17 points | by iamsyr 5 hours ago ago
4 comments
Pelican attempt: https://www.svgviewer.dev/s/8fbPVDUw
Solid but few weird artifacts.
Prompt: > Give me an svg pelican riding a bike
Coding evaluation : Claude Opus 4.6 : 47.9 GLM 5.1 : 45.3 GLM 5 : 35.4
What benchmark is "Coding Evaluation"?
Did you work on GLM 5.1?
Pelican attempt: https://www.svgviewer.dev/s/8fbPVDUw
Solid but few weird artifacts.
Prompt: > Give me an svg pelican riding a bike
Coding evaluation : Claude Opus 4.6 : 47.9 GLM 5.1 : 45.3 GLM 5 : 35.4
What benchmark is "Coding Evaluation"?
Did you work on GLM 5.1?