List your company
ResearchFormerly WizWand

Multimodal Benchmarking on MM-Bench 37

71.5AccuracyMipha-3B+ (Ours)
34.5844.16553.7563.335Jul 5, 2024
Updated 8mo ago

Evaluation results

MethodLinks
Mipha-3B+ (Ours)LM=Phi-2 (2.7B), Res.=384, PT=558K, IT=665K2024.0771.5
Mipha-3BLM=Phi-2 (2.7B), Res.=384, PT=558K, IT=665K2024.0769.7
Bunny-3BLM=Phi-2 (2.7B), Res.=384, PT=2M, IT=695K2024.0768.6
LLaVA-1.5+ (Ours)LM=Vicuna(7B), Res.=336, PT=558K, IT=665K2024.0767.6
LAF-7BLM=Vicuna (7B), Res.=336, PT=558K, IT=665K2024.0767.3
TinyLLaVALM=Phi-2 (2.7B), Res.=384, PT=1.2M, IT=665k2024.0766.9
Imp-v1LM=Phi-2 (2.7B), Res.=384, PT=558K, IT=665K2024.0766.5
mPLUG-Owl2LM=LLAMA (7B), Res.=448, PT=400M, IT=1.23M2024.0764.5
LLaVA-1.5LM=Vicuna (7B), Res.=336, PT=558K, IT=665K2024.0764.3
Mobile VLM-v2-3BLM=M-LLaMA (2.7B), Res.=336, PT=1.2M, IT=2.4M2024.0763.2
Qwen-VL-ChatLM=Qwen (7B), Res.=448, PT=1.4B, IT=50M2024.0760.6
LLaVA-PhiLM=Phi-2 (2.7B), Res.=336, PT=558k, IT=665K2024.0759.8
Mobile VLM-3BLM=M-LLaMA (2.7B), Res.=336, PT=558K, IT=665K2024.0759.6
ShikraLM=Vicuna (13B), Res.=224, PT=600K, IT=5.5M2024.0758.8
Mobile VLM-v2-1.7BLM=M-LLaMA (1.4B), Res.=336, PT=1.2M, IT=2.4M2024.0757.7
IDEFICS-80BLM=LLaMA (65B), Res.=224, PT=353M, IT=1M2024.0754.5
Mobile VLM-1.7BLM=M-LLaMA (1.4B), Res.=336, PT=558K, IT=665K2024.0753.2
IDEFICS-9BLM=LLaMA (7B), Res.=224, PT=353M, IT=1M2024.0748.2
InstructBLIPLM=Vicuna (7B), Res.=224, PT=129M, IT=1.2M2024.0736