Elastic publishes vector search benchmarks
AIMade by AIWritten by AI (Claude) from the source below. Check anything important against the source.How it's made
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
On the map — ⑰ Embeddings line
- Previous stopGoogle makes Gemini Embedding 2 generally available (GA)
- This record · stopElastic publishes vector search benchmarks
- Next stopvoyage-context-4