Preprint · 2026 · Open access

A Comprehensive Empirical Evaluation of Vector Database Systems for Approximate Nearest Neighbor Search: Performance, Quality, and Resource Trade-offs

Ashen Rashmiks, Tiroshan Madushanka

arXiv (Cornell University) · Published 13 August 2026 · DOI 10.48550/arxiv.2608.12812

Open PDFView at the publisherCite this paper

In brief

“A Comprehensive Empirical Evaluation of Vector Database Systems for Approximate Nearest Neighbor Search: Performance, Quality, and Resource Trade-offs” is a 2026 preprint by Ashen Rashmiks and Tiroshan Madushanka, published in arXiv (Cornell University). OpenAlex counts 0 citations as of 16 November 2026. It is open access under a CC BY-NC-ND licence: the full text is free to read at arXiv (Cornell University).

Citations
0
Authors
2

Abstract

Vector databases have emerged as critical infrastructure for modern artificial intelligence applications, particularly retrieval-augmented generation (RAG), semantic search, and recommendation systems. Despite their growing importance, there remains a significant gap in comprehensive, reproducible benchmarks that jointly evaluate retrieval quality, query latency, throughput, and resource utilization. We present a systematic empirical evaluation of seven prominent vector database systems: FAISS, Qdrant, Milvus, Weaviate, Chroma, pgvector, and LanceDB. Our methodology spans six diverse datasets, from classical computer-vision descriptors (SIFT, GIST) to transformer-based text embeddings (MS MARCO, GloVe), encompassing over 4 million vectors at dimensionalities from 96 to 960. We measure 15 metrics spanning retrieval quality (Recall@K, Precision@K, MRR, NDCG@K, Hit Rate@K), query performance (latency percentiles, QPS, cold-start latency), and resource consumption (index build time, memory, storage). On SIFT1M, FAISS achieves the highest single-node throughput (866 QPS) but lacks database operational features; Weaviate provides the best out-of-the-box recall (> 99%); Qdrant offers the best latency among full databases (4.55~ms median); and LanceDB trades retrieval quality for substantially faster index construction. We derive system-selection guidelines for practitioners and release our benchmarking framework as open-source software.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Rashmiks, A., & Madushanka, T. (2026). A Comprehensive Empirical Evaluation of Vector Database Systems for Approximate Nearest Neighbor Search: Performance, Quality, and Resource Trade-offs. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2608.12812

MLA 9

Rashmiks, Ashen, and Tiroshan Madushanka. “A Comprehensive Empirical Evaluation of Vector Database Systems for Approximate Nearest Neighbor Search: Performance, Quality, and Resource Trade-offs.” arXiv (Cornell University), 2026. https://doi.org/10.48550/arxiv.2608.12812.

Chicago

Rashmiks, Ashen and Tiroshan Madushanka. 2026. “A Comprehensive Empirical Evaluation of Vector Database Systems for Approximate Nearest Neighbor Search: Performance, Quality, and Resource Trade-offs.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2608.12812.

Harvard

Rashmiks, A. and Madushanka, T. (2026) ‘A Comprehensive Empirical Evaluation of Vector Database Systems for Approximate Nearest Neighbor Search: Performance, Quality, and Resource Trade-offs’, arXiv (Cornell University). doi:10.48550/arxiv.2608.12812.

IEEE

A. Rashmiks and T. Madushanka, “A Comprehensive Empirical Evaluation of Vector Database Systems for Approximate Nearest Neighbor Search: Performance, Quality, and Resource Trade-offs,” arXiv (Cornell University), 2026, doi: 10.48550/arxiv.2608.12812.

BibTeX

@misc{rashmiks2026comprehensive,
  title     = {{A Comprehensive Empirical Evaluation of Vector Database Systems for Approximate Nearest Neighbor Search: Performance, Quality, and Resource Trade-offs}},
  author    = {Rashmiks, Ashen and Madushanka, Tiroshan},
  howpublished = {arXiv (Cornell University)},
  year      = {2026},
  doi       = {10.48550/arxiv.2608.12812},
  url       = {https://doi.org/10.48550/arxiv.2608.12812}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques

  • vector databases
  • approximate nearest neighbor search
  • benchmarking
  • retrieval effectiveness
  • query response time
  • throughput
  • resource allocation trade-offs
  • FAISS

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Rashmiks, A., & Madushanka, T. (2026). A Comprehensive Empirical Evaluation of Vector Database Systems for Approximate Nearest Neighbor Search: Performance, Quality, and Resource Trade-offs. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2608.12812

How many times has this paper been cited?

0 times, according to OpenAlex on 16 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at arXiv (Cornell University): sign in and open the PDF from this page.

Who wrote this paper?

Ashen Rashmiks, Tiroshan Madushanka.

What is the DOI of this paper?

10.48550/arxiv.2608.12812, permanently at https://doi.org/10.48550/arxiv.2608.12812. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 16 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.