P

heretical · Production library run 3

43.3Library score
Pass rate84.9%
Simplicity58.1
Problems $$14.34

Implementers use the real production library (dompurify).

ImplementerPass rateSimplicityCostScore
DeepSeek V4.1 Flash · mini-SWE86.0%58.5$3.03
45.3
GLM 5.3 Flash · mini-SWE82.8%63.2$7.71
44.5
GPT-5.6 Luna · Codex85.8%52.6$3.60
40.0
ProblemDeepSeek V4.1 FlashGLM 5.3 FlashGPT-5.6 LunaMean

Click a problem to see how each solution's score is built.