Conversational Visual QA on MM-Vet (test)
52.8MM-Vet ScoreCogAgent
Evaluation results
| Method | Links | |
|---|---|---|
| CogAgentLLM=Vicuna-7B2023.12 | 52.8 | |
| LLaVA-1.5LLM=Vicuna-13B2023.12 | 36.3 | |
| EmuLLM=LLaMA-13B2023.12 | 36.3 | |
| DreamLLMLLM=Vicuna-7B2023.12 | 35.9 | |
| LLaMA-Adapter v2LLM=LLaMA-7B2023.12 | 31.4 | |
| LLaVALLM=LLaMA2-7B2023.12 | 28.1 | |
| InstructBLIPLLM=Vicuna-13B2023.12 | 25.6 | |
| OtterLLM=MPT-7B2023.12 | 24.7 | |
| MiniGPT4LLM=Vicuna-13B2023.12 | 24.4 | |
| BLIP-2LLM=Vicuna-13B2023.12 | 22.4 |