ModelsSep 22, 2026 · 18:578 sources

Grok 4.7 Uses 125% More Output Tokens on Intelligence Benchmark

From huggingnews.com

Image: huggingnews.com
AI;DR

Grok 4.7 scored 46 on the Artificial Analysis Intelligence Index, two points above Grok 4.6, while using about 81,000 output tokens per task versus 36,000, an increase of 125%.

Read the sourceSign in to suggest

Sources

+ 7 more
  1. SUPPORT@ns123abc“Grok TRIPLED on Terminal-Bench 4.0 in only two months (12.4% -> 38.0%), overtaking GPT-5.6 Sol”x.com
  2. SUPPORT@theo“Grok 4.7 doesn’t beat Sol. It doesn’t even best Grok 4.6 in many benchmarks.”x.com
  3. SUPPORT@theo“I have yet to find a single bench where Grok 4.7 is more token-efficient than Grok 4.6.”x.com
  4. SUPPORT@theo“Grok 4.7 is much harder to forgive. They claimed it would be more token-efficient, and it's less by 30 to 80%.”x.com
  5. SUPPORT@artificialanlys“API cost to produce example decks: Grok 4.7 (xhigh) ~$8 vs. Grok 4.6 (xhigh) ~$4.40”x.com
  6. SUPPORT@kimmonismus“Grok 4.7 looks super amazing!”x.com
  7. SUPPORT@theo“Looking like Grok 4.7 is not quite as cheap as before. Comes out more expensive than Astra on Artificial Analysis 🙃”x.com
#xai#grok#coding#agent#benchmark#inference#reasoningMarkdown
Content history (2)
  • 2026-10-04 · Summary · vi · Replaced stored text
    Phiên bản Grok 4.7 mới của xAI đã tăng cường đáng kể lượng token sử dụng cho đầu ra khi t…
    Grok 4.7 của SpaceXAI đạt 46 điểm trên Artificial Analysis Intelligence Index, cao hơn ha…
  • 2026-10-04 · Title · vi · Replaced stored text
    Grok 4.7 tiêu tốn 125% nhiều token đầu ra hơn trên bảng đánh giá trí tuệ
    Grok 4.7 dùng nhiều hơn 125% output token trên benchmark năng lực

One ranked edition, every morning

The stories that matter today. Free, cancel anytime.

Telegram @aidr_today