I evaluated GLM 5.2 against the frontier on tasks from real repos
1–3 of 3 posts
Re: I evaluated GLM 5.2 against the frontier on tasks from real repos
#2Why did you use GLM 5.2 on medium when you used all the other models on high or xhigh?
Re: I evaluated GLM 5.2 against the frontier on tasks from real repos
#3Why did you use GLM 5.2 on medium when you used all the other models on high or xhigh?
What does that even map to? On the official GLM 5.2 blog it is none, high and max.