WebsiteBenchWebsiteBench

LeetCode

Rebuilt by Claude Opus 5.5: 242 of 326 hidden tests passed (74.2%)

reference.local/
Reference for LeetCode, HomeReference
rebuild.local/
Rebuild by Claude Opus 5.5, HomeClaude Opus 5.5
    Every model on LeetCode
    ModelPassed%Screenshot
    Claude Opus 5.524274.2
    GPT 6.1 Sol22869.9
    Qwen 3.8 Max8024.5
    Kimi K37723.6—
    DeepSeek V4.1 Flash7322.4
    Claude Opus 56219.0
    GLM 5.3 Flash309.2
    Grok 4.6268.0