Our new X account is live! Follow @wizwand_team for updates

Multimodal Understanding on SEED-Bench 1

73.5Image Accuracy

Bunny-8B

Updated 3d ago

Evaluation Results

Method	Links
Bunny-8B 2024.02		73.5	66.2
VILA1.5-13B 2024.02		72.6	65.1
Bunny-4B 2024.02		72.5	64.9
LLaVA-NeXT-13B 2024.02		71.9	-
GPT-4V-1106 2024.02		71.6	-
ShareGPT4V-13B 2024.02		70.8	-
DeepSeek-VL-7B 2024.02		70.4	-
LLaVA-NeXT-7B 2024.02		70.2	-
MM1-7B-Chat 2024.02		69.9	64
Mipha-3B 2024.02		68.9	-
SPHINX-Intern2 2024.02		68.8	-
MM1-3B-Chat 2024.02		68.8	63
VILA1.5-3B 2024.02		67.9	60.9
Yi-VL-6B 2024.02		67.6	-
MiniCPM-V 2.0 2024.02		67.1	-
SVIT-v1.5-13B 2024.02		-	61.9
LVIS-INSTRUCT4V-13B 2024.02		-	61.6
LLaVA-v1.5-13B (LORA) 2024.02		-	61.3
InstructBLIP-Vicuna-7B 2024.02		-	53.4
mPLUG-Owl2 2024.02		-	57.8
LLaVA-v1.5-7B (LORA) 2024.02		-	60.1