| Paper | Code | Overall Accuracy | ModelName | ReleaseDate |
|---|---|---|---|---|
| AutoHallusion: Automatic Generation of Hallucination Benchmarks for Vision-Language Models | ✓ Link | 66.0 | GPT-4V | 2024-06-16 |
| []() | 51.4 | Gemini Pro Vision | ||
| MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models | ✓ Link | 51.0 | miniGPT4 | 2023-04-20 |
| Improved Baselines with Visual Instruction Tuning | ✓ Link | 44.5 | LLaVA-1.5 | 2023-10-05 |
| []() | 37.1 | Claude 3 |