Medical Question Answering on MVME (test)
8.46ETSGPT4o
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| GPT4ocategory=Base Model2025.12 | 8.46 | 8.39 | 8.58 | 8.47 | |
| o3category=Base Model2025.12 | 8.41 | 8.23 | 8.6 | 8.45 | |
| MedTutor-R1category=Final Model2025.12 | 8.41 | 8.55 | 8.53 | 8.49 | |
| MedTutor-R1training_variation=w/o reward veto2025.12 | 8.4 | 8.53 | 7.15 | 8.03 | |
| MedTutor-R1training_variation=w/o CS reward2025.12 | 8.39 | 8.51 | 7.84 | 8.25 | |
| MedTutor-R1training_variation=w/o AQ reward2025.12 | 8.25 | 7.62 | 8.5 | 8.12 | |
| DeepSeek-R1category=Base Model2025.12 | 8.2 | 8.16 | 8.29 | 8.22 | |
| MedTutor-R1training_variation=w/ LLaVA-based2025.12 | 8.2 | 7.95 | 7.66 | 7.94 | |
| MedTutor-R1simulation_variation=w/o Specialist2025.12 | 8.13 | 8.39 | 7.55 | 8.03 | |
| MedTutor-R1training_variation=w/o IS reward2025.12 | 8.04 | 8.48 | 8.49 | 8.34 | |
| MedTutor-R1simulation_variation=w/o Supervisor2025.12 | 7.92 | 8.45 | 7.83 | 8.2 | |
| MedTutor-R1training_variation=w/ Vanilla reward2025.12 | 7.79 | 8.03 | 7.83 | 7.88 | |
| MedTutor-R1training_variation=w/o Thinking2025.12 | 7.66 | 7.87 | 7.84 | 7.79 | |
| MedTutor-R1simulation_variation=w/o Patient2025.12 | 7.66 | 7.81 | 7.62 | 7.7 | |
| MedTutor-R1simulation_variation=w One-Student2025.12 | 7.47 | 7.42 | 8.17 | 7.69 | |
| Med-SocraticLMcategory=Agent for Medical Education2025.12 | 7.42 | 7.18 | 7.25 | 7.28 | |
| MedTutor-R1training_variation=w/o RL2025.12 | 7.4 | 7.95 | 7.4 | 7.58 | |
| TutorRLcategory=Agent for Medical Education2025.12 | 7.25 | 7.01 | 7.13 | 7.13 | |
| EduChat-R1category=Agent for Medical Education2025.12 | 7.06 | 6.47 | 7.41 | 6.98 | |
| Qwen2.5VLcategory=Base Model2025.12 | 6.85 | 7.13 | 6.51 | 6.83 | |
| DRLTutorcategory=Agent for Medical Education2025.12 | 6.76 | 7.25 | 7.22 | 7.08 | |
| InternVL-3.5category=Base Model2025.12 | 6.53 | 6.41 | 6.35 | 6.43 | |
| LLaVA-V1.6category=Base Model2025.12 | 5.28 | 5.74 | 5.67 | 5.56 |