Unverified85% confidenceFactTime unknown
Office 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
1
Sources
85%
Confidence
Long-term
Relevance
5/31/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedDatabricks uses Office QA as an agent benchmark to measure model performance in enterprise document parsing scenarios.80% similarUnverifiedThe test required three AI Agents to respectively output three types of files: a Word research report, an Excel data spreadsheet, and a PowerPoint presentation.67% similarUnverifiedStandard AI benchmarks include MMLU (a comprehensive knowledge test covering 57 subjects), GPQA (graduate-level professional question answering), SWE-bench (real-world software engineering tasks), HumanEval and MBPP (programming ability), and MATH and GSM8K (mathematical reasoning)66% similarUnverifiedAI基准测试均有公开的学术论文和排行榜（如Papers With Code），任何声称超越某基准的数据都可公开查证66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/5896API
curl https://kongchang.com/api/v1/knowledge/claims/5896MCP
get_claim(id=5896)