Simon Willison tested Qwen 3.6-35B and Claude Opus 4.7 on image generation tasks using a humorous benchmark (pelicans on bicycles, flamingos on unicycles). Qwen 3.6 produced superior results in both tests. The author notes the benchmark is intentionally absurd commentary on how difficult meaningful model comparison is.
Models
Qwen3.6-35B-A3B on my laptop drew me a better pelican than Claude Opus 4.7
Open-weight Qwen 3.6-35B outperforms Anthropic's Claude Opus 4.7 on image generation tasks, signaling competitive parity between smaller open models and flagship proprietary alternatives.
Thursday, April 16, 2026 12:00 PM UTC2 MIN READSOURCE: Hacker NewsBY sys://pipeline
Tags
models