Comment by Jimmc414

Hi Simon! Love your work! Our of curiosity - how many pelican-cycling samples do you produce. Curious about the variance here. Thanks!

Aiden is perhaps misinformed. From a Bing search performed just now.

> Yes, I am familiar with the "pelican riding a bicycle" SVG generation test. It is a benchmark for evaluating the ability of AI models, particularly large language models (LLMs) and multi-modal systems, to generate original, high-quality SVG vector graphics based on a deliberately unusual and complex prompt. The benchmark was popularized by Simon Willison, who selected the prompt because:

[flagged]

The fact that pelicans can't ride bicycles is pretty much the point of the benchmark! Asking an LLM to draw something that's physically impossible means it can't just "get it right" - seeing how different models (especially at different sizes) handle the problem is surprisingly interesting.

Honestly though, the benchmark was originally meant to be a stupid joke.

I only started taking it slightly more seriously about six months ago, when I noticed that the quality of the pelican drawings really did correspond quite closely to how generally good the underlying models were.

If a model draws a really good picture of a pelican riding a bicycle there's a solid chance it will be great at all sorts of other things. I wish I could explain why that was!

If you start here and scroll through and look at the progression of pelican on bicycle images it's honestly spooky how well they match the vibes of the models they represent: https://simonwillison.net/2025/Jun/6/six-months-in-llms/#ai-...

So ever since then I've continue to get models to draw pelicans. I certainly wouldn't suggest anyone take serious decisions on model usage based on my stupid benchmark, but it's a fun first-day initial impression thing and it appears to be a useful signal for which models are worth diving into in more detail.

It's just a variant of the wine glass - something that doesn't exist in the source material as-is. I have a few of my own I don't share publicly.

Basically in my niche I _know_ there are no original pictures of specific situations and my prompts test whether the LLM is "creative" enough to combine multiple sources into one that matches my prompt.

I think of if like this: there are three things I want in the picture (more actually, but for the example assume 3). All three are really far from each other in relevance, in the very corner of an equilateral triangle (in the vector space of the LLM's "brain"). What I'm asking it to do is in the middle of all three things.

Every model so far tends to veer towards one or two of the points more than others because it can't figure out how to combine them all into one properly.

It's not nessessarily the best benchmark, it's a popular one, probably because it's funny.

Yes it's like the wine glass thing.

Also it's kind of got depth. Does it draw the pelican and the bicycle? Can the penguin reach the peddles? How?

I can imagine a really good AI finding a funny or creative or realistic way for the penguin to reach the peddles.

An slightly worse AI will do an OK job, maybe just making the bike small or the legs too long.

An OK AI will draw a penguin on top of a bicycle and just call it a day.

It's not as binary as the wine glass example.

That depends on if "SVG generation" is a particularly useful LLM/coding model skill outside of benchmarking. I.e., if they make that stronger with some params that otherwise may have been used for "rust type system awareness" or somesuch, it might be a net loss outside of the benchmarks.

How? There's no way for you to verify if they put synthetic data for that into the dataset or not.

The easiest way to fix these is give the model an environment to run code.

Any model can easily one-shot a python script that can count the occurrence of any letter anywhere and return the result.

It's just a tooling issue. You really can't "train" an LLM to do it because tokenisation and ... stuff.