DeepSeek hasn't been SotA in at least 12 calendar months, which might as well be a decade in LLM years
What about Kimi and GLM?
These are well behind the general state of the art (1yr or so), though they're arguably the best openly-available models.
According to artificial analysis ranking, GLM-5 is at #4 after Claude Opus 4.5, GPT-5.2-xhigh and Claude Opus 4.6 .
Idk man, GLM 5 in my tests matches opus 4.5 which is what, two months old?
4.5 was never sota
What about Kimi and GLM?
These are well behind the general state of the art (1yr or so), though they're arguably the best openly-available models.
According to artificial analysis ranking, GLM-5 is at #4 after Claude Opus 4.5, GPT-5.2-xhigh and Claude Opus 4.6 .
Idk man, GLM 5 in my tests matches opus 4.5 which is what, two months old?
4.5 was never sota