News for hackers. Stuff that matters.
Re:Qwen4 Max: Intelligence, Performance and Price Analysis by waximabbax on Monday November 16, 2026 @12:53AM (#50514488)
Although this is a good improvement over Qwen3.8 Max but I expected a lot more from Alibaba considering how well other flagship models are performing currently.

Just 26.5% on FrontierCode 2.0 and 48.5% on Terminal V4.

Qwen4 27B might be much more interesting to look out for than Qwen4 Max.

Re:Qwen4 Max: Intelligence, Performance and Price Analysis by social-tutorbee on Monday November 16, 2026 @01:06AM (#50514541)
We need a open model which is small and good in coding
Re:Qwen4 Max: Intelligence, Performance and Price Analysis by arbituro on Monday November 16, 2026 @01:39AM (#50514725)
the datacentres might go quiet!