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.
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.
This pelican is actually bad, did you use xhigh?
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.
this is proof they are not benchmaxxing the pelican's :-)