Then what is Astra high-extra high-Ultra? That’s effort within each tier?

dyauspitr • yesterday at 6:24 PM • 2 replies • view on HN

Readerium • yesterday at 6:35 PM

Yes that is number of reasoning tokens used.

Performance increases both with larger model (Luna vs Sol)

And with more reasoning (low vs xhigh)

MaKey • yesterday at 6:32 PM

Exactly

alt Hacker News