Here's Qwen 3.6-35B-A3B v.s. Claude Opus 4.7 for 'Generate an SVG of a flamingo riding a unicycle', in case you thought Qwen might be cheati…

This post compares the performance of Qwen 3.6-35B-A3B and Claude Opus 4.7 models on a creative task of generating SVG code for a flamingo riding a unicycle, likely demonstrating differences in their capabilities for complex visual code generation. The comparison appears to address skepticism about whether Qwen might be producing superior results through shortcuts or cheating rather than genuine performance improvement. Simon Willison, a notable AI researcher and commentator, shared this analysis on X to provide evidence about the relative strengths of these two language models on a specific creative coding challenge.

Source: Simon Willison (X) | 2026-04-16