‹ BackHN Continuity

Thread

Pareto Front

198 points · 85 comments · binyu

  1. denismenace · · focus · HN ↗
    I'm assuming you must have discovered this through the OpenRouter LLM performance graphs.
    1. miyuru · · focus · HN ↗
      artificialanalysis for me.

      <a href="https:&#x2F;&#x2F;artificialanalysis.ai&#x2F;#intelligence-comparison-tabs" rel="nofollow">https:&#x2F;&#x2F;artificialanalysis.ai&#x2F;#intelligence-comparison-tabs

      1. trash_cat · · focus · HN ↗
        I think the one from hugging face is much clearer, albeit its an arena metric and a bit tricky to find the pareto view. Look for the the top Navigation Bar (Agent Chat Code Image Video). Chat -&gt; (dropdown) Text -&gt; (Side panel) View as Pareto.

        <a href="https:&#x2F;&#x2F;huggingface.co&#x2F;spaces&#x2F;lmarena-ai&#x2F;arena-leaderboard" rel="nofollow">https:&#x2F;&#x2F;huggingface.co&#x2F;spaces&#x2F;lmarena-ai&#x2F;arena-leaderboard

    2. Aachen · · focus · HN ↗
      First mention in chats for me was September 2016. Not sure how that topic came up but LLMs aren&#x27;t the only way to get there. It&#x27;s also a rather obvious principle to come up with, at least I&#x27;m pretty sure I was doing it without thinking I should name the concept of picking the option that best fits your requirements
Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.