A Local Qwen Model Beat Claude at the Pelican Test
Published on 17.04.2026
Qwen3.6-35B-A3B on my laptop drew me a better pelican than Claude Opus 4.7
TLDR: Simon Willison compared fresh model releases using his silly but memorable SVG benchmark. On this one task, a quantized local Qwen model running on a laptop produced a better result than Claude Opus 4.7.
Qwen3.6-35B-A3B on my laptop drew me a better pelican than Claude Opus 4.7
External Links (1)