Comment by kennywinker
8 hours ago
Does that not prove my point? Bigger doesn’t automatically mean better. Quality of training data, and model structure, matters as much or more than size
8 hours ago
Does that not prove my point? Bigger doesn’t automatically mean better. Quality of training data, and model structure, matters as much or more than size
Ah 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
Thanks! That's very helpful as a way to discuss.
First off, I'd include Qwen flash-next and GLM 5.3 to show some of the other strong open weight models, and they predictably dominate it, but they're much larger. But, it shows up right next to DSv4 Flash 0731 on the overall index, and that's much larger. It's a great model! But then scroll down and hit Time Per Task, and you'll see that DSv4 Flash takes 3.6 seconds per task to Qwen's 21.1. That's what I meant when I said this:
>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.
It can make up for its shortcomings by iterating a lot longer, and using way more thinking tokens. And that's a great trade if you don't have the vram to run the bigger models, but speed is pretty important for getting things done... And that's why DSv4Flash is great, too, despite being much larger, and scoring similarly on the intelligence index.
2 replies →