Obvious political reasons and implications aside, a clear quality gap opened up late last year when Opus 4.5 was released vs. GPT-5. Opus was obviously and demonstrably superior to any GPT-5 tier. The release of GPT-5.2 didn't improve matters, and then Opus 4.6 widened the gap further. Right now talking to GPT-5.2 Pro is 10x slower than chatting with Opus 4.6 and the output returned is, nevertheless, generally lower quality and more "sloppy."
What I'm getting at is that this could be, in part, because Claude is genuinely better at this point in time.
Weirdly enough, I agree with both sides. Opus beats every version of GPT 5 as a chat interface, hands down. ChatGPT, at this point, is mostly me correcting its output style, cadence, behavior, etc, and consistently remaining dissatisfied, meanwhile Opus one-shots things I didn’t even think it could (Typst code).
All that said, I do my programming in OpenAI’s Codex app for Mac. It has completely dominated Claude Code for me. I’ll only ever use Opus to check 5.3-Codex’s work.
Very weird world we’re living in. I hope it gets even weirder once Deepseek does whatever they’ve been cooking.
whatever they've been cooking at deepseek, i don't think i'm going to let their coding agent run shell stuff on my computer unless they make it free or something
Something very weird is going on; I just tried a free trial of Codex-5.3, and a significant fraction of what it gives me doesn't even compile (or in the case of python, run without crashing).
Unless I specifically say "use git", it won't bother using git, apparently saying "configure AGENTS.md to us best practices" isn't enough for it to (at least in this case) use git. If this was isolated I might put that down to bad luck, given the nature of LLMs, but I have been finding Codex uses the wrong approaches all over the place, also stops in the middle of tasks, skips some tasks entirely (sometimes while marking them as done, other times it just doesn't get around to it).
I'd rank the output of Claude as similar to a junior with 1-3 years experience. It's not great, but it's certainly serviceable, a bit of tweaking even shippable. Codex… what I see is more like a student project. Or perhaps someone in the first month of their first job. Even the absolute worst human developers I've worked with after university weren't as bad as Codex, but several of them I'd rank worse than Claude.
I have not observed meaningful quality differences between the default (medium) and extra high. What does make a difference is to turn the metaphorical lights back on, and instead of vibe-coding (as in, don't even look at the code) actually examine what it did at each step (either at code level or QA) before allowing it to proceed to the next step.
OpenAI's 5.3 Codex model on xhigh still makes a huge number of mistakes, somewhere between 25-50% of commits, and it's still terrible at making its own plan, estimating how long tasks will take to complete, and recognising which tasks need to be subdivided*. Claude's model last November was better on both counts, even though it still wasn't IMO ready for true lights-off-no-code-check-needed-vibe-coding, it was making mistakes far less often and was scoping task complexity appropriately.
That said, given xhigh seems to be going through my token allowance far, far slower than on medium, I wouldn't be surprised if it turns out the Codex app itself is vibe coded and has mis-mapped that setting in some weird way. Either that or they've suddenly got a lot more spare capacity because of the boycotts.
* given the METR study, in the planning phase I ask all these models (Codex and Claude) to break down tasks into things that would take a junior developer 1-2 hours, but Codex will estimate 60 minutes for everything from "write 19 lines including comments to stub 3 empty methods in new class" to tasks I'd expect to take a senior 2 days.
What where you using it for? claude is really good at agentic stuff, Pure coding, I can see codex being better, but for the entire workflow, I'm not sure
I use Codex purely for coding, and that's 90% of my use case for AI in general (10% using ChatGPT web for misc stuff). I pop out to Opus in Claude Code regularly to try to stay up on their relative performance, but so far the primary value I've been able to derive from CC is as a second set of eyes for code review / poking holes in plans. For primary planning / debugging / implementation Codex outclasses it atm sadly.
Me too. It's great that my employer pays for it and there's basically no budget, because this configuration is 10x more expensive than the regular default Sonnet.
Yep. For the past month I’ve been doing this thing where every time I need something from AI, I give Opus and Codex the same prompt. Opus is just better by a wide margin, especially on complex tasks. It uses tools quite a lot, taps into available MCP servers when it makes sense, and can think about repercussions down the line much better. Codex I feel is optimized for brevity, approaching terseness. Hard to put my finger on it but it’s never as thorough and it always misses important details.
Agree on the gap - in my own complex greenfield software dev spec test, opus 4.6 blows codex 5.3 out of the water, by wide margin, both in ui and backend.
Massivly better and I cannot understand how many comments online say that they're comparable (other than paid actors which now fits the right wing angle that OpenAI takes because right wing paid online comments seems quite common overall).
I remember on the Opus 4.5 release data watching what it can do to my test app I wanted it to build and saying outloud to myself "oh shit" because of how much better it was at the conversation, planning, understanding, and building. Posts like this[0] say similar things, where Opus 4.5 release + Claude Code was the tipping point and the gap is widening and Anthropic has infinite more momentum and going in the better direction with useful models that aren't fully aligned with bad actors.
no, it is because of the public perspection of Anthropic holding a principled stance against allowing their software to pull the trigger and kill humans. ChatGPT still has the bigger brand name recognition.
Anyone who's used both Claude and ChatGPT will instantly agree what is better by a large margin. Theres maybe a brand recognition long tail but its more likely theyre the rare occasional users who use the free tier. Thus ChatGPT is becoming the shitty free AI app while Claude is what you use to get real work done. Time (in months) will tell yow this will go.
If that's entirely the case, there could still be interesting implications, as people who switch to Claude are unlikely to switch back to ChatGPT in the near future. (If, that is, they regularly use LLMs for any technical or professional task.)
What I'm getting at is that this could be, in part, because Claude is genuinely better at this point in time.