Unverified50% confidenceFactExact time
DocVQA focuses on extracting information from scanned documents or table images, testing a model's OCR and structural comprehension capabilities.
1
Sources
50%
Confidence
Long-term
Relevance
9/29/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedOfficeQA Pro is a benchmark designed specifically to evaluate models' comprehensive capabilities in office document question-answering scenarios, covering tasks such as table comprehension, cross-page references, and mixed text-image parsing in Word, Excel, PowerPoint, and other formats.63% similarUnverifiedRD-Agent尝试读取研究材料、提出候选假设、生成代码、运行实验，并根据结果持续迭代修改63% similarUnverifiedPrompt adherence is one of the core metrics for measuring the quality of text-to-image models, referring to the degree to which the model's generated images accurately reflect all elements in the user's text description.61% similarUnverifiedGenerative retrieval allows models to directly generate document identifiers or answers, while agentic retrieval endows systems with the ability to autonomously plan, conduct multi-round retrieval, and evaluate result quality.60% similarUnverifiedOffice QA基准测试涵盖Word、Excel、PDF等格式中的信息抽取、表格推理和跨文档问答任务60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/958371API
curl https://kongchang.com/api/v1/knowledge/claims/958371MCP
get_claim(id=958371)