WebsiteBenchWebsiteBench

Notion

Rebuilt by Claude Opus 5.5: 192 of 393 hidden tests passed (48.9%)

reference.local/
Reference for Notion, HomeReference
rebuild.local/
Rebuild by Claude Opus 5.5, HomeClaude Opus 5.5
    Every model on Notion
    ModelPassed%Screenshot
    Claude Opus 5.519248.9
    GPT 6.1 Sol18045.8
    Claude Opus 514536.9
    GLM 5.3 Flash11629.5
    Kimi K35514.0
    DeepSeek V4.1 Flash4712.0
    Qwen 3.8 Max4611.7
    Grok 4.6307.6