WebsiteBenchWebsiteBench

Petco

Rebuilt by Claude Opus 5.5: 154 of 609 hidden tests passed (25.3%)

reference.local/
Reference for Petco, HomeReference
rebuild.local/
Rebuild by Claude Opus 5.5, HomeClaude Opus 5.5
    Every model on Petco
    ModelPassed%Screenshot
    Claude Opus 5.515425.3
    GPT 6.1 Sol13121.5
    Claude Opus 512420.4
    DeepSeek V4.1 Flash11819.4
    Grok 4.611518.9
    GLM 5.3 Flash11118.2
    Qwen 3.8 Max10116.6
    Kimi K39916.3