WebsiteBenchWebsiteBench

1Password Web

Rebuilt by Claude Opus 5.5: 57 of 679 hidden tests passed (8.4%)

reference.local/
Reference for 1Password Web, HomeReference
rebuild.local/
Rebuild by Claude Opus 5.5, HomeClaude Opus 5.5
    Every model on 1Password Web
    ModelPassed%Screenshot
    Claude Opus 5.5578.4
    GPT 6.1 Sol314.6
    Claude Opus 5304.4
    Grok 4.6284.1
    GLM 5.3 Flash253.7
    Kimi K3213.1
    Qwen 3.8 Max202.9
    DeepSeek V4.1 Flash192.8