AI Makes Mistakes in 88% of Complex Financial Queries

A study by Saturn found that popular chatbots like ChatGPT, Claude, Copilot, Grok, and Gemini provide incorrect answers to financial questions 57% of the time, and for complex queries involving multiple calculations, the error rate rises to 88%. This highlights the risks of using generative AI for tax, pension, and investment decisions, where mistakes can lead to financial losses. Researchers tested over 100 queries, uncovering errors in financial calculations, ignoring changes in tax legislation, and fabricating rules. In some models, the error rate for complex questions reached 99%. The best performer was Claude Opus 5, which made mistakes in 39% of its responses. Saturn's CEO Amal Jolly noted that millions of people trust AI for financial advice but receive incorrect answers. For instance, a mistake by the Claude Haiku 4.5 model could have led to a pension contributor being charged an HMRC fee of £17,500. Paid models generally provided more accurate responses, but Sarah Coles from AJ Bell emphasized that professional advice remains crucial. The results also show that 20% of adults in the UK are willing to allow AI to make financial decisions.

This content is provided for general informational purposes only and doesn't constitute financial, investment, legal, or tax advice. Any events, rewards, online promotions, or related information mentioned herein should not be considered a recommendation, solicitation, or invitation to purchase, sell, trade, or otherwise deal in any crypto assets. Crypto assets are highly volatile and may result in loss. The availability of WEEX services, products, and related events may vary by region. You are responsible for ensuring that your participation is in accordance with applicable local laws and regulations.