In November and December 2025, inspired by Simon Willison’s pelican-riding-a-bicycle benchmark, I had some then-current LLMs create SVGs from thirty similar prompts, such as “Generate an SVG of an octopus operating a pipe organ.” Simon mentioned that experiment on his blog [1].

Nine months have passed and much stronger models have been released, so I tried the experiment again today. The linked site shows the results.

Running ten of the prompts through six models at OpenRouter cost about twenty dollars, so I stopped there for now.

[1] https://simonwillison.net/2025/Nov/25/

I notice none of the octopi seem to be actually facing the organ.

I'd like to mention the Little Dorrit Benchmark [1] which I have been running for a couple of years now. It has a few nice features:

1. It tests visual reasoning and structured output in a single task.

2. It seems to sort correctly on advancing general intelligence. As a counterexample, if I'm not misremembering, artificialanalysis.ai made some changes to their benchmark recently after Astra ranked below several older models.

3. While models have gotten significantly better in the past 2 years, the top model is still at 0.78 F1, so the test is not yet saturated. As a reference point, when I started, the top models were in the [0.1, 0.2] range.

[1] https://dorrit.pairsys.ai/

Website looks very cool, Fable's octopus-organist looks very cute, but I feel like this benchmark (generate an SVG by a short and slightly ridiculous description) in general has been completely Goodharted [0].

I think they all just added a bunch of similar tasks to their training sets, so we cannot judge true emergent capabilities of the models anymore.

[0] https://en.wikipedia.org/wiki/Goodhart%27s_law

All models are pretty good now at generating these images. Back in the day, I remember experimenting with the pelican images and most of the models couldn't align the legs with the wheels. Right now as well, GPT messed up an octopus leg by originating it through the instrument rather than the octopus itself.

I think that intertwining two entities (living/non-living) is still challenging but overall they're pretty sound.

It is interesting how similar the designs are across the models.

Feels like google has a different training set than the others?

Gemini 3.8 flash seems to (subjectively) be the outlier in terms of performance to cost ratio?

Does a test of instructions how to fold origami figures in a SVG/jpeg exist? Or could be useful?

Well that benchmark is now saturated, what next. How fast you can hack the pentagon?

Interesting, out of all examples Gemini 3.8 is the best for me. Also the image style is different and more vibrant than others

> An elephant typing on a typewriter

A monkey, surely?

Why is this a good test?

The 3 US models have their own style.

Qwen3.8 is very clearly distilled from Claude models.

Asking to animate it add an interesting layer of difficulty