FrontierFinance (Financial Modeling): leaderboard

FrontierFinance (Krumdick et al., 2026; distinct from the Samaya AI FrontierFinance board) gives computer-use agents long-horizon financial modeling tasks: from a detailed prompt the agent builds a complete Excel model of a real company, scored against an expert-written rubric. Average rubric score over all 25 tasks (DCF, three-statement, LBO, merger and lender models) from a rubric-guided Claude Sonnet 4.6 judge, in percent; higher is better.

Metric: Average rubric score (%) over all 25 tasks (five each of DCF, three-statement, LBO, M&A and lender models), judged by a Claude Sonnet 4.6 agent against the expert-written task rubric (with SEC EDGAR and spreadsheet tools); computer-use agents in a minimal Inspect harness (GUI control plus a bash terminal) build complete Excel financial models from detailed prompts; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 3 models tracked. Updated 7 Oct 2026.

Top models

#ModelSettingScoreOverall rank
1GPT-5.4xHigh87.5#135
2Claude Opus 4.6High83#113
3Gemini 3.1 Pro (Preview)63.5#99

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=frontierfinance-financial-modeling · How It Works · Data refreshed daily, snapshot 2026-11-21.