Visual Question Answering Vqa On 5
Metrics
Overall Accuracy
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | Overall Accuracy |
|---|---|
| autohallusion-automatic-generation-of | 66.0 |
| improved-baselines-with-visual-instruction | 44.5 |
| Model 3 | 37.1 |
| Model 4 | 51.4 |
| minigpt-4-enhancing-vision-language | 51.0 |