MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Action
Open paper
Benchmark
Model
Rank
Results
visual-question-answering-on-mm-vet
MM-ReAct-GPT-4
#84
GPT-4 score: 44.6±0.2
visual-question-answering-on-mm-vet
MM-ReAct-GPT-3.5
#186
GPT-4 score: 27.9±0.1
Rank counts only results with a code link.