Visual Question Answering Vqa On 5
評価指標
Overall Accuracy
評価結果
このベンチマークにおける各モデルのパフォーマンス結果
モデル名 | Overall Accuracy | Paper Title | Repository |
|---|---|---|---|
| GPT-4V | 66.0 | AutoHallusion: Automatic Generation of Hallucination Benchmarks for Vision-Language Models | |
| LLaVA-1.5 | 44.5 | Improved Baselines with Visual Instruction Tuning | |
| Claude 3 | 37.1 | - | - |
| Gemini Pro Vision | 51.4 | - | - |
| miniGPT4 | 51.0 | MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models |
0 of 5 row(s) selected.