Hands-on: Opus 5.5 high beats GPT-6 astra xhigh on real Pagespeed optimization

mazzaTalk · x · 2026-09-27

The author tested frontier models on optimizing a website's Pagespeed and found GPT-6 astra xhigh failed to beat Opus 5.5 high. They also note that Codex is now the one being called underwhelming.

A first-hand horizontal comparison of frontier models on a real-world task.

Original post →

More from Models

Models channel →