ViperGPT: Visual Inference via Python Execution for Reasoning
Open paper
Benchmark
Model
Rank
Results
zero-shot-video-question-answer-on-next-qa
ViperGPT (GPT-3.5)
#21
Accuracy: 60.0
video-question-answering-on-next-qa
ViperGPT(0-shot)
#32
Accuracy: 60.0
Rank counts only results with a code link.