Everyone benchmarks GLM-5.2 against the frontier now. So we did too.
We pulled GLM-5.2's plan up against Claude Fable 5's, the plan that won our last frontier round. Same prompt, same task, same rubric.
Fable scored 9.1. GLM-5.2 scored 9.0.
omggg i made a joke about only 25 people using arch and all the fucking arch nerds appeared like UHMM ERRM SCHMELLY, ID LIKE TO INTERJECT FOR A MOMENT ,,, ASHCTULALY ARCH IS P POPULAR AND ITS USED FOR STEAM AND
holy cannoli bro, shut uppppp. its a joke. fucking hell
Let me get this straight. PM Starmer, who is about to be ousted due to Epstein stuff, decides for his legacy, he must "protect the children" by requiring ID to use the internet in the UK? Let's just be clear, there's no such thing as age verification for children only.
@TwittConta@Cherryiscoolbro here's a better look at it. peach, yoshi, luigi were taken from mk64, and mario and bowser are from sm64
https://t.co/ITYRJDj5cx
@KarolinaTone@Cherryiscoolbro yep, that still works. you can also hang out in the area where ganon kneels down when spying on him through the window
this is the only solid piece of ground beyond the main room. the mario paintings room and the room across from it are just invisible water