Trending PR Campaigns
The AI Financial Advice Accuracy Test
Fintech firm Saturn tested 18 popular AI models against 121 real financial questions, asking each five times to measure both accuracy and consistency. Its report found that the models gave wrong answers 57% of the time, creating a sharp, media-friendly warning about the risks of trusting chatbots with pensions, mortgages and insurance decisions.
Why it worked: It packaged a hard, scary number—57% wrong—backed by a transparent, repeat-measure test across 18 models and 121 real questions.
The lesson: Consider stress-testing a common tool across real tasks five times, publish the failure rate, and rank winners and losers by consistency.
Coverage over time
How this story spread across the media
| Publication | Headline | Date |
|---|---|---|
| npr.org | AI chatbots are offering financial advice. Should you trust them? : NPR | Wednesday 12th August, 2026 |
| professionaladviser.com | AI models give inaccurate financial advice 57% of the time | Monday 14th September, 2026 |
| investmentnews.com | AI chatbots give wrong financial answers most of the time, study finds - InvestmentNews | Monday 21st September, 2026 |
| insurancebusinessmag.com | New report shows AI gets financial advice wrong most of the time | Insurance Business | Monday 21st September, 2026 |
| tomsguide.com | AI could be costing you money: new study finds chatbots get most financial questions wrong | Tom's Guide | Monday 21st September, 2026 |
| fa-mag.com | Two Studies Find AI Chatbots Are Mostly Wrong On Financial Advice | Tuesday 22nd September, 2026 |