they're not near opus at all, anyone using the models in a real working environment will tell you the same thing. on paper they have impressive benchmarks, but that's not realistic to actual use.

I think it depends on your use case. For my personal projects (a mix of webdev & some Rust desktop apps) it's honestly very close to Opus 4.8 (which I use in my day job).

I don't feel like I'm missing out after cancelling my personal Claude subscription, whereas I used to feel that way a few months ago.

I've been using GLM 5.2 a lot this past week, it's been replacing Opus 4.8. I mostly do front-end web development and haven't noticed much of a quality difference.

Sure, "it's just frontend", but that's actual use enough for me to take it seriously.