Close/open-ended VQA on MMMU HM
67.3AccuracyMed-Gemini-L 1.0
Evaluation results
| Method | Links | |
|---|---|---|
| Med-Gemini-L 1.0Multimodal fine-tuned=false2024.04 | 67.3 | |
| GPT-4VMultimodal fine-tuned=false2024.04 | 64.7 |
| Method | Links | |
|---|---|---|
| Med-Gemini-L 1.0Multimodal fine-tuned=false2024.04 | 67.3 | |
| GPT-4VMultimodal fine-tuned=false2024.04 | 64.7 |