Early hands-on: GPT-6-Sol xhigh underwhelms on Codex's Boeing bench

victormustar · x · 2026-09-23

@victormustar reports that running GPT-6-Sol xhigh in Codex on the "Boeing bench" yields unimpressive results. No numbers are given in the text itself, with details in the attached screenshot. An early negative datapoint on the newest model's coding ability.

Original post →

More from Models

Models channel →