Codex vs Cursor
Compare models
Codex is more worth it — 58% vs 54%
How we score worth-it? →Reliable executor — lower ceiling, generous limits
- In my experience gpt5-codex (medium) and codex-cli is notably better than Sonnet 4.5 and claude-code. It is slower, but the results are much more often correct and it doesn't rush into half-baked solutions/dumb approaches as eagerly. I'd much rather wait 5 minutes than have to clean up manually.— hn
- I was able to use it for few use cases where it got it right the first time. The ability to use a screenshot to create an application is nice for rapid prototyping.— hn ↗
- Codex: a bit slow, but its instruction-following is quite good.— v2ex ↗
- By the time I moved to Codex, I felt the AI could handle UI design (frontend), implement features, and even test the project in the browser by itself.— v2ex ↗
- 我跟up主的感觉有点不一样,在我看还是Codex做事更稳一些。同样的提示词给到Codex和antigravity,出来的结果差异不小。Codex做事不急躁,稳扎稳打;而antigravity跟Gemini简直一个模子刻出来的,都是“谄媚+激进”。当然,这不是说antigravity不好,而是适合的任务与Codex不同。— bilibili ↗
- I've been quite unimpressed by Codex for now... the quality of the code is worse than Claude for me.— hn ↗
- I'm done. Codex was dumb as a rock today - on 6.1 it keeps stopping to report back, can't get through a single long task, and reports in again after every couple of file edits. Absolutely braindead.— v2ex ↗
- hi, just got 0.157.0, highlighting text in the TUI now has a pretty rough (~.5 seconds) latency. I copy the outputted text a lot, so this is a major pain point. Have to downgrade to 0.156.0 till this is fixed 😅— github ↗
“Great for kicking off background tasks and walking away”
“Predictable cost and generous limits — the budget pick for heavy use”
“But it feels lazy on complex reasoning. It'll take shortcuts you didn't ask for”
Anysphere's AI-first coding agent/IDE; acquired by xAI (SpaceX) in Aug 2026 and bundled with The X Subscription.
- I actually think Cursor is pretty good. For most tasks I just watch a video and glance over when it pauses — barely need to pay attention.— v2ex
- The commit and push button is a miracle. The pain points are very painful, but the good vastly exceeds the pain.— cursor_forum ↗
- I'm a happy Cursor user. Main reason is it just works great and was the first one I tried.— hn ↗
- I really wish there was something as good as Cursor for Jetbrains.— hn ↗
- IMO cursor all the way.— hn ↗
- Cursor IDE support hallucinates lockout policy, causes user cancellations.— hn ↗
- No VS Code Extensions Support — no Prettier, no TypeScript tooling, no linting. This makes reviewing agent-generated code significantly harder.— cursor_forum ↗
- Recently I became so frustrated by Cursor's bugs and tab completion performance regressions that I disabled completions.— hn ↗
- I've already relegated Cursor to a backup you use only when there's no other choice. Last year I still treated it as my first choice - it's just ridiculously expensive now.— v2ex ↗
- Whatever you do, don't sign up for that new bundled plan - it burned 7 days' worth of quota in a single day.— v2ex ↗
Which should you pick?
Codex is slightly ahead (58% vs 54%), a 4-point gap that rarely shows up in daily use — price and use case matter more here.
On entry price, Cursor is cheaper ($8 vs $20, Codex costs about 150% more).
Both are in the Agent category with similar coverage; the real difference is stability and cost — run one of your own tasks through each before deciding.
What users actually said about Codex: "In my experience gpt5-codex (medium) and codex-cli is notably better than Sonnet 4.5 and c…"
FAQ
Is Codex or Cursor more worth it?
Codex is more worth it, with a 58% worth-it score vs 54% for Cursor.
How much does Codex cost vs Cursor?
Codex: Free · Plus $20/mo · API $1.75/$14 · Cursor: Free · $8 Plus · $30 Premium · $100 Super · $200 Ultra.
What do users say about Codex vs Cursor?
Codex: Great for kicking off background tasks and walking away. Cursor: no highlights yet.