alt Hacker NewsAh sorry, I should've continued, the bigger recent models are commensurately smarter. If you really want to make the point, then you'd need to show 27b being smarter than similar vintage bigger models. And in that case, there's confounding issues like efficiency, speed due to excessive thinking maybe to make up for the smaller amount of world knowledge baked in (qwen 27b's main issue iirc), etc - they're tuned for different things.
https://artificialanalysis.ai/?models=gpt-5-3-codex%2Cqwen3-...
Shows qwen3.8-27b along side seven larger models of ~similar vintage. Only one scores above 27b.
Many of those are closed models so idk their exact parameter count / active param count, but it hardly matters - i’m sure all of them are far above 100b params
My point is not that bigger is pointless. It’s just clearly not the only road to take to make a model better, which is obvious just from seeing how models of the same size have gotten better over the past few years