WebsiteBenchWebsiteBench

Backcountry

Rebuilt by Claude Opus 5.5: 254 of 1,317 hidden tests passed (19.3%)

reference.local/
Reference for Backcountry, HomeReference
rebuild.local/
Rebuild by Claude Opus 5.5, HomeClaude Opus 5.5
    Every model on Backcountry
    ModelPassed%Screenshot
    Claude Opus 5.525419.3
    GPT 6.1 Sol25019.0
    Kimi K318414.0
    DeepSeek V4.1 Flash16912.8
    Grok 4.615812.0
    Claude Opus 5393.0
    GLM 5.3 Flash191.4
    Qwen 3.8 Max120.9—