Have you ever used an open model for a bit? I am not saying they are not benchma... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		meffmadd 7 days ago \| parent \| context \| favorite \| on: Qwen3.5: Towards Native Multimodal Agents Have you ever used an open model for a bit? I am not saying they are not benchmaxxing but they really do work well and are only getting better.

		help

Aurornis 7 days ago [–]

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.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact