AA-Omniscience hallucination benchmark: Grok 4.7 at 29%, Astra at 51%

X Freeze @XFreezeOriginally posted 2026.09.22

Open original on X

Grok 4.7 xHigh just hit a remarkably low hallucination rate on Artificial Analysis’ AA-Omniscience benchmark • Grok 4.7 xHigh — 29% 🏆 • GPT-6 Astra — 51% • Claude Fable 5.1 — 73% Lower is better Grok is dramatically outperforming both Astra and Fable 5.1 on hallucination rate