
- 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”.