WHAT NEW IN X11.06 FRI

X 上的 AI 合集档案 · 23 个合集 · 69,408 条

gpt-6IMAGE

AA-Omniscience 幻觉率榜:Grok 4.7 29%,Astra 51%

Artificial Analysis 幻觉率基准显示 Grok 4.7 xHigh 仅 29%,GPT-6 Astra 为 51%,Claude Fable 5.1 为 73%,越低越好。

X Freeze
@XFreeze2026.09.22收录原推发布于 2026.09.22
AA-Omniscience 幻觉率榜:Grok 4.7 29%,Astra 51%
X Freeze @XFreeze原推发布于 2026.09.22
在 X 上打开原推

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

x.com/xfreeze/status/2102126393014534216采集于 2026.09.22 10:17