Well yeah, it is just better. At my work we have a copilot license, but we use it to access Claude Sonnet/Opus model in OpenCode.
The Copilot-Cli is not so bad, https://github.com/features/copilot/cli
I'm amazed that a company that's supposedly one of the big AI stocks seemingly won't spare a single QA position for a major development tool. It really validates Claude's CLI-first approach.