WebsiteBenchWebsiteBench

EveryDollar

Rebuilt by Claude Opus 5.5: 142 of 394 hidden tests passed (36.0%)

reference.local/
Reference for EveryDollar, HomeReference
rebuild.local/
Rebuild by Claude Opus 5.5, HomeClaude Opus 5.5
    Every model on EveryDollar
    ModelPassed%Screenshot
    Claude Opus 5.514236.0
    GPT 6.1 Sol13534.3
    Grok 4.612331.2
    Claude Opus 510025.4
    Qwen 3.8 Max9624.4
    GLM 5.3 Flash9323.6
    Kimi K39123.1
    DeepSeek V4.1 Flash7418.8