News for hackers. Stuff that matters.
Re:Qwen3.5: Towards Native Multimodal Agents by Aurornis on Monday February 16, 2026 @10:41AM (#47036390)
I have used a lot of them. They’re impressive for open weights, but the benchmaxxing becomes obvious. They don’t compare to the frontier models (yet) even when the benchmarks show them coming close.

There are no comments on this comment yet.