Re:Qwen4-Max
by small_model on Monday November 16, 2026 @05:17AM
(#50515985)
Only 43 on AA, no where near the frontier now, looks like distillation blocking has halted their progress.
[ Parent
| on HN ]
Re:Qwen4-Max
by testtestmetest on Monday November 16, 2026 @05:34AM
(#50516088)
I love how Americans are so brainwashed to think the Chinese can't innovate without cheating, while they lap us in basically every category possible except this one verticle, that we had a 3-4 year head start on.
I partially wonder if the Chinese would even release a model that flat out beats Claude/fable I say this half jokingly...
but I imagine there's part of them that goes "These Americans are so delusional about how language models are dangerous/existential threats that they might kill us or hurt our economy over a chat bot"
China is not better than America on any metric.
Okay, they have way better public transportation.
And they have a way better power grid.
And they are moving much faster on the robotics side.
And their EVs are killing every other nation’s EVs.
And they are making available LLMs that are very efficient and cost pennies to use.
But, other than that, they cannot operate on their own.
Re:Qwen4-Max
by kylehotchkiss on Monday November 16, 2026 @12:41PM
(#50520353)
> You do not a mega super PhD assitant to build your 4 MAU SaaS app.
lol
Re:Qwen4-Max
by fancyfredbot on Monday November 16, 2026 @06:42AM
(#50516501)
Progress has not halted. On terminal bench 4, for example, score improved from 38.9 to 48.5.