WebsiteBenchWebsiteBench

Warby Parker

Rebuilt by Claude Opus 5.5: 292 of 992 hidden tests passed (29.4%)

reference.local/
Reference for Warby Parker, HomeReference
rebuild.local/
Rebuild by Claude Opus 5.5, HomeClaude Opus 5.5
    Every model on Warby Parker
    ModelPassed%Screenshot
    Claude Opus 5.529229.4
    GPT 6.1 Sol16116.2
    Claude Opus 510210.3
    Kimi K3686.9
    DeepSeek V4.1 Flash616.1
    Grok 4.6515.1
    Qwen 3.8 Max191.9
    GLM 5.3 Flash40.4