WebsiteBenchWebsiteBench

Change.org

Rebuilt by Claude Opus 5.5: 181 of 420 hidden tests passed (43.1%)

reference.local/
Reference for Change.org, HomeReference
rebuild.local/
Rebuild by Claude Opus 5.5, HomeClaude Opus 5.5
    Every model on Change.org
    ModelPassed%Screenshot
    Claude Opus 5.518143.1
    GLM 5.3 Flash12429.5
    Qwen 3.8 Max12128.8
    GPT 6.1 Sol11627.6
    Claude Opus 511527.4
    Grok 4.610926.0
    Kimi K39322.1
    DeepSeek V4.1 Flash8821.0