Codex - ChatGPT 5.4 and 5.5 is perfroming like Gemini low level agents

Resolved 💬 2 comments Opened Apr 27, 2026 by Nanny1955 Closed Apr 27, 2026
💡 Likely answer: A maintainer (github-actions[bot], contributor) responded on this thread — see the highlighted reply below.

What version of the Codex App are you using (From “About Codex” dialog)?

the latest

What subscription do you have?

20 or 25 a month

What platform is your computer?

Windows

What issue are you seeing?

I have been using Codex for 2 months or more. I am now paying for a subscription and it is absolutley terrible. It is behaving like Gemini low level agents. I have used Chat 5.4 and 5.3. and now 5.5. You are ripping off your customers. I know the difference. I have used ChatGPT for months now!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!

What steps can reproduce the bug?

Uploaded thread: 019dccb5-e8bd-7d51-a649-2a9f5c9f7f9b

What is the expected behavior?

_No response_

Additional information

_No response_

View original on GitHub ↗

2 Comments

github-actions[bot] contributor · 4 months ago

Potential duplicates detected. Please review them and close your issue if it is a duplicate.

  • #18104
  • #19361

Powered by Codex Action

etraut-openai contributor · 4 months ago

Thanks for the bug report. We'll share the feedback with the team responsible for training our codex models. We're tracking this feedback and similar reports so we can improve future models. And thanks for using the /feedback command. That additional information is useful.