WebsiteBenchWebsiteBench

Dooney & Bourke

Rebuilt by Claude Opus 5.5: 185 of 754 hidden tests passed (24.5%)

reference.local/
Reference for Dooney & Bourke, HomeReference
rebuild.local/
Rebuild by Claude Opus 5.5, HomeClaude Opus 5.5
    Every model on Dooney & Bourke
    ModelPassed%Screenshot
    Claude Opus 5.518524.5
    GPT 6.1 Sol13618.0
    Claude Opus 513017.2
    GLM 5.3 Flash12716.8
    DeepSeek V4.1 Flash11715.5
    Grok 4.611415.1
    Kimi K310814.3
    Qwen 3.8 Max385.0