P

wapi · Production library run 1

27.2Library score
Pass rate48.7%
Simplicity73.4
Problems $$19.74

Implementers use the real production library (servant).

ImplementerPass rateSimplicityCostScore
DeepSeek V4.1 Flash · mini-SWE31.7%73.6$1.56
18.7
GLM 5.3 Flash · mini-SWE51.6%69.9$14.51
25.8
GPT-5.6 Luna · Codex62.7%76.6$3.66
36.9
ProblemDeepSeek V4.1 FlashGLM 5.3 FlashGPT-5.6 LunaMean
agent-runtime-protocol2.31.90.81.7reservation-receipts0.00.828.19.6page-publish-links1.80.52.11.5catalog-api35.952.929.439.4portal-routing93.849.554.565.9index-gateway0.057.388.748.7chain-index0.00.054.418.1chain-archive50.627.421.033.0project-routes0.037.753.130.3callback-registry2.930.137.423.5