WebsiteBenchWebsiteBench

Resy

Rebuilt by Claude Opus 5.5: 24 of 519 hidden tests passed (4.6%)

reference.local/
Reference for Resy, HomeReference
rebuild.local/
Rebuild by Claude Opus 5.5, HomeClaude Opus 5.5
    Every model on Resy
    ModelPassed%Screenshot
    Claude Opus 5.5244.6
    GLM 5.3 Flash214.0
    GPT 6.1 Sol203.9
    DeepSeek V4.1 Flash142.7
    Claude Opus 5132.5—
    Kimi K3122.3
    Qwen 3.8 Max122.3
    Grok 4.6101.9