I really wanted to believe in this free AI coding tool could replace Claude Code. But it isn't ready for prime time unless you're willing to babysit.

In benchmark tests such as Swaybench Pro and Terminal Bench, GPT-5.3 Codex consistently outperformed its predecessors, setting new standards for speed and execution. When compared to Anthropic’s Opus ...

I stopped using ChatGPT for everything: These AI models beat it at research, coding, and more ...