Grok 4.20 Posts Record-Low 17% Hallucination Rate on New Benchmark

xAI's latest model scores dramatically lower on hallucination metrics than competitors, potentially carving out a differentiated position as the 'honest' model in a market where confidence often masks confabulation.

xAI's Grok 4.20 achieved a 17% hallucination rate on a new benchmark that prioritizes factual honesty over completeness, as reported by @XFreeze. For comparison, the same benchmark reportedly scored GPT-5.4 at 89% — though the specific benchmark methodology and conditions weren't detailed in the initial report, which warrants caution about direct comparisons.

Lorem ipsum dolor sit amet, consectetur adipiscing elit. Sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum. Vestibulum ante ipsum primis in faucibus orci luctus et ultrices posuere cubilia curae.

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