To be fair I have a feeling that if you added 'animated' to the SVG request, the output quality from many other models would improve, just because of the extra chain-of-thought work needed to fulfill the more complex request. IMHO the animation requirement should be added to the canonical pelican prompt.
definitely not frontier though, as even on max both legs are in front of the frame; although I am wondering how much getting that right correlates with model intelligence.
The biggest (of many) failing of the pelican test is that it's only one prompt - what matters most these days is how well a model can drive a lengthy agentic tool calling session.
I think I have yet to see a pelican where the left leg and pedal are drawn on the left side of the bike.
There have been a few that get that right - most notable Qwen 3.8 27B running on my laptop: https://simonwillison.net/2026/Aug/16/qwen-38-27b/#the-defau...
Also the recent Geminis - https://simonwillison.net/2026/Oct/13/llm-gemini/ - and GPT-6 Astra on Max: https://static.simonwillison.net/static/2026/gpt-pelicans-gr... - and Claude Fable 5.1 https://static.simonwillison.net/static/2026/claude-pelicans...
GLM 5.3 not only got that part right, but animated it: https://crimson-jeri-74.tiiny.site/
To be fair I have a feeling that if you added 'animated' to the SVG request, the output quality from many other models would improve, just because of the extra chain-of-thought work needed to fulfill the more complex request. IMHO the animation requirement should be added to the canonical pelican prompt.
Simon's comment apparently got flagkilled; I vouched for it.
If enough people are flagging it, we may be at a point where the pelican benchmark is truly overdone.
Please do not decrease the useful signal with this noise
Is that even a debate at this point? Doing my job as a netizen to maintain signal/noise ratio
definitely not frontier though, as even on max both legs are in front of the frame; although I am wondering how much getting that right correlates with model intelligence.
The biggest (of many) failing of the pelican test is that it's only one prompt - what matters most these days is how well a model can drive a lengthy agentic tool calling session.
I like the low effort one most.
Can I just say that I love how you are also just always here the moment something drops lmao. Hope you're all well! The pelicans indeed are solid.