WebsiteBenchWebsiteBench

Columbia Sportswear

Rebuilt by Claude Opus 5.5: 88 of 338 hidden tests passed (26.0%)

reference.local/
Reference for Columbia Sportswear, HomeReference
rebuild.local/
Rebuild by Claude Opus 5.5, HomeClaude Opus 5.5
    Every model on Columbia Sportswear
    ModelPassed%Screenshot
    Claude Opus 5.58826.0
    GPT 6.1 Sol7321.6
    Grok 4.66820.1
    Claude Opus 54413.0
    Qwen 3.8 Max82.4
    Kimi K372.1
    DeepSeek V4.1 Flash00.0
    GLM 5.3 Flash00.0—

    Every result in the WaffleRun the benchmark