Show HN: FAB – A benchmark for AI agents doing financial due diligence

A team of ex-EY employees released FAB (Finance Agents Benchmark), a public benchmark testing AI agents on financial due diligence work, with code on GitHub and data room and tasks on Hugging Face. The team reports that agents can find relevant facts but still struggle to carry them through to a complete, reliable analysis, and says it will keep expanding FAB to more companies and models, scaling in stages because building and running the benchmark isn't cheap.

The world economy around us depends on complex financial work. How well can AI do it? We a team of ex-EY employees built FAB - Finance Agents Benchmark, testing AI Agents on the work behind financial due diligence. Agents can find the relevant facts, but still struggle to carry them through to a complete, reliable analysis. We’ll keep expanding FAB to more companies and testing more models. Building and running this benchmark isn’t cheap, so we’re scaling it in stages. The benchmark is public. GitHub: Hugging Face: https://github.com/SecondState-ai/finance-agents-benchmark https://github.com/SecondState-ai/finance-agents-benchmark data room and tasks: https://huggingface.co/datasets/secondstate/finance-agents-b... https://huggingface.co/datasets/secondstate/finance-agents-benchmark Comments URL: https://news.ycombinator.com/item?id=49874360 https://news.ycombinator.com/item?id=49874360 Points: 1 Comments: 0