OpenAI Codex vs Gemini CLI: what developers actually say
Based on 2,224 opinions on Hacker News from developers who discussed these two, most of them first-hand users.
OpenAI Codex comes out ahead in this HN sample of 2,013 opinions against 211: 69% approval against 29%, 63% over the last 90 days against 25%, and 12 explicit picks over Gemini CLI with none going the other way. Its code-quality mentions run 343 positive to 116 negative, and it has more positive than negative mentions on autonomy (169 to 46), cost/pricing (174 to 54) and usage limits (131 to 61). Reliability is Codex's weak spot at 112 positive and 127 negative, while Gemini CLI is worse there at 7 and 55 and has 7 positive and 28 negative UX mentions. Gemini CLI is the better pick when you want a lightweight open-source companion for an existing IDE or notes workflow, or a fallback when Codex limits are reached.
When developers explicitly said they prefer one or switched: 12 picked OpenAI Codex, 0 picked Gemini CLI.
Choose OpenAI Codex if
- Want stronger code-quality feedback
- Want more positive autonomy and usage-limit feedback
- Want a larger HN evidence base
Choose Gemini CLI if
- Want an open-source terminal agent
- Work inside an existing IDE or notes vault
- Need a fallback when Codex limits are reached
Where each one wins and loses
Why developers switched
Picked OpenAI Codex
Picked Gemini CLI
No explicit switches recorded.
Summaries are paraphrased. Each links to the original comment.