FrontierFinance (Financial Modeling) - Expert-Graded: 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 ten tasks graded by finance domain experts rather than an LLM judge, in percent; higher is better.

Metric: Average rubric score (%) over ten tasks (two per model type) graded by finance domain experts against the expert-written rubrics; computer-use agents in a minimal Inspect harness build complete Excel financial models from detailed prompts; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 2 models tracked. Updated 7 Oct 2026.

Top models

#ModelSettingScoreOverall rank
1GPT-5.4xHigh70.9#135
2Claude Opus 4.6High61.8#113

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-expert-graded · How It Works · Data refreshed daily, snapshot 2026-11-21.