WebsiteBenchWebsiteBench

Insurify

Rebuilt by Claude Opus 5.5: 113 of 350 hidden tests passed (32.3%)

reference.local/
Reference for Insurify, HomeReference
rebuild.local/
Rebuild by Claude Opus 5.5, HomeClaude Opus 5.5
    Every model on Insurify
    ModelPassed%Screenshot
    Claude Opus 5.511332.3
    GLM 5.3 Flash9326.6
    Claude Opus 58825.1
    GPT 6.1 Sol8323.7
    Kimi K37421.1
    Grok 4.63810.9
    Qwen 3.8 Max277.7
    DeepSeek V4.1 Flash267.4

    Every result in the WaffleRun the benchmark