I got a 3D pelican out of Blender and Astra a few weeks ago: https://simonwillison.net/2026/Sep/5/blender-coding-agents-m...

I've not committed to that as a benchmark yet because you really need a full coding agent configured to run Blender, and I like benchmarks I can run as a single prompt/response through the appropriate API.

I have been intending to get more of a coding agent benchmark going though, so maybe this should be part of it.

Well, how about this one... Opus 5.5 wrote a raytracer, IK animation, and pelican riding a bicycle for a novel VM with new instruction set and micro-GPU instruction set (DB32), in 4kb! https://demobench.janekm.com/studio?demo=pelican

Not sure if it is the same thing they're referring, but the transition from loading the prompt from the gist to the result is indeed jarring: https://files.catbox.moe/c56eyl.mp4

I don't believe it is that important, but I guess you might've just hit some people's pet peeve with that. If anything, it goes to show as to why skeletons are popular on modern sites

Apologies for not taking the time to find it, but there was a post that tried to determine if the pelican was benchmaxxed across a bunch of models by comparing it to other SVGs, and found that it wasn't at all.

This "no, Virginia, they aren't pelicanmaxxing" article is what broodbucket is probably thinking of: https://dylancastillo.co/posts/pelicanmaxxing.html

In any case, pelicanmaxxing comments without any further proof or evidence probably fall under the "Please don't post shallow dismissals" guideline.

Honestly, seems like a pelican WOULD ride side saddle if at all.

Yeah, I thought the "N" was for Nest

How dare people say neural networks generalize when it's all clearly in the training data? /ß

Making SVGs is coding (of a very specific markup language). So it's not actually absurd. We've also seen that more capable models are generally better at everything minus benchmark contamination (benchmaxxing) anomalities.