Yep, I think next month will be on that. It feels slightly better from a few days of use, and in our WIP benchmarking it scores way higher

Ill tell you from my personal use glm 5.3 flash was better then deepseek 4.1 flash, also deepseek liked to yap in his reasoning traces soo fucking much, the yapping was fast but the task was so slow to complete...

DS v4.1 Flash is roughly equivalent. It's going to get some things right/better that GLM flash doesnt and vice versa.

They've got an image of their homegrown benchmark in the post that lists DS4.1.