[MiSeRyDeee]

Kudos to them then, for doing such a good job at distillation. Only 16 million chats(shared by multiple labs/models) needed for distillation for getting mostly on par performance at 1/10th - 1/50th cost, keep up keeping up!

[icedchai]

The output quality of open models still has a long way to go... I've experimented with many of them, through services like openrouter and on my own hardware.

[culi]

Try Kimi 2.5

[icedchai]

I have (through openrouter.) It didn't change my opinion.