
New tests show ChatGPT-5 is more accurate than GPT-4o – Grok still struggles with hallucinations
According to the latest figures ChatGPT-5 hallucinates less than GPT-4o, but Grok 4 hallucinates a lot more than most GPT models.
Other versions of this page are available with specific content for the following regions:
Please login or signup to comment
Please wait...