hckrnws
Interesting, the new model's prompt is ~half the size (10KB vs. 23KB) of the previous prompt[0][1].
SWE-bench performance is similar to normal gpt-5, so it seems the main delta with `gpt-5-codex` is on code refactors (via internal refactor benchmark 33.9% -> 51.3%).
As someone who recently used Codex CLI (`gpt-5-high`) to do a relatively large refactor (multiple internal libs to dedicated packages), I kept running into bugs introduced when the model would delete a file and then rewrite in (missing crucial or important details). My approach would have been to just the copy the file over and then make package-specific changes, so maybe better tool calling is at play here.
Additionally, they claim the new model is more steerable (both with AGENTS.md and generally). In my experience, Codex CLI w/gpt-5 is already a lot more steerable than Claude Code, but any improvements are welcome!
[0]https://github.com/openai/codex/blob/main/codex-rs/core/gpt_...
[1]https://github.com/openai/codex/blob/main/codex-rs/core/prom...
So you're all saying suddenly codex cli w gpt 5 codex is better than claude code? Hard to believe
Not suddenly, it's been better since GPT-5 launched.
Prompting is different, but in a good way.
With Claude Code, you can use less prompting, and Claude will get token happy and expand on your request. Great for greenfield/vibing, bad for iterating on existing projects.
With Codex CLI, GPT-5 seems to handle instructions much more precisely. It won't just go off on it's own and do a bunch of work, it will do what you ask.
I've found that being more specific up-front gets better results with GPT-5, whereas with Claude, being more specific doesn't necessarily stop the eagerness of it's output.
As with all LLMs, you can't compare apples to oranges, so to clarify, my experiences are primarily with Typescript and Rust codebases.
Codex CLI of course will sometimes do the wrong thing, or sometimes do something extra that you didn't intend for it to do.
It seems about half my sessions quickly become "why did you do that? rip __ out and just do ___". Then again, most of the other sessions involve Codex correctly inferring what I wanted without having to be so specific.
Yeah, I tried Claude Code CLI and never found it too useful, but that was Claude 3.5 era. Still using Claude 3.7/4.0 via Cursor were much better but still had to micro managed.
GPT5 + Codex CLI has been pretty productive for me. It's able to get a lot right in a simple prompt without getting too distracted with other crap. It's not perfect, but it's pretty good.
I actually worry GPT5-Codex will make it worse on that aspect though. One of the best parts of GPT5/Codex CLI is that it tends to plan and research first, then make code.
Yea, I have struggled with Claude to keep it focused on what I want and only what I want. I have no experience with GPT-5-Codex, but maybe I should.
Sounds like the difference between finding what needs to be done, making a plan, and executing on it remains something to consider and be aware of.
Claude Code has been a revelation and a bit of a let down the past 45 days.
Some open acknowledgement would have been great, but in lieu of it, it seems it's best to hop on a new tool and make sure you learn how to prompt better and not rely on the model to read between until usage is "optimized" and it no longer seems to work for those folks.
I've seen some interesting files that help any model understand a programming language as it's strong suit and it might not even be an expert in and how to best develop with it.
Its been better for awhile, people are sleeping on it, just like they slept on claude code when it initially came out.
It is 100% true. And they are rapidly losing users to Codex. Charts were shared recently showing a massive migration underway.
Oh yeah, Sonnet performance has been in the toilet for me. They claim they've mitigated it but when 4.0 first dropped CC was really impressive, and now I constantly have to babysit it because any time it hits a challenge it'll just stop trying and make a simple toy version and declare false victory. If I don't catch it and I let it build on top of that bullshit, things get nasty in a hurry.
It's a shame because the plan is a great deal but the number of all caps and profanity laced messages I'm firing off at Claude is too damned high.
GPT-5 is comparable to Opus without needing to constantly dip back down to Sonnet for cost management
Am I missing something? That.. doesn't seem to be true? https://npmtrends.com/@anthropic-ai/claude-code-vs-@openai/c...
> SWE-bench performance is similar to normal gpt-5, so it seems the main delta with `gpt-5-codex` is on code refactors
SWE-bench is a great eval, but it's very narrow. Two models can have the same SWE-bench scores but very different user experiences.
Here's a nice thread on X about the things that SWE-bench doesn't measure:
so annoying you cant read replies without an account nowadays
Use Nitter, the main instance works but there are a lot of other instances as well.
Change the url from x.com to xcancel.com to see it all.
Interestingly, "more steerable" can sometimes be a bad thing, as it will tend to follow your prompt to the letter even if that's against your interests. It requires better prompting and generally knowing what you're doing - might be worse for vibe-coders and better for experienced SWEs.
Yes, given a similarly sparse prompt, Claude Code seems to perform "better" because it eagerly does things you don't necessarily know to ask
GPT-5 may underwhelm with the same sparse prompt, as it seems to do exactly what's asked, not more
You can still "fully vibe" with GPT-5, but the pattern works better in two steps:
1. Plan (iterate on high-level spec/PRD, split into actions)
2. Build (work through plans)
Splitting the context here is important, as any LLM will perform worse as the context gets more polluted.
The best of both worlds would surely be for the LLM to write what you've asked, but also write comments about other things it could have done so you can consider those extra bits when you check the output.
think they're indexing here for professional work (people in the VSCode terminal)
I wonder if this means part of the prompt has been moved to a higher level somehow... or baked into the bread elsewhere.
Small suggestion on refactors into packages: Move the files manually. Just tell codex "they used to be in different locations, fix it up so it builds".
It seems that the concept of file moving isn't something Codex (and other clis) handle well yet. (Same goes for removing. I've ~never seen success in tracking moves and removes in the git commit if I ask for one)
Does refactoring mean moving things around for people? Why don't you use your IDE for this, it already handles fixing imports (or use find-replace) and it's faster and deterministic.
Not necessarily -- in the case I posted about, we first abstracted some common functionality to internal libs, and then further abstracted that functionality into a number of packages (so they could be used by other clients).
So it was part simplification (dedupe+consolidate), and part moving files around.
Codex CLI IDE just works, very impressed with the quality. If you tried it a while back and didn’t like it, try it again via the vscode extension generous usage included with plus.
Ditched my Claude code max sub for the ChatGPT pro $200 plan. So much faster, and not hit any limits yet.
i just use aider + gemini pro, here's the project i developed: https://aretecodex.pages.dev/tools/
Did anybody switch away from Aider for a compelling alternative? What was the feature?
Im using Cursor with the $20 plan and hit rate limits after 15 days (so im paying extra the rest of the month). What do you recommend I do?
You could get two plus accounts? Or maybe a business account with two seats?
The $200 pro feels good value personally.
>CLI IDE
What?
Codex cli Vscode extension https://developers.openai.com/codex/ide
Wait, what? They now allow claude code like subscription instead of the API too?
Yes for at least a month. Download the vscode extension and sign in with ChatGPT
Yes, just do "codex login" and it'll use your ChatGPT subscription.
It's been interesting reading this thread and seeing that others have also switched to using Codex over Claude Code. I kept running into a huge issue with Claude Code creating mock implementations and general fakery when it was overwhelmed. I spent so much time tuning my input prompt just to keep it from making things worse that I eventually switched.
Granted, it's not an apples-to-apples comparison since Codex has the advantage of working in a fully scaffolded codebase where it only has to paint by numbers, but my overall experience has been significantly better since switching.
From my observation of the past 2 weeks is that Claude Code is getting dramatically worse and super low usage quota's while OpenAI Codex is getting great and has a very generous usage quota in comparison.
For people that have not tried it in say ~1 month, give Codex CLI a try.
All that matters to the end users is to never be trapped. Cross-shop these products around constantly and go for lowest price, highest performance ratios. We've seen over the last year all companies trade blows, but none are offering something novel within the current space. There is no reason to "stick to one service". But the services will try very hard to keep you stuck for that SaaS revenue.
Question, how do I get the equivalent of Claude's "normal mode" in Codex CLI?
It is super annoying that it either vibe codes and just edits and use tools, or it has a plan mode, but no in-between where it asks me whether it's fine it does a or b.
I'm not understanding why it lacks such a capability, why in the world would I want to choose between having to copy paste the edits or auto accept them by default...
Usually I give it a prompt that includes telling it to formulate a plan and not not do any coding until I approve. I will usually do several loops of that before I give it the instruction to go forward with the plan. I like to copy and paste the plan elsewhere because at times these LLM's can "forget" the plan. I usually do testing at each major milestone (either handed off to me or do builds/unit tests.)
Yeah, no way I'm doing copy pasting or allowing it to vibe it.
I want it to help me come up with a plan, execute and check and edit every single edit but with the UX offered by claude, Codex is simply atrocious, I regret spending 23 euros on this.
I see the visual studio code extension does offer something like this, but the UX/UI is terrible, doesn't OAI have people testing those things?
The code is unreadable in that small window[1], doesn't show the lines above/below, it doesn't have IDE tooling (can't inspect types e.g.).
https://i.imgur.com/mfPpMlI.png
This is just not good, that's the kind of AI that slows me, doesn't help at all.
Very impressive. I've been working on a shared background presence animation, and have been testing out Claude and Codex. (By shared presence, I mean imagine a page's background changing based on where everyone's cursor is)
Both were struggling yesterday, with Claude being a bit ahead. Their biggest problems came with being "creative" (their solutions were pretty "stock"), and they had trouble making the simulation.
Tried the same problem on Codex today. The design it came up with still felt a bit lackluster, but it did _a lot_ better on the simulation.
I literally tried out Codex for the first time this weekend, and the results were ... weird. It'll be interesting to see if it does things differently. (It was a super simple prompt, standing up a Rails app in Docker Compose with a home page and Devise; it hard-coded each file to create inside of the bootstrap.sh, instead of actually creating the files to begin with)
I bought chatgpt last month and I think that openai is doing things right now, mostly in the experience, for example it has a better voice mode than Claude's and I liked their new model names than the confusing ones they used to have, it simplified the whole thing. Also as a general assistant is better too, for comparison Claude for non code things is not that very good. And openai keep releasing tools and seems more reliable in their tools
Cool upgrade, but I wonder how this plays with existing tools like Copilot and Cursor. Everyone’s moving toward “AI pair programmer in every IDE,” and it feels like the competition is less about raw model quality now and more about integration + workflow lock-in. Codex getting everywhere (terminal, GitHub, phone) sounds powerful
Only an 1.7% upgrade on SWE-Bench compared to GPT-5, but 33.9 vs 51.3% on their internal code refactoring benchmark. This seems like an Opus 4.1-like upgrade, which is nice to see and means they're serious about Codex.
Comment was deleted :(
I've considered swapping to Claude since the last update made talking to gpt absolutely terrible. I heavily make use of being able to put in PRs on mobile by working with codex, and if it wasn't for this I'd probably have switched. Excited to see the updates.
Don't. Claude is worse for everything but coding, and even then it's mostly better for coding in greenfield/small projects, and it makes a mess of large projects. The only thing really good about Claude was the plan economics, and now I'm not so sure about it.
Oh since when Codex cli is now included as part of a ChatGPT plan? 99% sure that wasn't the case before. Time to try to use it for real.
They added that around June 4th, here's the PR: https://github.com/openai/codex/pull/1212
It's relatively new - they enabled it ~1 month ago or something.
The code review thing might be my favorite UX for AI based development. Largely stays out of your way and provides good comments.
I’m imagining if it can navigate the codebase and modify tests - like add new cases or break the tests by changing a few lines. This can actually verify if the tests were doing actual assertions and being useful.
Thorough reviewing like this probably benefits me the most - more than AI assisted development.
Comment was deleted :(
It's interest to see this quote: `for the bottom 10% of user turns sorted by model-generated tokens (including hidden reasoning and final output), GPT‑5-Codex uses 93.7% fewer tokens than GPT‑5`
It sounds like it can make simple tasks much more correct. It's impressive to me. Today coding agent tends to pretend they're working hard by generating lots of unnecessary code. Hope it's true
This is my issue with gpt-5. If you use the low or medium reasoning it’s garbage. If you use high, it’ll think for up to five minutes on something dead simple.
Can you be more specific about what type of code you're talking about, and what makes it garbage?
I'm happy with medium reasoning. My projects have been in Go, Typescript, React Dockerfiles stuff like that. The code almost always works, it's usually not "Clean code" though.
Do they have a GitHub action to run in GitHub, similar to Claude?
I just want the codex models in the API, I won’t touch them until then.
And before someone says it, I do happen to have my own codex like environment complete with development containers, browser, github integration, etc.
And I'm happy to pay a mint for access to the best models.
They've said it's coming:
>For developers using Codex CLI via API key, we plan to make GPT‑5-Codex available in the API soon.
I saw that, but soon doesn’t inspire confidence, and is easy to overlook if they don’t. They didn’t with the previous Codex model.
Comment was deleted :(
OpenAI is starting its new era of specialized models. Guess they gave up on a monolithic model approach
If you try to optimize for everything you get a model that's good at nothing (or hyper expensive to train and run). Simple economics. There is no free lunch.
One major improvement I have seen today, even before I saw the announcement, was that the model is far more reliable in using the Task Completion interface to communicate what stage of the prompt is being implemented. Previously this was only shown sparingly (especially in the first few weeks) and if, it didn't properly tick tasks, simply jumping from the first to completion at the end. Now this works very reliably and I do like this improvement, but if I didn't know better, would have suspected this was merely the result of a system prompt change, considering GPT-5 adherence being very solid in my experience, this should have been fixable without a tuned model. Nevertheless, I like this improvement (arguably fix of a previously broken feature).
Beyond that, purely anecdotal and subjective, but this model does seem to do extensive refactors with semi precise step-by-step guidance a bit faster (comparing GPT-5 Thinking (Medium) and GPT-5 Codex (Medium)), though adherence to prompts seems roughly equivalent between the two as of now. In any case, I really feel they should consider a more nuanced naming convention.
New Claude Sonnet 3.7 was a bit of a blunder, but overall, Anthropic has their marketing in tight order compared to OpenAI. Claude Code, Sonnet, Opus, those are great, clear differentiating names.
Codex meanwhile can mean anything from a service for code reviews with Github integration to a series of dedicated models going back to 2021.
Also, while I do enjoy the ChatGPT app integration for quick on-the-go work made easier with a Clicks keyboard, I am getting more annoyed by the drift between Codex VSCode, Codex Website and Codex in the ChatGPT mobile app. The Website has a very helpful Ask button, which can also be used to launch subtasks via prompts written by the model, but such a button is not present in the VSCode plugin, despite subtasks being something you can launch from the VSCode plugin if you have used Ask via the website first. Meanwhile, the iOS app has no Ask button and no sub task support and neither the app, nor VSCode plugin show remote work done beyond abbreviations, whereas the web page does show everything. Then there are the differences between local and remote via VSCode and the CLI, ... To people not using Codex, this must sound insane and barely understandable, but it seems that is the outcome of spreading yourself across so many fields. CLI, dedicated models, VSCode plugin, mobile app, code review, web page, some like Anthropic only work on one or two, others like Augment three, but no one else does that much, for better and worse.
I like using Codex, but it is a mess with such massive potential that needs a dedicated team lead whose only focus is to untangle this mess, before adding more features. Alternatively, maybe interview a few power user on their actual day to day experience, those that aren't just in one, but are using multiple or all parts of Codex. There is a lot of insight to be gained from someone who has an overview off the entire product stack, I think. Sending out a questionnaire to top users would be a good start, I'd definitely answer.
Wait. There's Codex support in the mobile app? But on iOS only?
Ffs...
is this model just super slow to anyone else?
Extremely slow for me - takes minutes to get anything done. Regular GPT5 was much faster. Hoping it’s mostly due to the launch day.
I've been using gpt-5 on effort=high but for gpt-5-codex, try: `-c model_reasoning_effort=medium`.
On high it is totally unusable.
Doesn't seem ready for prime-time. I'll be impressed when it actually installs.
npm ERR! code 1 npm ERR! path /usr/local/lib/node_modules/@openai/codex/node_modules/@vscode/ripgrep npm ERR! command failed npm ERR! command sh -c node ./lib/postinstall.js npm ERR! /usr/local/lib/node_modules/@openai/codex/node_modules/@vscode/ripgrep/lib/download.js:199 npm ERR! zipFile?.close();
codex cli has been out for 5 months with 170k weekly downloads - it's definitely 'ready for primetime' if you can get past your bug. I don't have that issue.
Agent-1
Has anyone hit any programming usage limits with the ChatGPT 5 Pro account?
None yet, feels unlimited. Huge repos too
Still waiting on codex cli to support lm studio.
? Isn't lmstudio API openai compatible? Codex cli already supports 3rd party models, you have to edit the config yaml file, and you can add many model providers.
I never managed to get it to work. I used chatgpt to try to do it for me :)
Is so good that need advertising, LOL. (Anthropic enters chat)... Jokes apart, I guess it is good (cause I cant afford it to try). (Meta enters chat)... Deepseek R2 enters chat and drop mike. Anthtopic, Meta, OpenAi, Google, leaves chat and call Trump for another Dinner.
No really Jokes apart, ChatGPT and Trump are awesome, all works and keeps getting better by the day.
I agree because I don’t want to get fired or get audited
Take off the guardrails and let humanity thrive.
It is inevitable.
Crafted by Rajat
Source Code