WebsiteBenchWebsiteBench

Airtable

Rebuilt by Claude Opus 5.5: 74 of 589 hidden tests passed (12.6%)

reference.local/
Reference for Airtable, HomeReference
rebuild.local/
Rebuild by Claude Opus 5.5, HomeClaude Opus 5.5
    Every model on Airtable
    ModelPassed%Screenshot
    Claude Opus 5.57412.6
    GLM 5.3 Flash6010.2
    GPT 6.1 Sol417.0
    Claude Opus 5366.1
    DeepSeek V4.1 Flash355.9
    Grok 4.6335.6
    Qwen 3.8 Max274.6
    Kimi K3264.4