P
wapi · Production library run 3
27.3Library score
Pass rate48.3%
Simplicity77.5
Problems $$20.43
Implementers use the real production library (servant).
ImplementerPass rateSimplicityCostScore
DeepSeek V4.1 Flash · mini-SWE33.0%76.5$1.74
GLM 5.3 Flash · mini-SWE60.1%73.5$14.86
GPT-5.6 Luna · Codex52.9%82.2$3.83
ProblemDeepSeek V4.1 FlashGLM 5.3 FlashGPT-5.6 LunaMean
agent-runtime-protocol0.00.00.20.1reservation-receipts0.00.00.80.3page-publish-links6.30.04.83.7catalog-api43.635.024.434.3portal-routing93.627.053.958.2index-gateway0.046.685.644.0chain-index0.054.44.019.5chain-archive54.716.922.031.2project-routes0.038.954.731.2callback-registry3.964.182.350.1