I've seen this reply to Simon's benchmark for 2 years running now, and yet you still see improvements and objectively-bad results over time from new releases, even when I'm sure every frontier AI team has/had a person at least partially dedicated to better bicycle-pelican SVG outputs. Alas.

▲

sarreph 2 hours ago | parent | next [-]

I had intended to caveat that: I'm sure I'm not the first person to ask about this!

> you still see improvements

This is expected if they are training their models on it, right?

> objectively-bad results

Keen to learn when this has been the case, i.e. across version increments in major models.

▲

simonw 2 hours ago | parent [-]

I've written about this a couple of times, most notably here: https://simonwillison.net/2025/Nov/13/training-for-pelicans-...

I've been enjoying seeing how the quality of individual models differ based on the amount of reasoning effort you give them. If they were baking an a good pelican you wouldn't expect them to differ so much.

(Google Gemini are the only lab that have very clearly paid attention to the quality of SVG animals-riding-vehicles, see their announcement for Gemini 3.1: https://twitter.com/JeffDean/status/2024525132266688757 )

▲

sarreph 2 hours ago | parent [-]

Amazing, thank you Simon! Look forward to reading.

	▲	38484858 2 hours ago \| parent [-]
		[flagged]

▲

llm_nerd 2 hours ago | parent | prev [-]

I honestly assumed their comment was tongue in cheek humour, because positively no one actually cares how these models generate an SVG pelican riding a bicycle. It's some meme thing that this stuff always appears here.

▲

BrokenCogs 2 hours ago | parent [-]

Yeah this is not a real benchmark, it's just a fun tradition everytime a new model is released

	▲	pelipost123 2 hours ago \| parent [-]
		"fun" / boringly predictable meme thread with 30+ replies already