MM-Instruct: Generated Visual Instructions for Large Multimodal Model Alignment
Open paper
Benchmark
Model
Rank
Results
visual-question-answering-on-mm-vet
LLaVA-Instruct (Vicuna-1.5-13B)
#94
GPT-4 score: 37.1
visual-question-answering-on-mm-vet
LLaVA-Instruct (Vicuna-1.5-7B)
#123
GPT-4 score: 32.9
Rank counts only results with a code link.