These benchmarks show TopK's end-to-end query performance for hybrid vector search across different collection sizes and filter selectivity levels.
The metrics include median (p50), 95th percentile (p95), and 99th percentile (p99) latencies in milliseconds, as well as overall throughput in queries per second (QPS).
Selectivity refers to what fraction of the collection is scanned - from a full scan (100%) down to scanning just 1% of vectors. Lower selectivity generally yields better performance without impacting the quality of results.
1m3s
Ingest + index
6m
Ingest + index
10m30s
Ingest + index
15m50s
Ingest + index
1h44m
Ingest + index
2h52m
Ingest + index
17h12m
Ingest + index
29h50m
Ingest + index