Large Vision-Language Model Evaluation on LLAVA (bench)
77.8ScoreCogVLM-Chat
Evaluation Results
| Method | Links | |
|---|---|---|
| CogVLM-ChatLLM=Vicuna-7B2023.11 | 77.8 | |
| LLaVA-1.5LLM=Vicuna-13B2023.11 | 64.6 | |
| LLaVA-1.5LLM=Vicuna-7B2023.11 | 60.7 | |
| InstructBLIPLLM=Vicuna-7B2023.11 | 59.8 | |
| IDEFICS-InstructLLM=LLaMA-65B2023.11 | 56.9 | |
| Emu2-ChatLLM=LLaMA-33B2023.11 | 56.4 | |
| MiniGPT-4LLM=Vicuna-7B2023.11 | 45.1 | |
| OpenFlamingoLLM=MPT-7B2023.11 | 34.2 | |
| FuyuLLM=Fuyu-8B2023.11 | 27.4 | |
| mPLUG-Owl2LLM=LLaMA2-7B2023.11 | 25 |