codex is good, both cli and desktop app, you get lots of usage on any plan. sol is good! and gets the job done, write or dictate a very long and thoughtful prompt, and leave sol xhigh or max fast working on it for an hour or so
omp is an amazing harness, any feature claude code or codex is adding has likely already been here for a couple months. good harness which im suggesting to all my developer friends, but for everyone else codex is the better option due to its simplicity and being the plug and play option
claude is decent, but not great. all models are somehow getting restrictive. you get basically unlimited opus on max plans, fable is good but slow and the random guardrails suck soo much which is why i havent used it once in weeks now.
gemini 3.7 is great for speed. everyone is sleeping on it, including even me
kimi k3 - great for frontend, one of the few models thats willing to commit crimes for you AND has the intelligence to have a chance at actually succeeding;
ds pro and flash are fast but not something id actually use for important things, unlike sol, fable and maybe 3.7 here and there
glm 5.3 i haven't tested yet
honorable mention to local models which are actually getting good now! 5090s will continue to get more and more expensive in the coming months. sadly.
theres way way more than claude in this world and its taking people surprisingly long to figure that out. maybe its for the best!
With Opus 5.0 being kinda crappy vs 4.8, I think Anthropic is in trouble.
I mostly do very obsessive, tightly scoped, carefully thought out small changes on a fairly boring stack, one interaction at a time, verifying functionality and code. I know what I am doing, but I also know what I don’t like doing (the same exact set of things I’ve already done a dozen times in my career)
I do agree claude looks for more things to do in your repo, whereas codex is more likely to do what its old and stop. Which is better is personal preference as far as I can tell.
Why is fewer comments a good thing?
One thing I don’t love about codex/sol is I find it tends to overengineer and be overly cautious.
I was using it to do create some scraping + data processing.
It went kind of crazy on the provenance, need at least 3 sources of consensus before promoting facts type bullshit.
defined a bunch of enums and gates.
I just wanted scrape some site data and put it into a SQLite dB. Like chill codex.
I feel like Claude is better at that.
It felt like it was commenting on the diff sometimes instead of what the code was doing.
Useful for the LLM to know the "why", but not something a human would do, unless it's a very critical and confusing part of the code.
You'll ask it to do something and it'll comment the code with an answer to what you asked it, rather than just explanatory comments to whoever comes after.
There's also a second issue that if the code is actually incorrect, the comment can nevertheless bolster the case for it.
I feel like codex/sol is better at well scoped hard technical problem.
Where it can sort of run this brute force analytical loop.
Like doing performance optimization or other search type problems. I think the math proofs are good examples of this.
Not to Claude – its own, old comments have helped me/it solve new issues on more than one occasion.
It writes out stories describing what isn't there or what used to be there. It's usually not helpful, just noise. It also likes to write it in very verbose AI-styled prose.
Some quick and very personal impressions from using Codex more than Claude this week (I will do a full analysis during the weekend hopefully).
(1) While I tried this year to keep Claude and Codex on par, having the same set of plugins/skills and so on, Claude had more skills, as I created skills out of some sessions and not all of them were ported to Codex. Fix for this is simple: Point Codex at the Claude skills folder and ask it to transform them for Claude
(2) When I was in a rush (like debugging something that felt urgent), I still opened Claude as somehow I felt more at home with it. I am not saying it was better, but it was familiar, and when debugging, using tools that I know is important.
(3) Changes created by Codex had fewer comments in Ruby/Ruby on Rails code. I liked that a lot, and I will soon share some experiments I ran on this.
(4) The output of the Codex agent harness is much more “technical” than the one from Claude. Claude feels more like your colleague in a Tuple session writing to you while Codex feels more like a version of Data from Star Trek.
(5) I want to open many more sessions of Codex and keep them focused instead of a big session of Claude as I was doing before. This may not be specific to Codex, but I noticed it while working with Codex.
(6) It feels to me that Codex does changes faster than Claude. But after making the main changes, it took a lot to finish the pull request: rerunning many tests, review, and so on. I like the thoroughness of this, but in the end, there was no win in terms of time difference.
(7) It felt to me that Codex created a much simpler solution in terms of code architecture than Claude. Claude usually goes on to create a lot of things: abstractions, concepts, Sorbet signatures, type aliases, and so on. Codex was a bit more contained and created less. This week I also tested an improved flow of code research -> design change -> review change -> implement -> verify. But I made both of them implement the same requirement using the same documents, and Claude’s code was a bit more complex but handled cases.
(8) Codex also made some mistakes. Claude could understand my intention to branch out from other work and keep them in sync. Codex did some nasty things like branch A targets branch B that targets main, and when I asked it to rebase, it rebased with main, which created some PR with 4000+ additions. I had to be explicit and ask it to rebase only with the target.
(9) For Codex, working with Jira and Atlassian was a hassle in my environment where I use the CLI tool and not the MCP. It opened JIRA to prompt me to log in, then switched to the CLI, then back to the browser. In this case, Claude was much more eager to try to get what I want and to do it the way I want it done, based on previous sessions.
(10) Working with MCPs, I like the Codex CLI approach more, where it asks me to execute codex mcp login and every time it opens the right authentication and authorization flow. Claude sometimes tries to run it automatically in a turn, and it can get stuck.
I think the main difference I feel between Claude and Codex is that Claude tries to go above and beyond what is asked and guess what you might want and then directly do it, while Codex is more like a companion that does what you tell it but will not overdo it. It will stop at the first sign that it might be done.