List your company
ResearchFormerly WizWand

Multi-modal Benchmark on MMBench (dev)

73.5AccuracyBunny-4B
57.27661.48865.769.912May 20, 2024
Updated 8mo ago

Evaluation results

MethodLinks
Bunny-4BLLM=Phi-3-3.8B, Visual Encoder=SigLIP-SO@384, #PT=2M, #FT=695K2024.0573.5
Imp-4BLLM=Phi-3-3.8B, Visual Encoder=SigLIP-SO@384, #PT=558K, #FT=1M2024.0573.3
Imp-3BLLM=Phi-2-2.7B, Visual Encoder=SigLIP-SO@384, #PT=558K, #FT=1M2024.0572.9
Bunny-3BLLM=Phi-2-2.7B, Visual Encoder=SigLIP-SO@384, #PT=2M, #FT=695K2024.0568.6
LLaVA-1.5-13BLLM=Vicuna-1.5-13B, Visual Encoder=CLIP-L@336, #PT=558K, #FT=665K2024.0568.5
Yi-VL-6BLLM=Yi-6B, Visual Encoder=CLIP-H@224, #PT=100M, #FT=26M2024.0568.4
MiniCPM-V-3BLLM=MiniCPM-SFT-2B, Visual Encoder=SigLIP-SO@384, #PT=300M, #FT=8M2024.0567.9
LLaVA-1.5-7BLLM=Vicuna-1.5-7B, Visual Encoder=CLIP-L@336, #PT=558K, #FT=665K2024.0566.1
mPLUG-Owl2-8BLLM=LLAMA2-7B, Visual Encoder=CLIP-L@448, #PT=400M, #FT=1.2M2024.0564.5
Imp-2BLLM=Qwen-1.5-1.8B, Visual Encoder=SigLIP-SO@384, #PT=558K, #FT=1M2024.0563.8
LLaVA-Phi-3BLLM=Phi-2-2.7B, Visual Encoder=CLIP-L@336, #PT=558K, #FT=665K2024.0559.8
Mini-Gemini-2BLLM=Gemma-2B, Visual Encoder=CLIP-L@336, #PT=1.2M, #FT=1.5M2024.0559.8
MobileVLM-3BLLM=MobileLLaMA-2.7B, Visual Encoder=CLIP-L@336, #PT=558K, #FT=665K2024.0559.6
Bunny-2BLLM=Qwen1.5-1.8B, Visual Encoder=SigLIP-SO@384, #PT=2M, #FT=695K2024.0559.1
SPHINX-X-8BLLM=InternLM2-7B, Visual Encoder=CLIP&Dino@224, #PT=0, #FT=15M2024.0557.9