgentsCategory=Multi-Agents2026.03 | 87.9 | |
| AutoGenCategory=Multi-Agents2026.03 | 87.67 | |
| Intern-S1Category=Single LLM2026.03 | 82.56 | |
| Qwen3-VL-235BCategory=Single LLM2026.03 | 82.09 | |
| HuaTuoGPT-o1-7BCategory=Single LLM2026.03 | 71.01 | |
| FineMedLM-o1-8BCategory=Single LLM2026.03 | 67.87 | |
| MedGemma-4BCategory=Single LLM2026.03 | 66.77 |