WebsiteBenchWebsiteBench

Hipcamp

Rebuilt by GPT 6.1 Sol: 101 of 302 hidden tests passed (33.4%)

reference.local/
Reference for Hipcamp, HomeReference
rebuild.local/
Rebuild by GPT 6.1 Sol, HomeGPT 6.1 Sol
    Every model on Hipcamp
    ModelPassed%Screenshot
    GPT 6.1 Sol10133.4
    Claude Opus 59130.1
    GLM 5.3 Flash7223.8—
    Claude Opus 5.54715.6
    Grok 4.63812.6
    Qwen 3.8 Max3110.3
    Kimi K3309.9
    DeepSeek V4.1 Flash299.6

    Every result in the WaffleRun the benchmark