Model,Language Model,Open Source,Text Recognition,Text Referring,Text Spotting,Relation Extraction,Element Parsing,Mathematical Calculation,Visual Text Understanding,Knowledge Reasoning,Average Score,Link
Gemini-Pro,,No,61.2,39.5,13.5,79.3,39.2,47.7,75.5,59.3,51.9,https://arxiv.org/abs/2312.11805
Qwen2-VL-8B,,Yes,72.1,47.9,17.5,82.5,25.5,25.4,78.4,61.5,51.4,https://arxiv.org/abs/2409.12191