Benchmarks

These benchmarks show TopK's end-to-end query performance for nearest-neighbor search across different collection sizes and 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 but requires effective filtering or indexing strategies.

1M Document Collection

1M Documents, 768 Dimensions, k=10
Reducing scan size from 100% to 1% improves median latency by ~28% (6.8ms → 4.9ms) and throughput by ~17% (54 → 63 QPS)
Selectivity	p50 (ms)	p95 (ms)	p99 (ms)	QPS
100% (Full Scan)	6.8	9.1	13	54
10% (100K docs)	5.25	7.3	10	61
1% (10K docs)	4.9	6.7	9	63

p50 (ms)

p95 (ms)

p99 (ms)

10M Document Collection

10M Documents, 768 Dimensions, k=10
Selectivity	p50 (ms)	p95 (ms)	p99 (ms)	QPS
100% (Full Scan)	16.5	20	25	36.5
10% (1M docs)	11	15	19	46
1% (100K docs)	9.5	13	16	49

p50 (ms)

p95 (ms)

p99 (ms)

100M Document Collection

100M Documents, 768 Dimensions, k=10
Selectivity	p50 (ms)	p95 (ms)	p99 (ms)	QPS
100% (Full Scan)	24	34	41	27
10% (10M docs)	18.5	29	34	34
1% (1M docs)	17	27	33	36

p50 (ms)

p95 (ms)

p99 (ms)

Latency Scaling

Summary by Collection Size (100% Selectivity)
Shows how performance scales with collection size when performing full scans
Collection Size	p50 (ms)	p95 (ms)	p99 (ms)	QPS
1M	6.8	9.1	13	54
10M	16.5	20	25	36.5
100M	24	34	41	27

p50 (ms)

p95 (ms)

p99 (ms)

QPS vs Concurrency

Queries per second (QPS) achieved with different number of concurrent clients and single query path replica.

1% Selectivity

10% Selectivity

100% Selectivity

Achieving higher QPS can be easily achieved by provisioning more query path replicas.