Medical Visual Question Answering on MIMIC-Ext-VQA (Overall)
77.95AccuracyPhi3.5V-Med
Evaluation results
| Method | Links | |
|---|---|---|
| Phi3.5V-MedEvaluation Protocol=Fine-Tuning, Decoding Strategy=ARCD2025.12 | 77.95 | |
| Phi3.5V-MedEvaluation Protocol=Fine-Tuning, Decoding Strategy=DoLA2025.12 | 72.05 | |
| Phi3.5V-MedEvaluation Protocol=Fine-Tuning, Decoding Strategy=OPERA2025.12 | 71.65 | |
| Phi3.5V-MedEvaluation Protocol=Fine-Tuning, Decoding Strategy=VCD2025.12 | 69.69 | |
| Phi3.5V-MedEvaluation Protocol=Fine-Tuning, Decoding Strategy=Greedy2025.12 | 69.29 | |
| GPT-4oEvaluation Protocol=General Domain, Decoding Strategy=Greedy2025.12 | 63.39 | |
| HuatuoV-34BEvaluation Protocol=Zero-Shot, Decoding Strategy=Greedy2025.12 | 53.54 | |
| Phi3.5V-MedEvaluation Protocol=Zero-Shot, Decoding Strategy=ARCD2025.12 | 50.79 | |
| Phi3.5V-MedEvaluation Protocol=Zero-Shot, Decoding Strategy=OPERA2025.12 | 50 | |
| Phi3.5V-MedEvaluation Protocol=Zero-Shot, Decoding Strategy=VCD2025.12 | 48.43 | |
| Phi3.5V-MedEvaluation Protocol=Zero-Shot, Decoding Strategy=Greedy2025.12 | 47.24 | |
| Phi3.5V-MedEvaluation Protocol=Zero-Shot, Decoding Strategy=DoLA2025.12 | 47.24 | |
| Qwen-VL-7BEvaluation Protocol=General Domain, Decoding Strategy=Greedy2025.12 | 46.46 | |
| Phi3.5V-4.2BEvaluation Protocol=General Domain, Decoding Strategy=Greedy2025.12 | 46.46 | |
| LLaVA-1.6-7BEvaluation Protocol=General Domain, Decoding Strategy=Greedy2025.12 | 46.06 | |
| LLaVA-Med-7BEvaluation Protocol=Zero-Shot, Decoding Strategy=Greedy2025.12 | 45.28 |