WebsiteBenchWebsiteBench

Meetup

Rebuilt by Claude Opus 5.5: 143 of 347 hidden tests passed (41.2%)

reference.local/
Reference for Meetup, HomeReference
rebuild.local/
Rebuild by Claude Opus 5.5, HomeClaude Opus 5.5
    Every model on Meetup
    ModelPassed%Screenshot
    Claude Opus 5.514341.2
    GPT 6.1 Sol14240.9
    DeepSeek V4.1 Flash11132.0
    Claude Opus 510530.3
    Qwen 3.8 Max8023.1
    GLM 5.3 Flash7521.6
    Grok 4.65917.0
    Kimi K3257.2

    Every result in the WaffleRun the benchmark