20 Nov 2025
AI tools including Chat GPT, Gemini and Meta AI are giving inaccurate, unclear and risky advice which could prove costly if followed, warns consumer champion Which?.
Research showed that around half of UK adults are now using AI tools to research topics including personal finance, the law and health.
Which? tested six AI tools - ChatGPT, Google Gemini, Gemini AI Overview (AIO), Microsoft's Copilot, Meta AI and Perplexity - to establish how well they could answer common consumer questions. Meta AI received the worst score in Which?'s tests, achieving just 55% overall.
ChatGPT, which is the most used tool according to Which?'s survey, came second to bottom with an overall score of 64%. Perplexity topped the table with 71%. It received the highest scores for accuracy, relevance, clarity and usefulness of any of the tools on test.
Andrew Laughlin, Which? Tech Expert, said: 'Everyday use of AI is soaring, but we've found that when it comes to getting the answers you need, the devil is in the details. Our research uncovered far too many inaccuracies and misleading statements for comfort, especially when leaning on AI for important issues like financial or legal queries.
'When using AI, always make sure to define your question clearly, and check the sources the AI is drawing answers from. For particularly complex issues, always seek professional advice - particularly for medical queries, before making major financial decisions or embarking on legal action.'