I find 4.6 pretty noticeable upgrade, but it might be the 1M context. I'm interested in how the 1M context works out with Qwen.

From Qwen-3-max thinking, I remember the inference becoming veeery slow as you pushed towards 1M context, already at 300k tokens you would notice the degradation. But of course, I was using Qwen Chat, so could be a resource allocation thing.

I found it worse, in a very clear way.