WebsiteBenchWebsiteBench

PetSmart

Rebuilt by Claude Opus 5.5: 125 of 837 hidden tests passed (14.9%)

reference.local/
Reference for PetSmart, HomeReference
rebuild.local/
Rebuild by Claude Opus 5.5, HomeClaude Opus 5.5
    Every model on PetSmart
    ModelPassed%Screenshot
    Claude Opus 5.512514.9
    Grok 4.612514.9
    Claude Opus 512414.8
    DeepSeek V4.1 Flash10612.7
    GLM 5.3 Flash9311.1
    GPT 6.1 Sol9010.8
    Kimi K3698.2
    Qwen 3.8 Max212.5