[2512.13168] Finch: Benchmarking Finance & Accounting across Spreadsheet-Centric Enterprise Workflows

Computer Science > Artificial Intelligence arXiv:2512.13168 (cs) [Submitted on 15 Dec 2025 (v1), last revised 5 Apr 2026 (this version, v4)] Title:Finch: Benchmarking Finance & Accounting across Spreadsheet-Centric Enterprise Workflows Authors:Haoyu Dong, Pengkun Zhang, Yan Gao, Xuanyu Dong, Yilin Cheng, Mingzhe Lu, Zikun Zhu, Adina Yakefu, Shuxin Zheng View a PDF of the paper titled Finch: Benchmarking Finance & Accounting across Spreadsheet-Centric Enterprise Workflows, by Haoyu Dong and 8 other authors View PDF HTML (experimental) Abstract:We introduce FinWorkBench (a.k.a. Finch), a benchmark for evaluating agents on real-world, enterprise-grade finance and accounting workflows that interleave data entry, structuring, formatting, web search, cross-file retrieval, calculation, modeling, validation, translation, visualization, and reporting. Finch is built from authentic enterprise workspaces from Enron (15,000 files and 500,000 emails) and other financial institutions spanning 2000 to 2025, preserving the in-the-wild messiness of multimodal artifacts such as tables and charts across diverse domains including budgeting, trading, and asset management. We propose a workflow construction process that combines LLM-assisted mining of workflows from authentic enterprise environments with expert annotation. Specifically, we use LLM-assisted, expert-verified derivation of workflows from real-world email threads and spreadsheet version histories, followed by meticulous workflow an...