← Back to context

Comment by simonw

6 days ago

Claude Sonnet 5 itself described its pelican as looking like a goose:

> Illustration of a white goose riding a bicycle, with one wing extended forward to grip the handlebar, set against a plain white background with a brown ground line.

https://simonwillison.net/2026/Jun/30/claude-sonnet-5/

That's possibly the worst pelican I saw from all recent LLMs.

Meanwhile GLM 5.2 drew a cool self-contained fully animated SVG pelican:

https://simonwillison.net/2026/Jun/17/glm-52

  • Yeah, GLM have been beating Anthropic on the pelicans for a while now.

    (I suspect that's more of an indication that Anthropic have chosen not to waste resources training on animals riding vehicles, personally.)

    • This is interesting, I haven’t actually heard you suggest that the labs are focusing on this benchmark before. Have you come around to this position as a result of the quality of pelicans you’ve been getting?

      The reason I thought this was an interesting benchmark is because it’s a non-image generating model creating an image using SVG code, so it kinda spans capabilities.

      If an AI lab trained a model specifically for animals riding bicycles it seem trivial to modify the prompt and determine if it was trained specifically for that or if it’s generalized a skill and can also generate a proper orangutan walking on stilts or an armadillo on a skateboard, this sort of thing?

      1 reply →

    • That's one possibility albeit quite charitable. I'd be inclined to think the same personally if GLM 5.2 wasn't also rocking in other areas too.

Mine is to ask it to write a parallel parking simulator and animation. The math there is surprisingly complex including differential equations. Fable 5 can almost one shot it with all tunable params.