Benchmarks

Fast and accurate retrieval is the backbone of the new generation of AI-native applications.
TopK is built for teams working with large volumes of data where high performance, flexibility, and cost efficiency matter.

These benchmarks show TopK's end-to-end query performance for Dense Vector Search, Sparse Vector Search, and File Search answer accuracy across industry datasets.

Collection Size
Ingest + index:1m3s

Query Latency

p50, p95, and p99 latencies across selectivity levels

p50p95p99
Selectivity%

Concurrency

Queries per second as concurrent clients scale

QPS
Concurrent clients