# FrontierFinance: A Long-Horizon Computer-Use Benchmark of Real-World Financial Tasks

arXiv: https://arxiv.org/abs/2604.05912 · HTML: https://mlsanity.com/paper/2604.05912/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 29 references that are in the map.
- First posted on arXiv 7 Apr 2026.

## Builds on (most cited first, 21 of 21)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://mlsanity.com/paper/2311.12022/) (2023)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [WebArena: A Realistic Web Environment for Building Autonomous Agents](https://mlsanity.com/paper/2307.13854/) (2023)
- [Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models](https://mlsanity.com/paper/2206.04615/) (2022)
- [Prometheus: Inducing Fine-grained Evaluation Capability in Language Models](https://mlsanity.com/paper/2310.08491/) (2023)
- [FinQA: A Dataset of Numerical Reasoning over Financial Data](https://mlsanity.com/paper/2109.00122/) (2021)
- [Meta-Harness: End-to-End Optimization of Model Harnesses](https://mlsanity.com/paper/2603.28052/) (2026)
- [FinanceBench: A New Benchmark for Financial Question Answering](https://mlsanity.com/paper/2311.11944/) (2023)
- [MT-Bench-101: A Fine-Grained Benchmark for Evaluating Large Language Models in Multi-Turn Dialogues](https://mlsanity.com/paper/2402.14762/) (2024)
- [ConvFinQA: Exploring the Chain of Numerical Reasoning in Conversational Finance Question Answering](https://mlsanity.com/paper/2210.03849/) (2022)
- [GDPval: Evaluating AI Model Performance on Real-World Economically Valuable Tasks](https://mlsanity.com/paper/2510.04374/) (2025)
- [SWE-Lancer: Can Frontier LLMs Earn 1 Million from Real-World Freelance Software Engineering?](https://mlsanity.com/paper/2502.12115/) (2025)
- [DocFinQA: A Long-Context Financial Reasoning Dataset](https://mlsanity.com/paper/2401.06915/) (2024)
- [MCP-RADAR: A Multi-Dimensional Benchmark for Evaluating Tool Use Capabilities in Large Language Models](https://mlsanity.com/paper/2505.16700/) (2025)
- [FinanceMath: Knowledge-Intensive Math Reasoning in Finance Domains](https://mlsanity.com/paper/2311.09797/) (2023)
- [LongCLI-Bench: A Preliminary Benchmark and Study for Long-horizon Agentic Programming in Command-Line Interfaces](https://mlsanity.com/paper/2602.14337/) (2026)
- [BizBench: A Quantitative Reasoning Benchmark for Business and Finance](https://mlsanity.com/paper/2311.06602/) (2023)
- [XFinBench: Benchmarking LLMs in Complex Financial Problem Solving and Reasoning](https://mlsanity.com/paper/2508.15861/) (2025)

## Built on by (most cited first, 3 of 3)

- [FrontierFinance: A Challenging Benchmark for Measuring Frontier Intelligence of Finance Agents](https://mlsanity.com/paper/2608.11683/) (2026)
- [One Analyst Is Not Ground Truth: Grading Agent-Built Financial Models Against Observed Professional Practice](https://mlsanity.com/paper/2607.24889/) (2026)
- [FinFIRST: Benchmarking Search Agents for Financial Information Retrieval, Sourcing and Traceability](https://mlsanity.com/paper/2609.25192/) (2026)

## Abstract (arXiv)

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.