logoalt Hacker News

simonw • yesterday at 6:20 PM • 6 replies • view on HN

> The benchmark is saturated. Frontier models are tested with an armadillo in fishnet tights jaywalking on Mars.

OK well I couldn't resist this one:

  llm -m claude-opus-5.5 'Generate an SVG of an armadillo in fishnet tights jaywalking on Mars'
  llm -m gpt-6.1-sol 'Generate an SVG of an armadillo in fishnet tights jaywalking on Mars'
  llm -m gemini-3.8-flash 'Generate an SVG of an armadillo in fishnet tights jaywalking on Mars'
  llm -m mistral/mistral-large-4 'Generate an SVG of an armadillo in fishnet tights jaywalking on Mars'
Default reasoning levels for each: https://tools.simonwillison.net/markdown-svg-renderer?url=ht...

Replies

monstertank • today at 3:47 AM

I absolutely love that Claude and Gemini seem to have a sense of humor about it.

flowardnut • yesterday at 6:27 PM

The rover honking is pretty silly, opus has a good sense of humor

viraptor • yesterday at 7:23 PM

I'm getting 403 inside the tool for this one. (The pelican bike on top works) This has been happening a lot recently.

➕ show 1 reply
largbae • yesterday at 6:58 PM

Gemini wins this one clearly. Honey please!

xmcp123 • yesterday at 9:19 PM

Big L for mistral in this benchmark. Sorry Europe.

➕ show 2 replies
knowaveragejoe • today at 3:42 AM

Honestly they're all pretty impressive!