P

rubberband · Production library run 2

66.7Library score
Pass rate88.9%
Simplicity80.4
Problems $$12.14

Implementers use the real production library (tantivy).

ImplementerPass rateSimplicityCostScore
DeepSeek V4.1 Flash · mini-SWE92.3%80.4$1.73
69.4
GLM 5.3 Flash · mini-SWE90.0%82.2$7.45
69.1
GPT-5.6 Luna · Codex84.4%78.5$2.96
61.6
ProblemDeepSeek V4.1 FlashGLM 5.3 FlashGPT-5.6 LunaMean
case-law-export82.972.20.051.7session-recall43.550.844.146.1document-finder73.153.866.064.3code-chunk-search38.464.638.347.1symbol-resolution46.572.152.757.1docs-search66.155.763.861.9knowledge-ingest82.669.484.478.8federated-search64.974.285.574.9post-indexer93.486.983.888.0blog-rebuild73.675.668.472.5mailbox-tags80.183.585.983.2attachment-explorer86.70.070.352.3archive-search74.985.883.381.3index-admin10.887.72.133.5file-locator90.196.481.989.5project-rule-search86.370.776.777.9blog-filters51.068.737.452.4dictionary-lookup91.473.756.473.8archive-timeline73.361.082.972.4source-rule-search78.278.667.874.8