WebsiteBenchWebsiteBench

AutoSlash

Rebuilt by Claude Opus 5.5: 54 of 353 hidden tests passed (15.3%)

reference.local/
Reference for AutoSlash, HomeReference
rebuild.local/
Rebuild by Claude Opus 5.5, HomeClaude Opus 5.5
    Every model on AutoSlash
    ModelPassed%Screenshot
    Claude Opus 5.55415.3
    GPT 6.1 Sol4312.2
    GLM 5.3 Flash154.2
    Claude Opus 592.5
    Kimi K372.0
    DeepSeek V4.1 Flash61.7
    Grok 4.610.3
    Qwen 3.8 Max10.3