GDP.pdf: Benchmarking Grounded Multimodal Reasoning over Professional PDF Documents
GDP.pdf:针对专业PDF文档的基础多模态推理基准测试
机构 * Surge AI
AI总结 该研究针对专业PDF文档构建多模态推理基准测试GDP.pdf,由专业人员编写问题-文档对,通过严格筛选保留问题,有详细评分标准和能力分类。评估七个前沿模型,发现多数错误源于特定模式,公开了完整基准测试。
Comments 9 pages. v2: results updated to July 2026 leaderboard (17 models). Accepted at the 2nd Workshop on Knowledge-Intensive Multimodal Reasoning (KnowledgeMR) at CVPR 2026 (non-archival), under the former title "PDFParse: A Benchmark for Grounded Multimodal Reasoning over Professional PDF Documents". Dataset: https://huggingface.co/datasets/surgeai/GDP.pdf ; Code: https://github.com/surge-ai/gdp-pdf