A study by UK fintech firm Saturn reveals that mainstream AI models fail 57% of personal finance answers, with the failure rate climbing to 88% for complex multi-step queries. Free models show a 63% failure rate versus 49% for paid versions, reaching 93% on the hardest questions. Claude Opus 5 in reasoning mode performs best with a 39% failure rate, but one error on pension tax could have exposed a saver to a £17,500 penalty from HM Revenue and Customs. Meanwhile, 49% of global consumers have used AI for savings and investment decisions, 56% trust these tools, and 44% are unaware that such advice is unregulated.
Source: Read the original article
