Vector Search Bench — ASO

By Tsubasa Kato on AppTrack Ninja.

Vector Search Bench is a high-signal, no-nonsense benchmark suite for vector similarity search on iPhone. Measure how fast and stable your device can score embeddings using the CPU (Accelerate/vDSP) versus the Apple Neural Engine (Core ML)—with real metrics you can trust. What you can benchmark Exact Top-K vector search (dot-product similarity) CPU path: Accelerate / vDSP optimized scoring NPU path: Core ML Dense inference tuned for Neural Engine scheduling Query-by-query execution with repeatable timing Intricate performance metrics Latency distribution: median, p95 Throughput: QPS Recall@K …

Categories: Utilities

Keyword visibility, ranked search terms and daily position movement for Vector Search Bench.