Skip to content

Back to the catalog

Abdullah (@abdullah0094) on X
x.comthread

Abdullah (@abdullah0094) on X

An X thread by Abdullah on GPT-6.1 Terra versus Sol in Codex. Abdullah says Terra gives twice the Codex usage of Sol and asks whether the quality drop is obvious. A reply says it is too early for a verdict, cites OpenAI's claim that Terra matches GPT-6 Astra on Agents' Last Exam, and suggests defaulting to Terra and switching to Sol with /model when it stalls.

TL;DR Thread weighing GPT-6.1 Terra as the default Codex model for its 2x usage over Sol, with Sol as a fallback via /model.
Open original ↗

Organisations named here

  • OpenAI
  • Agents' Last Exam

Technologies named here

  • Codex
  • GPT-6.1 Terra
  • /model
  • GPT-6.1 Sol
  • GPT-6 Astra

Techniques named here

  • Default to cheaper model with escalation

Related in coding-agents