OpenAI Codex vs GitHub Copilot: what developers actually say
Based on 2,672 opinions on Hacker News from developers who discussed these two, most of them first-hand users.
Codex comes out ahead on nearly every measure. It has 2,013 opinions from 1,386 authors and 69% approval, versus 659 opinions from 535 authors and 42% for Copilot, and it leads on code quality (343 positive to 116 negative, against 38 to 93), cost (174 to 54, against 60 to 80) and usage limits (131 to 61, against 20 to 31). Head-to-head, 13 commenters picked Codex and 2 picked Copilot, and 90-day approval is 63% against 38%. Copilot is the better pick for developers already working in VS Code or Visual Studio who want an in-editor agent and autocomplete.
When developers explicitly said they prefer one or switched: 13 picked OpenAI Codex, 2 picked GitHub Copilot.
Choose OpenAI Codex if
- Want the stronger terminal agent on quality, cost and limits
- Run long multi-step tasks and value autonomy and speed
- Accept occasional quota caps in exchange for better output
Choose GitHub Copilot if
- Already work in VS Code or Visual Studio and want an in-editor agent
- Want autocomplete more than a terminal workflow
- Already pay for Copilot and want to use its included quota
Where each one wins and loses
Why developers switched
Picked OpenAI Codex
Picked GitHub Copilot
Summaries are paraphrased. Each links to the original comment.