WebsiteBenchWebsiteBench

Lowe’s

Rebuilt by Claude Opus 5.5: 340 of 494 hidden tests passed (68.8%)

reference.local/
Reference for Lowe’s, HomeReference
rebuild.local/
Rebuild by Claude Opus 5.5, HomeClaude Opus 5.5
    Every model on Lowe’s
    ModelPassed%Screenshot
    Claude Opus 5.534068.8
    GPT 6.1 Sol25251.0
    Grok 4.619639.7
    GLM 5.3 Flash18737.9
    Qwen 3.8 Max17936.2
    Claude Opus 514429.1
    DeepSeek V4.1 Flash13527.3
    Kimi K300.0—