Original Summary

This is something I&#x27;ve been playing with for the last couple days - an app I vibecoded to arrange oneshot LLM visual benchmarks without the need to write any code. I do it form my phone so the excellence of mobile UI is high in the priority list.<p>It is inspired by Simon Willison&#x27;s benchmark writeups[0], basically you can recreate them in one go.<p>Besides text and images, it supports SVG outputs and whole static websites, which is where benchmarks get the most interesting.<p>Additionally, I added the ability to alter chat history for the chat completion API, which I think is useful for model red teaming (or if you just want to see how different models apologize) - but I haven&#x27;t found any impressive uses of that feature yet.<p>This thing helped me improve my intuition on different SOTA models&#x27; strengths and weaknesses; check out the various examples on the website, and feel free to create your own<p>[0] <a href="https:&#x2F;&#x2F;simonwillison.net&#x2F;tags&#x2F;svg&#x2F;" rel="nofollow">https:&#x2F;&#x2F;simonwillison.net&#x2F;tags&#x2F;svg&#x2F;</a>

  • 情报分类：商业与市场研究
  • 分类依据：内容涉及商业、投资或市场动态
  • 信息来源：Hacker News 新项目
  • 发布时间：2026/10/16 21:26:03