Beat Simon Willison ;)

https://www.svgviewer.dev/s/gAa69yQd

Not the best pelican compared to gemini 3.1 pro, but I am sure with coding or excel does remarkably better given those are part of its measured benchmarks.

▲

GaggiX 5 hours ago | parent [-]

This pelican is actually bad, did you use xhigh?

▲

nickandbro 5 hours ago | parent [-]

yep, just double checked used gpt-5.4 xhigh. Though had to select it in codex as don't have access to it on the chatgpt app or web version yet. It's possible that whatever code harness codex uses, messed with it.

	▲	nubg 4 hours ago \| parent [-]
		this is proof they are not benchmaxxing the pelican's :-)