WebsiteBenchWebsiteBench

Ace Hardware

Rebuilt by Claude Opus 5.5: 131 of 433 hidden tests passed (30.3%)

reference.local/
Reference for Ace Hardware, HomeReference
rebuild.local/
Rebuild by Claude Opus 5.5, HomeClaude Opus 5.5
    Every model on Ace Hardware
    ModelPassed%Screenshot
    Claude Opus 5.513130.3
    GPT 6.1 Sol8519.6
    Claude Opus 57116.4
    Kimi K36114.1
    Qwen 3.8 Max5612.9
    DeepSeek V4.1 Flash4911.3
    GLM 5.3 Flash337.6
    Grok 4.6286.5