Large Vision-Language Model Evaluation on MMBench v1.0 (dev)
77.6ScoreCogVLM-Chat
Evaluation results
| Method | Links | |
|---|---|---|
| CogVLM-ChatLLM=Vicuna-7B2023.11 | 77.6 | |
| Qwen-VL-ChatLLM=Qwen-7B2023.11 | 67.7 | |
| LLaVA-1.5LLM=Vicuna-13B2023.11 | 67.7 | |
| SPHINX-2kLLM=LLaMA2 13B2023.11 | 65.9 | |
| mPLUG-Owl2LLM=LLaMA2-7B2023.11 | 64.5 | |
| LLaVA-1.5LLM=Vicuna-7B2023.11 | 64.3 | |
| Emu2-ChatLLM=LLaMA-33B2023.11 | 63.6 | |
| IDEFICS-InstructLLM=LLaMA-65B2023.11 | 54.5 | |
| InstructBLIPLLM=Vicuna-7B2023.11 | 33.9 | |
| MiniGPT-4LLM=Vicuna-7B2023.11 | 23 | |
| OpenFlamingoLLM=MPT-7B2023.11 | 5.7 |