It's generating a raster image and then using a tracing algorithm to turn it into an SVG, rather than generating an SVG via coding from the ground-up. If you put a raster image into Adobe Illustrator and use its image tracing you'll get a similar result.
AFAIK that model is pretty old, and it was explicitly trained for SVG generation. For other models the capability of generating SVGs of real stuff is accidental. Same as GPT-5.x and Sonnet 4.5+ being able to generate MIDI music.
https://clocks.brianmoore.com/
but static.