By skyforbes 
Honestly, I don't see many apps programmed with ChatGPT, while it's good Overall in Writing, Image creation etc, I don't think it is as good as Claude AI when it comes to creating code alone. but I saw on Anthropic's official website that the difference , is only like 3% between GPT-5.1-Codex-Max vs Opus 4.5
Definitely it has to be much higher than that, right?
I myself only use Claude AI, but haven't really used the recent GPT 5.1 models. I use Claude code and I have made absolutely large apps close to 50,000 lines of code combined(of course, lines of code does not equate to a metric of success).
What is your take on it?