Elastic publishes vector search benchmarks
Published vector search benchmarks — float32 HNSW at 15,000 QPS with recall@10 of 0.99, DiskBBQ quantization at 55,000 QPS with recall@10 of 0.97 (company-measured). 32× compression by storing binary vectors on disk
Why it matters
An integrated search engine using quantization to take direct aim at the performance and cost case for dedicated vector DBs
Source — Primary sources first; secondary reports are labelled “Press”
Officialelastic.cohttps://www.elastic.co/blog/understanding-approximate-nearest-neighbor-searchAdded in Week 35, 2026 · See that week