Beyond Embeddings: The Promise of Visual Table in Visual Reasoning
Open paper
Benchmark
Model
Rank
Results
visual-question-answering-on-mm-vet
LLaVA-VT (Vicuna-13B)
#102
GPT-4 score: 39.8
visual-question-answering-on-mm-vet
LLaVA-VT (Vicuna-7B)
#166
GPT-4 score: 31.8
Rank counts only results with a code link.