Medical Visual Question Answering on (SLAKE, VQA-RAD, PathVQA, PMC-VQA) Aggregate (test)
81.2AccuracyMedCausalX
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| MedCausalXfine-tuned=true, evaluation=5-fold cross validation2026.03 | 81.2 | 78.7 | 36.4 | |
| MedVLM-R1fine-tuned=true, evaluation=5-fold cross validation2026.03 | 79.1 | 73.3 | 47.1 | |
| Med-R1fine-tuned=true, evaluation=5-fold cross validation2026.03 | 78.4 | 72.3 | 48.5 | |
| MedRegAfine-tuned=false, evaluation=5-fold cross validation2026.03 | 77.3 | 71.2 | 50.2 | |
| MedCoTfine-tuned=true, evaluation=5-fold cross validation2026.03 | 76.6 | 69.6 | 51.8 | |
| MedDrfine-tuned=false, evaluation=5-fold cross validation2026.03 | 72.7 | 68.5 | 52.5 | |
| InternVLfine-tuned=false, evaluation=5-fold cross validation2026.03 | 60 | 58.3 | 62.1 | |
| RadFMfine-tuned=false, evaluation=5-fold cross validation2026.03 | 57.2 | 60.3 | 59.1 | |
| Qwen2.5-VLfine-tuned=false, evaluation=5-fold cross validation2026.03 | 56.9 | 55.5 | 65 | |
| LLaVA-Medfine-tuned=false, evaluation=5-fold cross validation2026.03 | 48.8 | 48.9 | 68 | |
| Med-Flamingofine-tuned=false, evaluation=5-fold cross validation2026.03 | 40.4 | 41.9 | 72.3 |