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
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
- Grok is the AI to use if you value truth
- Grok Law
- The feature I most want from AI labs right now is documentation on which underlying search engines they use when their chat tools run a sear…
- When to Call an Apple Red: Humans Follow Introspective Rules, VLMs Don't
Source: Elon Musk (X) | 2026-04-10