Depends how you define "better". Quality/breadth of tasks/capabilities? Probably not (TBD how gpt5 will fare, colleagues were saying that it was better at some frontend tasks than claude4 in the alpha/beta horizon tests).

But if you take speed/availability/cost into account, there might be "better" offers out there. I did some tests w/ windsurf when they announced their swe1 and swe1-lite models, and the -lite could handle easy tasks pretty well. I also tested 4.1-mini and 4.1-nano. There are tasks that I could see them handle reliably enough to make sense (and they're fast, cheap and don't throttle you).

You can already use non-Anthropic models with Claude Code with tools like Claude Code Router [1].

[1]: https://github.com/musistudio/claude-code-router

No