Finch

Finch (FinWorkBench): Benchmarking Finance & Accounting across Spreadsheet-Centric Enterprise Workflows This repository contains the dataset for Finch, an enterprise-grade benchmark for evaluating an agent’s ability to work like a skilled finance & accounting expert (work IQ) on real-world professional workflows. Paper: Evaluation Code: 🍻 Updates 2026-4-6: FinWorkBench is accepted to ACL… See the full description on the dataset page:

Source: Hugging Face Hub (FinWorkBench/Finch). Metadata imported from the dataset’s Hub tags.