WebsiteBenchWebsiteBench

Tripadvisor

Rebuilt by Claude Opus 5.5: 98 of 625 hidden tests passed (15.7%)

reference.local/
Reference for Tripadvisor, HomeReference
rebuild.local/
Rebuild by Claude Opus 5.5, HomeClaude Opus 5.5
    Every model on Tripadvisor
    ModelPassed%Screenshot
    Claude Opus 5.59815.7
    Claude Opus 58012.8
    GPT 6.1 Sol7812.5
    DeepSeek V4.1 Flash6810.9
    Kimi K3629.9
    Grok 4.6416.6
    Qwen 3.8 Max335.3
    GLM 5.3 Flash315.0