vector-db-benchmark and VBench
These are competitors—both provide benchmarking frameworks for evaluating vector search performance, though Qdrant's benchmark is more mature and focused on specialized vector databases while VBench targets vector analytics within relational databases.
About vector-db-benchmark
qdrant/vector-db-benchmark
Framework for benchmarking vector search engines
Supports benchmarking across multiple vector databases (Qdrant, Weaviate, Milvus, etc.) with pluggable engine implementations and configurable scenarios covering connection, indexing, data upload, and query phases. Uses a distributed server-client architecture with Docker-based engine deployment and Python clients, allowing parameter tuning via JSON configurations and wildcard-based test selection. Integrates datasets automatically via a central registry and produces standardized performance metrics across different hardware setups for comparative analysis.
About VBench
microsoft/VBench
An Approximate Vector-Analytics Benchmark for Relational Databases
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work