Finance Agents Benchmark - Criterion Pass Rate: leaderboard
FAB's share of the 231 due-diligence rubric criteria that the agent's answers satisfy, over 50 tasks and three trials; higher is better.
Metric: Share of the 231 rubric criteria passed (%), 50 tasks x 3 trials. Source: github.com. Saturation forecast: Around February 2027. 4 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-6 Sol (Medium) | 83.4 | #25 (GPT-6 Sol) |
| 2 | GPT-6 Luna (Medium) | 79.5 | #95 (GPT-6 Luna) |
| 3 | GLM-5.3 Flash (Medium) | 76.2 | #122 (GLM-5.3 Flash) |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=finance-agents-benchmark-criterion-pass-rate · How It Works · Data refreshed daily, snapshot 2026-11-13.