OfficeQA benchmark
Agent Q&A over office documents.
Browse OfficeQA agent evaluation tasks — document Q&A over treasury and office PDFs, with dual-harness runs and public traces.
133Tasks
1Published models
95Primary passes
Published model set
This public benchmark currently includes gpt-5.4. Model counts reflect completed, shareable runs in this catalog.
Related categories
OfficeQA tasks also appear inDocument Q&AandFinancial Statement Analysis.
All tasks
Dual-harness runs on U.S. Treasury bulletin Q&A tasks.