List your company
ResearchFormerly WizWand

Multimodal Understanding on SEED Image

77.1AccuracyGPT-4o
70.02871.86473.775.536Apr 25, 2024May 20, 2024Jun 15, 2024Jul 11, 2024Aug 5, 2024Aug 31, 2024Sep 26, 2024
Updated 8mo ago

Evaluation results

MethodLinks
GPT-4o2024.0977.1
EMOVAModel Size=72B2024.0976.6
InternVL 1.5#param=26B, open-source=false2024.0476
LLaVA-NeXT#param=35B, open-source=false2024.0475.9
InternVL 1.2#param=40B, open-source=false2024.0475.6
EMOVAModel Size=7B2024.0975.5
EMOVAModel Size=3B2024.0974.9
VITAModel Size=1.52024.0974.2
Baichuan-OmniModel Size=7B2024.0974.1
Qwen-VL-Plusopen-source=false2024.0472.7
VITAModel Size=8x7B2024.0972.6
GPT-4Vopen-source=false2024.0471.6
Gemini Pro 1.52024.0971.6
Gemini Pro 1.0open-source=false2024.0470.7
Step-1V#param=100B, open-source=false2024.0470.3