‹ BackHN Continuity

Thread

Qwen3.8 Max now ranked as the best overall model by agentic index

403 points · 261 comments · apitman

  1. drnick1 · · focus · HN ↗
    Why does an open weights model cost nearly the same as GPT5.6? $1.14 vs $1.23 on the cost index. Since you can't presumably run this on your own hardware given the model size and hence gain other things like privacy, I don't see any reason to move away from GPT at this rate.
    1. apitman · · focus · HN ↗
      For one thing, providers of open models can't arbitrarily increase their prices without facing competition.
      1. frereubu · · focus · HN ↗
        But given the extremely low cost of switching, why wouldn't you use the cheaper one if they're comparable?
        1. apitman · · focus · HN ↗
          As low as it is, switching between providers on OpenRouter is still lower.

          That said, it&#x27;s a fair point. For me, it boils down to things covered here: <a href="https:&#x2F;&#x2F;earendil.com&#x2F;posts&#x2F;session-portability&#x2F;" rel="nofollow">https:&#x2F;&#x2F;earendil.com&#x2F;posts&#x2F;session-portability&#x2F;

          Things like obscured reasoning traces.

Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.