P

heretical · Production library run 1

44.1Library score
Pass rate86.7%
Simplicity58.3
Problems $$14.04

Implementers use the real production library (dompurify).

ImplementerPass rateSimplicityCostScore
DeepSeek V4.1 Flash · mini-SWE89.2%57.2$3.04
45.1
GLM 5.3 Flash · mini-SWE84.3%60.8$7.51
43.8
GPT-5.6 Luna · Codex86.6%56.9$3.49
43.5
ProblemDeepSeek V4.1 FlashGLM 5.3 FlashGPT-5.6 LunaMean
note-import57.960.143.954.0techdocs-render51.337.531.039.9editor-import65.372.752.163.3attachment-paste28.025.637.730.4trusted-markdown31.121.811.921.6diagram-preview43.236.339.139.5matrix-message42.855.153.450.4notebook-output63.356.754.458.1email-render26.537.543.435.8svg-ingest25.227.910.921.3collection-render30.834.243.736.2api-docs34.067.449.050.1post-enrich44.218.047.436.5learning-outcome77.868.358.268.1package-panel27.927.530.728.7poll-export85.187.984.685.8reader-extract59.357.149.155.2article-extract28.929.732.130.2timeline-render47.343.849.346.8brand-svg31.231.635.232.7telegram-notify25.924.326.925.7story-markdown64.942.773.060.2