Grok 4.7 early test: highly token-efficient, overnight task used only ~6% quota
xdNiBoR · x · 2026-09-22
A power user's early impressions of Grok 4.7: clear improvements over 4.6, still very cheap, and seemingly highly token-efficient — a large overnight task consumed only about 6% of usage. Verdict: roughly met expectations, and doing more work at the same cost is highly valuable for heavy users.
Related event: Heavy Users Report Big Token Efficiency Gains in Grok 4.7(2 posts)→
More from Models
- Robot build test: GPT-6 Astra stabilizes two-board structure, Claude Fable 5.2 falls short — qinzytech · 2026-11-12
- Zvi dissects Anthropic's latest system card, disputing the autonomy threshold call — Don't Worry About the Vase (Zvi) · 2026-11-12
- antirez backs low-bit DeepSeek 4.1 Flash over Qwen 27B dense on Apple M5 Macs — antirez · 2026-11-12
- Gemini re-renders images as text when vision is removed, dropping only 6% WSR — zacharynado · 2026-11-12
- Bare-harness coding benchmark: Fable 5.2 best overall, Gemini 4 Carbon best value — Semantic_meaning · 2026-11-12
- Google's Physical-Engineering's Last Exam: all 14 frontier models score below 50% — dl_weekly · 2026-11-12