WebsiteBenchWebsiteBench

ioby

Rebuilt by Claude Opus 5.5: 69 of 380 hidden tests passed (18.2%)

reference.local/
Reference for ioby, HomeReference
rebuild.local/
Rebuild by Claude Opus 5.5, HomeClaude Opus 5.5
    Every model on ioby
    ModelPassed%Screenshot
    Claude Opus 5.56918.2
    DeepSeek V4.1 Flash5915.5
    Kimi K35815.3
    Grok 4.65614.7
    Claude Opus 54712.4
    GPT 6.1 Sol3910.3
    GLM 5.3 Flash328.4
    Qwen 3.8 Max00.0—

    Every result in the WaffleRun the benchmark