Reaction
Open models, Grok 4.7 and Muse reportedly fell in Artificial Analysis re-rankings
One user jokes it’s a terrible day for people who say open-weight models are as good as Opus 5.5.
TLDR
A post describes AI models re-ranking step by step from Artificial Analysis v4.3.2 to v5. One user jokes that the shift is bad news for claims that open-weight models match Opus 5.5. Another says open models fell a lot, but finds it funny that Grok 4.7 and Muse fell a lot too.
Combined views
285
2 Sources, first seen ago
