WebsiteBenchWebsiteBench

L.L.Bean

Rebuilt by Claude Opus 5.5: 164 of 423 hidden tests passed (38.8%)

reference.local/
Reference for L.L.Bean, HomeReference
rebuild.local/
Rebuild by Claude Opus 5.5, HomeClaude Opus 5.5
    Every model on L.L.Bean
    ModelPassed%Screenshot
    Claude Opus 5.516438.8
    GPT 6.1 Sol12930.5
    Kimi K39722.9
    DeepSeek V4.1 Flash9021.3
    Claude Opus 58119.1
    Qwen 3.8 Max6515.4
    Grok 4.65813.7
    GLM 5.3 Flash5312.5

    Every result in the WaffleRun the benchmark