Share your thoughts, 1 month free Claude Pro on usSee more

Multi-discipline Multimodal Understanding on MMMU F

45.9Accuracy

GPT-4o

Updated 1mo ago

Evaluation Results

Method	Links
GPT-4o 2024.06		45.9
GPT-4v 2024.06		42
Prism Captioner-7B 2024.06		35.6
InternVL-Chat-v1.5 2024.06		33.7
Prism Captioner-2B 2024.06		32.4
Prism Captioner-2B 2024.06		32
ShareCaptioner 2024.06		30.2
Prism Captioner-7B 2024.06		29.8
Emu2-Chat 2024.06		27.8
LLaVA-NeXT (Yi-34B) 2024.06		26.7
LLaVA-InternLM2-7B 2024.06		21.9
InternLM-XComposer2 2024.06		21.2
Yi-VL-34B 2024.06		21.2
MiniCPM-V-2 2024.06		21.2
DeepSeek-VL-7B 2024.06		19.6
mPLUG-Owl2 2024.06		19.6
LLaVA-NeXT (Mistral-7B) 2024.06		19.2
LLaVA-InternLM2-1.8B 2024.06		18.4
LLaVA-NeXT (Vicuna-7B) 2024.06		18
LLaVA-InternLM2-20B 2024.06		18
LLaVA-NeXT (Vicuna-13B) 2024.06		16.5
LLaVA-v1.5-7B 2024.06		15.7
LLaVA-v1.5-13B 2024.06		15.3