WebsiteBenchWebsiteBench

Simplify Jobs

Rebuilt by Claude Opus 5.5: 80 of 752 hidden tests passed (10.6%)

reference.local/
Reference for Simplify Jobs, HomeReference
rebuild.local/
Rebuild by Claude Opus 5.5, HomeClaude Opus 5.5
    Every model on Simplify Jobs
    ModelPassed%Screenshot
    Claude Opus 5.58010.6
    GLM 5.3 Flash699.2
    DeepSeek V4.1 Flash678.9
    GPT 6.1 Sol608.0
    Claude Opus 5253.3
    Grok 4.6222.9
    Kimi K3212.8
    Qwen 3.8 Max00.0—