Clinical Licensing Examination Question Answering on Clinical Examination (CE)
81.1Accuracy (CE - Physiology)Qwen3-32B+SFT
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| Qwen3-32B+SFT2026.05 | 81.1 | 66.08 | 77.42 | |
| SafeMed-R1Optimization=CoT reasoning, safety-ethics alignment, improved GRPO2026.05 | 80.97 | 67.58 | 79.25 | |
| qwen3-30B-A3B-Instruct-25072026.05 | 80.1 | 66.04 | 78.5 | |
| Qwen3-32B2026.05 | 79.83 | 66.71 | 77.67 | |
| Baichuan-M2-32B2026.05 | 79.33 | 68.58 | 74.92 | |
| gemini-2.5-flash2026.05 | 76.97 | 64.67 | 68.5 | |
| gpt-5-mini2026.05 | 75.2 | 61.25 | 65.92 | |
| Qwen2.5-32B-Instruct2026.05 | 72.97 | 58.46 | 69.92 | |
| DeepSeek-R1-Distill-Qwen-32B2026.05 | 72.93 | 59.79 | 71.25 | |
| HuatuoGPT-o1-70B2026.05 | 66.17 | 49.17 | 54.33 | |
| google_medgemma-27b-text-it2026.05 | 65.73 | 52.08 | 54.08 | |
| Lingshu-32B2026.05 | 45.21 | 53.83 | 58.75 |