WebsiteBenchWebsiteBench

Rate My Professors

Rebuilt by Claude Opus 5.5: 64 of 721 hidden tests passed (8.9%)

reference.local/
Reference for Rate My Professors, HomeReference
rebuild.local/
Rebuild by Claude Opus 5.5, HomeClaude Opus 5.5
    Every model on Rate My Professors
    ModelPassed%Screenshot
    Claude Opus 5.5648.9
    Claude Opus 5365.0
    DeepSeek V4.1 Flash334.6
    Kimi K3324.4
    GPT 6.1 Sol294.0
    Grok 4.6263.6
    Qwen 3.8 Max223.1
    GLM 5.3 Flash192.6