FinBen: leaderboard
FinBen: Evaluates financial analysis, accounting, market reasoning, and quantitative business tasks.
Metric: Cumulative Return (percentage). Source: github.com. Source: benchmarklist.com. Saturation forecast: Estimated already saturated. 6 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-4 | 28.19 | #438 |
| 2 | GPT-3.5 Turbo | 4.48 | #865 |
| 3 | Llama 2 70B | 4.02 | #1201 |
| 4 | Llama 3 70B | -2.57 | #631 |
| 5 | GPT-4o | -5.54 | #343 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=finben · How It Works · Data refreshed daily, snapshot 2026-10-20.