Who is “us”? It does seem that some scientists prefer Codex for its math capabilities but when it comes to general frontend and backend construction, Claude Code is just as good and possibly made better with its extensive Skills library.

Both codex and Claude code fail when it comes to extremely sophisticated programming for distributed systems

I also find Codex much more generous in terms of what you get with a Pro ($20/mo) subscription. I use it pretty much non-stop and I have yet to hit a limit. Weekly reset is much better as well.

Usage limits are more generous and GPT 5.4 is a good model, but yes, UI/UX lags behind Claude Code. Currently I'm especially missing /rewind with code restoration and proper support for plugin marketplaces

GPT/claude/gemini is pretty interchangeable at this point.

I prefer GLM 5.1 and MiniMax 2.7. With a better harness like Forge Code, I have better results for way less money than by using GPT and Opus.

i find myself being more productive with codex/copilot on coding tasks, but claude does seem to be better at planning

Does this work for people? To me having a "better product" would be completely irrelevant if the use cases are evil.

Shill talk

[flagged]