zilliztech/VectorDBBench

Health v2 · maintenance only

Adoption not part of the score

1166 stars · 431 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

VectorDBBench (VDBBench) is an open-source Python benchmark tool for comparing the performance and cost-effectiveness of vector databases and cloud vector services. It provides a visual interface, public datasets, and reproducible test scenarios including insertion, search, filtered search, and full-text (BM25) retrieval.

Use cases

• benchmark vector database performance
• compare vector database cost-effectiveness
• reproduce vector database benchmark results
• test qps and recall of vector search systems
• evaluate cloud vector database services
• benchmark full text search bm25 retrieval
• choose the best vector database for my workload

When to choose

• you need to compare vector databases like Milvus, Qdrant, Pinecone, or Elastic on QPS, latency, and recall
• you want reproducible benchmarks with real-world datasets such as SIFT, GIST, or Cohere
• you need cost-effectiveness reports for cloud vector services
• you want a GUI plus CLI to run and visualize benchmark results

When to avoid

• you need to benchmark non-vector databases like SQL or document stores
• you only need a published leaderboard without running your own tests
• your system under test is not among the supported database clients

Facets

cli-tool · maturity active

benchmarking vector-database search-engine data-visualization databases performance developer-tools python cli cross-platform vector-search vectordb qps recall cost-effectiveness leaderboard load-testing search

Member repositories

For agents

markdown · JSON · MCP: product_card(name="zilliztech/VectorDBBench")