← Back to context

Comment by khazhoux

10 days ago

Well, I've got it as Auto (configured by my company and I forget to change it). The list of enabled models includes claude-4.6-opus-high, claude-4.5-sonnet, gpt-5.3-codex, and a couple more.

That is probably Composer-1, which is their in-house model (in so much a fine-tune of an open-weights model can be called in-house). It's competent at grunt work, but it doesn't compare to the best of Claude and Codex; give those a shot sometime.

Auto is not likely to choose the high quality models unless you really try for complex plans. Give the explicit models a try instead. It really makes a difference.