FrontierFinance: A Long-Horizon Computer-Use Benchmark of Real-World Financial Tasks
This addresses the problem of measuring AI-driven labor displacement in finance for professionals and policymakers, though it is incremental as it focuses on benchmarking rather than novel AI methods.
The authors tackled the lack of robust benchmarks for AI performance in real-world financial tasks by introducing FrontierFinance, a long-horizon benchmark of 25 complex financial modeling tasks requiring over 18 hours of human labor each, and showed that human experts outperform state-of-the-art systems in scores and client-ready outputs.
As concerns surrounding AI-driven labor displacement intensify in knowledge-intensive sectors, existing benchmarks fail to measure performance on tasks that define practical professional expertise. Finance, in particular, has been identified as a domain with high AI exposure risk, yet lacks robust benchmarks to track real-world developments. This gap is compounded by the absence of clear accountability mechanisms in current Large Language Model (LLM) deployments. To address this, we introduce FrontierFinance, a long-horizon benchmark of 25 complex financial modeling tasks across five core finance models, requiring an average of over 18 hours of skilled human labor per task to complete. Developed with financial professionals, the benchmark reflects industry-standard financial modeling workflows and is paired with detailed rubrics for structured evaluation. We engage human experts to define the tasks, create rubrics, grade LLMs, and perform the tasks themselves as human baselines. We demonstrate that our human experts both receive higher scores on average, and are more likely to provide client-ready outputs than current state-of-the-art systems.