Thread

1. dom96 · 1790062122 · focus · HN ↗

   It is an impressive model. Agreed on most that is written on this page, with the exception of it being fast. I ran it on my own LLM benchmark suite[1] and it is faster than DeepSeek but still much slower than leading models. But it's pricing is where it really shines.

   KillSwitch-Bench 1.0

     Claude Opus 5           66.9
     GPT-6 Astra             57.9
     Claude Fable 5.1        46.7
     MiMo-V2.6-Pro           38.8
     Muse Spark 1.3          36.5
   

   1 - <a href="https:&#x2F;&#x2F;bench.killswitch-lang.org&#x2F;" rel="nofollow">https:&#x2F;&#x2F;bench.killswitch-lang.org&#x2F;

   1. ricardobeat · 1790074378 · focus · HN ↗

      Speed seems to vary a lot with demand. Last night it was reaching 80+ tok&#x2F;s

Unofficial Hacker News client; not affiliated with Y Combinator.