List your company
ResearchFormerly WizWand

Visual Instruction Following on LLaVA-W

102ScoreGPT-4o
26.18445.86765.5585.233Jun 18, 2024Jul 5, 2024Jul 22, 2024Aug 9, 2024Aug 26, 2024Sep 12, 2024Sep 30, 2024
Updated 8mo ago

Evaluation results

MethodLinks
GPT-4oZero-shot=true, Decoding Strategy=greedy2024.09102
Gemini-1.5-ProZero-shot=true, Decoding Strategy=greedy2024.0995.3
GPT-4VZero-shot=true, Decoding Strategy=greedy2024.0993.1
TroLModel size=7B2024.0692.8
LLaVA-NeXT-34BModel Scale=30B, Zero-shot=true, Decoding Strategy=greedy2024.0989.6
MM1-30BModel Scale=30B, Zero-shot=true, Decoding Strategy=greedy2024.0989.3
LLaVA-NeXT-7BModel Scale=7B, Zero-shot=true, Decoding Strategy=greedy2024.0981.6
MM1-7BModel Scale=7B, Zero-shot=true, Decoding Strategy=greedy2024.0981.5
MM1.5-30BModel Scale=30B, Zero-shot=true, Decoding Strategy=greedy2024.0980.4
DeepSeek-VLModel size=7B2024.0678.9
TroLModel size=3.8B2024.0676.6
MM1.5-3B-MoEModel Scale=3B, Architecture=MoE, Zero-shot=true, Decoding Strategy=greedy2024.0976.1
TinyLLaVAModel Scale=3B, Zero-shot=true, Decoding Strategy=greedy2024.0975.8
MM1.5-1B-MoEModel Scale=1B, Architecture=MoE, Zero-shot=true, Decoding Strategy=greedy2024.0975.5
MM1.5-7BModel Scale=7B, Zero-shot=true, Decoding Strategy=greedy2024.0974.2
MM1.5-3BModel Scale=3B, Zero-shot=true, Decoding Strategy=greedy2024.0973
MM1-3BModel Scale=3B, Zero-shot=true, Decoding Strategy=greedy2024.0972.1
CoLLaVOModel size=7B2024.0671.9
MM1.5-1BModel Scale=1B, Zero-shot=true, Decoding Strategy=greedy2024.0971.6
Phi-3-Vision-4BModel Scale=3B, Zero-shot=true, Decoding Strategy=greedy2024.0971.6
MoAIModel size=7B2024.0669.7
LAFModel size=7B2024.0669.5
MiniCPM-V 2.0-3BModel Scale=3B, Zero-shot=true, Decoding Strategy=beam search2024.0969.2
MM1-1BModel Scale=1B, Zero-shot=true, Decoding Strategy=greedy2024.0967.5
TinyLLaVAModel Scale=1B, Zero-shot=true, Decoding Strategy=greedy2024.0960.8
InternVL2-2BModel Scale=1B, Zero-shot=true, Decoding Strategy=beam search2024.0960
SPHINX-TinyModel Scale=1B, Zero-shot=true, Decoding Strategy=greedy2024.0952.3
LLaVAOne Vision-0.5BModel Scale=1B, Zero-shot=true, Decoding Strategy=greedy2024.0929.1