📊 Showing 3 results | 📏 Metric: Overall Accuracy
| Rank | Model | Paper | Overall Accuracy | Date | Code |
|---|---|---|---|---|---|
| 1 | GPT-4V | AutoHallusion: Automatic Generation of Hallucination Benchmarks for Vision-Language Models | 66.00 | 2024-06-16 | 📦 tianyi-lab/hallusionbench 📦 wuxiyang1996/AutoHallusion 📦 zli12321/videohallu |
| 2 | miniGPT4 | MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models | 51.00 | 2023-04-20 | 📦 vision-cair/minigpt-4 📦 zyang1580/binllm 📦 2024-MindSpore-1/Code6 |
| 3 | LLaVA-1.5 | Improved Baselines with Visual Instruction Tuning | 44.50 | 2023-10-05 | 📦 huggingface/transformers 📦 haotian-liu/LLaVA 📦 LLaVA-VL/LLaVA-NeXT |