P

rubberband · Production library run 3

65.3Library score
Pass rate92.0%
Simplicity76.3
Problems $$12.19

Implementers use the real production library (tantivy).

ImplementerPass rateSimplicityCostScore
DeepSeek V4.1 Flash · mini-SWE89.9%73.4$2.15
60.0
GLM 5.3 Flash · mini-SWE94.2%78.6$6.95
69.9
GPT-5.6 Luna · Codex91.9%76.9$3.09
66.0
ProblemDeepSeek V4.1 FlashGLM 5.3 FlashGPT-5.6 LunaMean
case-law-export40.954.053.449.4session-recall43.640.166.950.2document-finder60.541.470.357.4code-chunk-search38.536.033.636.0symbol-resolution53.567.646.956.0docs-search68.848.164.560.5knowledge-ingest77.790.084.684.1federated-search82.878.175.778.8post-indexer95.489.089.191.2blog-rebuild78.957.059.065.0mailbox-tags0.997.078.858.9attachment-explorer89.883.261.078.0archive-search80.686.589.685.6index-admin2.197.62.133.9file-locator64.592.596.884.6project-rule-search62.174.685.874.2blog-filters58.148.255.654.0dictionary-lookup59.762.351.557.8archive-timeline68.684.583.378.8source-rule-search73.470.970.771.7