If I wanted to switch from Claude Code to this - what openai model is comparable to opus 4.6? And is it the same speed or slower/faster? Thank you!
back
3 comments
GPT 5.4 has been the winner this week. Last week Opus 4.6. You can use both in OpenCode.
5.4 kind of falls apart in big/large projects.
How does it compare to using GPT 5.4 inside Codex?
I used Codex for a long time. It's definitely better than Claude Code due to being open source, but opencode is nicer to use. Good hotkeys, plan/build modes, fast and easy model switching, good mcp support. Supports skills, is not the fastest but good enough.
Well not anymore with Claude pro…
It is "not supported" for two month at this point, yet somehow opencode + claude max is still my main workflow today
If you want faster, anything running on a Cerebras machine will do.
Never tried it for much coding though.
Outside of their (hard to buy) GLM 4.7 coding plans, it's also extremely expensive.
do you care about harness benchmarks or no?
Just a data point, I would need to use it for my workflows. I do have a monorepo with a root level claude.md, and project level claude.md files for backend/frontend.
thats not at all the question i asked