Y
Hacker News
new
|
ask
|
show
|
jobs
by
riknos314
1 day ago
Qwen 3.5 27B also scores higher than 3.5 122BA10B. So even in the same generation the smaller dense model outperformed the larger MOE
2 comments
riknos314
1 day ago
https://artificialanalysis.ai/evaluations/artificial-analysi...
link
apitman
18 hours ago
Ah gotcha, I hadn't noticed that. Thanks
link