Qwen3.6-35B-A3B Outperforms Claude Opus 4.7 in Pelican Image Test

In a comparative test, Simon Willison observed that Alibaba’s Qwen3.6-35B-A3B model running locally generated a superior pelican image compared to Anthropic’s Claude Opus 4.7. This informal benchmark highlights varying image generation capabilities between the two recently released models.

Source: Simon Willison