Medical Reasoning on HiMed-West Exam English
78.1AccuracyGPT-4o
Evaluation Results
| Method | Links | |
|---|---|---|
| GPT-4oZero-shot=true2026.05 | 78.1 | |
| Qwen2.5-14B-InstructZero-shot=true2026.05 | 71.4 | |
| HiMed-8BBackbone=LLaMA-3.1-8B, Zero-shot=true2026.05 | 58.7 |
Loading the SOTA2 catalog…