shadcn reports 'weird' eval results with Sonnet and Gemini on top

shadcn, creator of shadcn/ui, reported 'weird things' happening in his evals, with a ranking showing Claude Sonnet and Gemini passing the most tasks; Vercel engineer shuding quipped it might be a good thing.

2026-11-07 ~ 2026-11-08 · 2 related posts

• shadcn reports weird eval results: Sonnet and Gemini pass the most tasks — shadcn · 2026-11-07
• shadcn reports 'weird things' in his evals; shuding hints it may be good news — shuding · 2026-11-08