Codex vs Perplexity
قارن النماذج
Codex is more worth it — 58% vs 40%
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”
AI answer engine that combines real-time web search with cited, conversational answers, deep research, and multi-model selection.
- What Apple needs to accomplish with AI hasn't been done, at scale and with refinement, by any company anywhere, except maybe Perplexity.— hn ↗
- Comet user, so I use it by default. In my experience its overall capability is still strong, at least stronger than Gemini.— v2ex ↗
- You're not the only one using Perplexity Pro at $17 per month. And for what I've needed it to help me with, it has been fantastic.— hn ↗
- Using Gemini, ChatGPT and Claude in Hong Kong is a hassle, so I still use Perplexity.— bilibili ↗
- Somehow I convinced my colleague to finally try Perplexity, once dared - there’s no turning back. Brave is not something I’ll ever consider seriously given its crypto history and all.— hn ↗
- I did in-depth experiments this summer and was disappointed. It gets surface-level details right but falls apart on detailed work.— hn
- I remember asking Perplexity about instructions for upgrading an open source app... Instead, it hallucinated some instructions from its training corpus.— hn ↗
- They substituted models quite often, and imposed low usage limits for users who had been onboarded for free.— hn ↗
- When I was first dipping my toes into premium, hosted AI systems, I purchased a both a Perplexity Pro and Kagi Ultimate subscription to evaluate both of them. I decided to cancel Perplexity because it made me feel physically ill when I used it.— hn ↗
- Perplexity seems desperate. I used to be a subscriber, but they've been making their service worse to save money using tricks like "forgetting" that you picked a smarter model and switching you "accidentally" to their cheaper (and dumber) one.— hn ↗
Which should you pick?
The gap is clear: Codex sits at 58% while Perplexity is at 40%, a 18-point difference. If you just want the safer pick, start with Codex.
They price differently (Codex: Free · Plus $20/mo · API $1.75/$14; Perplexity: Free · Pro $20/mo · Max $200/mo), so estimate by your own usage.
Both are in the وكيل 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 Perplexity more worth it?
Codex is more worth it, with a 58% worth-it score vs 40% for Perplexity.
How much does Codex cost vs Perplexity?
Codex: Free · Plus $20/mo · API $1.75/$14 · Perplexity: Free · Pro $20/mo · Max $200/mo.
What do users say about Codex vs Perplexity?
Codex: Great for kicking off background tasks and walking away. Perplexity: no highlights yet.