That is really helpful for me. From your experience it appears like codex is better value for money as a developer who can write proper prompts and not just expect AI to vibe code everything.
Though I think gpt was better in terms of architectural decisions earlier as well, and claude was better interms of coding and UI. Do you think with codex gpt has beaten claude or on par with claude in terms of UI and clean code quality?
I wouldn’t say that my prompts are more proper than anyone else’s, but GPT-5.4 adheres to them really well and does a good job of asking clarifying questions when needed. Spending some time up front to make a very detailed list of requirements here really helped. I think Claude Code still creates better UIs when given a broad task, but Codex makes totally usable interfaces when it’s fed designs and specific instructions. Your mileage may vary; I think different people’s development styles may mesh better with different models and harnesses. I don’t think that Claude Code is a clear winner in April 2026 compared to how it outperformed other options a few months ago.