List your company
ResearchFormerly WizWand

Multi-modal Understanding on Q-Bench (test)

62.9Overall ScoremPLUG-Owl2
46.57250.81155.0559.289Nov 7, 2023
Updated 8mo ago

Evaluation results

MethodLinks
mPLUG-Owl2Vision Encoder=ViT-L (0.3B), Language Model=LLAMA (7B), Zero-shot=true2023.1162.9
Qwen-VL-ChatVision Encoder=ViT-G (1.9B), Language Model=Qwen (7B), Zero-shot=true2023.1161.6
LLaVA-1.5Vision Encoder=ViT-L (0.3B), Language Model=Vicuna (7B), Zero-shot=true2023.1160.7
mPLUG-OwlVision Encoder=ViT-L (0.3B), Language Model=LLaMA (7B), Zero-shot=true2023.1158.9
LLaMA-Adapter-v2Vision Encoder=ViT-L (0.3B), Language Model=LLaMA (7B), Zero-shot=true2023.1158.1
InstructBLIPVision Encoder=ViT-g (1.3B), Language Model=Vicuna (7B), Zero-shot=true2023.1155.8
LLaVAVision Encoder=ViT-L (0.3B), Language Model=Vicuna (7B), Zero-shot=true2023.1154.7
OtterVision Encoder=ViT-L (0.3B), Language Model=LLaMA (7B), Zero-shot=true2023.1147.2