What is Reranking?
Verified 5 August 2026
Retrieval is optimised for recall over millions of documents; reranking is optimised for precision over a few dozen. Running the expensive scorer only on candidates that survived the first stage makes accuracy affordable.
The same principle appears inside a vector index — retrieve on quantised codes, rerank on higher-precision vectors — and at the application layer, where a cross-encoder reorders the top fifty results.
unlob does the first internally. The second is worth considering in your application if precision at rank one matters more than latency.
Common questions
What is Reranking?
Reranking reorders an initial candidate set with a more expensive, more accurate model than the one used to retrieve it.
How does Reranking work in practice?
The same principle appears inside a vector index — retrieve on quantised codes, rerank on higher-precision vectors — and at the application layer, where a cross-encoder reorders the top fifty results.
See it working
The free tier is 10,000 requests a month with no card — enough to test any of this against your own queries.