Grok Claims Lowest Hallucination Rate in Workplace AI Study — But the Methodology Deserves Scrutiny
A Relum study found Grok hallucinated at just 8% compared to ChatGPT's 35%, generating massive engagement. The result is provocative, but the study's framing raises questions about what "hallucination rate" actually measures in practice.
A reliability study from Relum has crowned Grok as the most truthful AI assistant in workplace contexts, reporting an 8% hallucination rate versus ChatGPT's 35%. As @MarioNawfal reported — in a post that racked up 3.7 million views — Grok also achieved the lowest overall "risk score" in the evaluation, positioning xAI's model as the reliability leader heading into 2026.
Unlock the full briefing
Get every story in today's briefing, the full archive, and the daily AI intelligence brief.
All stories today
Full archive
Daily brief
Cancel anytime. Payments powered by Stripe.