Get all your news in one place.
100's of premium titles.
One app.
Start reading
TechRadar
TechRadar
Graham Barlow

New tests show ChatGPT-5 is more accurate than GPT-4o – Grok still struggles with hallucinations

ChatGPT-5.
  • ChatGPT-5 scores a low 1.4% on the Hallucination Leaderboard
  • This puts it ahead of ChatGPT-4 which scores 1.8% and GPT-4o, which scores 1.49%
  • Grok 4 is much higher at 4.8%, with Gemini-2.5 Pro at 2.6%

Sam Altman, OpenAI CEO, launched ChatGPT-5 on Thursday as the most “powerful, smart, fastest, reliable and robust version of ChatGPT that we’ve ever shipped”, and in the presentation, OpenAI staff also emphasized that ChatGPT-5 would “mitigate hallucinations”.

Sign up to read this article
Read news from 100's of titles, curated specifically for you.
Already a member? Sign in here
Related Stories
Top stories on inkl right now
One subscription that gives you access to news from hundreds of sites
Already a member? Sign in here
Our Picks
Fourteen days free
Download the app
One app. One membership.
100+ trusted global sources.