Scaling Reranked Retrieval: Hybrid Search + LLM Reranking Lifts nDCG@10 2.6x

CShorten30 · x · 2026-11-16

Christopher Shorten shares a research report, Scaling Reranked Retrieval, framed around three levers for spending the next unit of search compute: depth (deeper retrieval), stages (more reranking stages), and width (more models per stage).

Depth and stages compose into a quality ladder with nDCG@10 climbing at each rung:

Related event: Scaling Reranked Retrieval: Hybrid Search Plus LLM Reranking Multiplies nDCG by 2.6x(3 posts)→

Original post →

More from Research

Research channel →