WebsiteBenchWebsiteBench

Petfinder

Rebuilt by Claude Opus 5.5: 648 of 1,783 hidden tests passed (36.3%)

reference.local/
Reference for Petfinder, HomeReference
rebuild.local/
Rebuild by Claude Opus 5.5, HomeClaude Opus 5.5
    Every model on Petfinder
    ModelPassed%Screenshot
    Claude Opus 5.564836.3
    GLM 5.3 Flash18810.5
    Claude Opus 518010.1
    Grok 4.6110.6
    Kimi K340.2
    Qwen 3.8 Max40.2—
    DeepSeek V4.1 Flash00.0
    GPT 6.1 SolError