They are comparing grok 4.7 xhigh with grok 4.6 high
This is a AI post classified by Jev as Frontier models (a model release), kept by the AI Radar because it carries real work, not commentary.
They are comparing grok 4.7 xhigh with grok 4.6 high this model is dead on arrival check quoted tweet Grok 4.7 eats 2.5 times token to score 2 points higher on artificial arena and on cursorbench 4.7 low score less than grok 4.6 low takes more token and more steps
Posted by Chetaslua (35.7k followers) 1 h ago · 156 likes · 9.4k views · view the original post on X. Kept by the AI Radar as Frontier models.
More AI work like this
- Claude Opus 5.5 beats GPT-6 Astra — @0x0SojalSec
- grok 4.7 somehow forgot everything 4.6 knew about frontend — @daradoescode
- Grok 4.7 has launched, and the price performance is interesting — @MaaSonder
- Grok 4.7 is now live on the APEX leaderboards. — @mercor
- Grok 4.7 will match Opus 5 they said.. and it turned out to be behind Muse Spark 1.3 too… — @TimJayas
- Grok 4.7 by @SpaceXAI is now available on Design Arena! — @DesignArena
- Grok 4.7’s SVG of an Xbox One controller. — @TokenGremlin
- Grok 4.7 is responsible for this UX on https://kody.codes — @kentcdodds
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 39.7k posts from 5k X accounts over the last 14 days, 1.6k tools, 19 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-21 18:40 UTC. Full method.