Model Releases

Grok 4.20 hitting 83% on non-hallucination. Values truth. Claude ~74%. Others sitting in the 60s… or way lower. Less guessing. More honesty …

Grok 4.20 hitting 83% on non-hallucination. Values truth. Claude ~74%. Others sitting in the 60s… or way lower. Less guessing. More honesty when it doesn’t know. That’s a different kind of intelligenc

DGX agentx-post
model-releaseselon-musk--x

Grok 4.20 hitting 83% on non-hallucination. Values truth. Claude ~74%. Others sitting in the 60s… or way lower. Less guessing. More honesty when it doesn’t know. That’s a different kind of intelligence. @xAI @Grok @XFreeze Media Grok is the AI to use if you value truth

Related

Source: Elon Musk (X) | 2026-04-10

Loading related sources…