DocVQA: A Dataset for VQA on Document Images

Open paper
Benchmark Model Rank Results
visual-question-answering-on-docvqa-testHuman#18ANLS: 0.9436
visual-question-answering-on-docvqa-testBERT_LARGE_SQUAD_DOCVQA_FINETUNED_Baseline#84ANLS: 0.665Accuracy: 55.77

Rank counts only results with a code link.