Medical Reasoning on MedBullets 4-option multiple choice
62.3AccuracyMedVerse
Evaluation Results
| Method | Links | |
|---|---|---|
| MedVerseBackbone=LLaMA-3.1-8B-Instruct2026.02 | 62.3 | |
| MedReasonBackbone=LLaMA-3.1-8B-Instruct2026.02 | 57.1 | |
| Huatuo-o1Backbone=LLaMA-3.1-8B-Instruct2026.02 | 55.8 | |
| MedVerseBackbone=Qwen2.5-7B-Instruct2026.02 | 55.2 | |
| MedReasonBackbone=Qwen2.5-7B-Instruct2026.02 | 49.7 | |
| Original (LLaMA-3.1-8B-Instruct)Backbone=LLaMA-3.1-8B-Instruct2026.02 | 48.7 | |
| Original (Qwen2.5-7B-Instruct)Backbone=Qwen2.5-7B-Instruct2026.02 | 45.8 |