Not really, GLM uses more tokens to get work done.
By how much? At least TFA provided numbers for one example, and they disagree with you (by a lot).
I ran a fairly large experiment last week, and the token usage wasn't bad at all. What softs of use cases are you seeing large token usage by GLM 5.2?
By how much? At least TFA provided numbers for one example, and they disagree with you (by a lot).