A childhood game idea prototyped "with Opus 5.5 and Grok 4.7" in three.js
DesignCodeRead the post
x.com · link re-checked 2026-10-16
Grok 4.6
By SpaceXAI. 5 results on 5 boards, copied as published. Different boards, different metrics: don't add them up.
License (as listed)Proprietary
Hosting regionNot confirmed
Boards5
Code
Agentic / terminal
- 20.3%Terminal-Bench 4.0
Grok 4.6 (high) · Resolution rate
Grok Build · as of 2026-08-12 ↗
Websites
Design
No result on the boards we captured
Android
No result on the boards we captured
iOS
No mature public leaderboard
Available in
Grok (consumer app) Free→ Grok (consumer app) Plus→ Grok (consumer app) Premium→ Grok (consumer app) Super→ Grok (consumer app) Ultra→ Grok Build Free→ Grok Build Plus→ Grok Build Premium→ Grok Build Super→ Grok Build Ultra→
Use cases with this model
No sourced use case names this exact model version.
Same family: Grok 9
Grok Build Beta with Grok 4.7 shipped a complex game in 30 minutes. 195 steps
CodeRead the post
x.com · link re-checked 2026-10-16
with Opus 5.5 being what it is, there's really zero reason to use Grok 4.7 unless…
CodeRead the post
x.com · link re-checked 2026-10-16
A game catching a Super Heavy booster with Mechazilla arms, "entirely built with Grok Build, Grok 4.7 and a simple prompt"
CodeRead the post
x.com · link re-checked 2026-10-16
Grok 4.7 just built a GTA-style open-world game from a single prompt in Grok Build
CodeDesignRead the post
x.com · link re-checked 2026-10-16
A cloth simulation in three.js. "not one shot, it took many iterations … took the entire weeks usage"
DesignRead the post
x.com · link re-checked 2026-10-16
Sources
lmarena.ai/leaderboard/webdev vals.ai/benchmarks/vibe-code vals.ai/benchmarks/swebench vals.ai/benchmarks/lcb tbench.ai/leaderboard