FrontierFinance (Financial Modeling) - Expert-Graded: leaderboard
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 January 2027. 2 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.4 (xHigh) | 70.9 |
| 2 | Claude Opus 4.6 (High) | 61.8 |
Interactive version: theaggregate.ai/benchmark?slug=frontierfinance-financial-modeling-expert-graded · How It Works · Data refreshed daily, snapshot 2026-10-07.