Multimodal Understanding and Reasoning on MM-Vet
44.6MM-Vet ScoreGPT-4V
Evaluation results
| Method | Links | |
|---|---|---|
| GPT-4V2024.06 | 44.6 | |
| LLaVA-1.5-LLaMA3-8BBase Model=LLaMA3, Model size=8B2024.06 | 37.8 | |
| LLaVA-1.5-13BModel size=13B2024.06 | 36.3 | |
| LLaVA-1.5-7BModel size=7B2024.06 | 33.9 |