Four models build a radial engine from one prompt, and no two match
Given the same prompt to build a radial engine, Claude Opus 5.5, GPT-6 Astra, Gemini 4 Argon and Grok 4.7 each produced a different machine, and the author argues the gap is now about taste and restraint rather than accuracy.
this is f*cking wild. 4 AIs, one prompt - build a radial engine - and not one built the same machine. Claude Opus 5.5 · GPT-6 Astra · Gemini 4 Argon · Grok 4.7 same words, four completely different instincts. Astra over-built it - every cylinder, every bolt, a full holographic blueprint. Opus went tight and clean, exactly enough and nothing extra. Gemini leaned industrial, all fins and mass. Grok kept it simple - maybe too simple. this is the part benchmarks never catch. build it isn’t one skill. one model shows off, one model edits itself, one model shrugs. the gap isn’t accuracy anymore - it’s taste and restraint. so which one would you actually trust to turn over and run? Opus, Astra, Gemini or Grok? I run one of these every week, and the differences only get sharper.
This post quotes another post: x.com/kinderlayer/status/2109997714591068522