WebsiteBenchWebsiteBench

Coursera

Rebuilt by Claude Opus 5.5: 190 of 765 hidden tests passed (24.8%)

reference.local/
Reference for Coursera, HomeReference
rebuild.local/
Rebuild by Claude Opus 5.5, HomeClaude Opus 5.5
    Every model on Coursera
    ModelPassed%Screenshot
    Claude Opus 5.519024.8
    GPT 6.1 Sol10613.9
    GLM 5.3 Flash496.4
    Grok 4.6486.3
    Claude Opus 5273.5
    DeepSeek V4.1 Flash253.3
    Qwen 3.8 Max111.4
    Kimi K350.7