Grok 4.7 xHigh hits 58% on AA-Briefcase, just 1 point behind Claude Fable 5.1 Max

XFreeze · x · 2026-09-22

Grok 4.7 xHigh now sits at the top of Artificial Analysis' AA-Briefcase benchmark with 58%, just one point behind Claude Fable 5.1 Max at 59%. Grok outscores GPT-6 Astra, GPT-5.6, Gemini, Kimi, GLM and nearly every other frontier model on the benchmark, marking the closest race yet at the top.

Related event: Grok 4.7 Scores 46 on Intelligence Index, Enters Top Four Labs at Double Token Cost(8 posts)→

Original post →

More from Models

Models channel →