Medical Test Recommendation on MedAction 300-Hard
54PrecisionOpenAI-o3-mini
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| OpenAI-o3-miniModel Source=Closed-Source2026.05 | 54 | 47 | 50 | |
| MedGemmaModel Source=Open-Source, Model Parameters=27B2026.05 | 52 | 52 | 52 | |
| Qwen-QwQModel Source=Open-Source, Model Parameters=32B2026.05 | 51 | 41 | 45 | |
| II-Medical-8B SFTModel Source=Open-Source, Model Parameters=8B, Training Stage=SFT2026.05 | 51 | 51 | 51 | |
| Baichuan-M3Model Source=Open-Source, Model Parameters=235B2026.05 | 50 | 54 | 52 | |
| Gemini 2.5 Flash-LiteModel Source=Closed-Source2026.05 | 47 | 48 | 47 | |
| Baichuan-M1Model Source=Open-Source, Model Parameters=14B2026.05 | 47 | 41 | 44 | |
| II-Medical-8BModel Source=Open-Source, Model Parameters=8B, Training Stage=Base2026.05 | 45 | 45 | 45 | |
| GPT-5.4Model Source=Closed-Source2026.05 | 42 | 60 | 49 |