Many users are excited about GLM-5.2 for substantially outperforming K2.7 on benchmarks, calling it a legit step up that now serves as their daily driver for coding and content tasks.
No Digg Deeper questions have been answered for this story yet.
Most Activity
after spending a ton of time with GLM5.2 today in order to add it to noumena, i have to say i am very impressed. if it keeps this up, it could replace k2.7 as my daily driver beside gpt 5.5 . very impressive work @Zai_org !
... soon ...
ok thats it, im deploying glm5.2 on the noumena platform
@_xjdr Did you ever try Xiaomi MiMo V2.5 Pro?
@_xjdr Yeah between it and Kimi GLM is my first target for an idea while I get Kimi going elsewhere. Excited to see your thoughts
@_xjdr @Zai_org i think it's a legit step up. had a rig dialled in for k2.7 so wasn't planning on switching but after one 'have a look around' was floored and never looked back.
fable class by eoy
@_xjdr @Zai_org Ooooooo
@_xjdr yes!! top of the list for me
@_xjdr @Zai_org On my personal long context coding benches that are not yet trained on, glm substantially beats k2.7
@_xjdr @Zai_org i can finally have an opinion on this model, thank u i will see u again when i need to form my next opinion
@_xjdr @Zai_org it is my daily driver now. I started making youtube shorts with it(plus my own workflow). It is good(though no engagement so far). Example(completely made with GLM 5.2) -
https://youtube.com/shorts/ontFE9wvX_U?feature=share
@_xjdr @Zai_org sounds like a solid contender, exciting developments ahead!