GigaOm Study: Astra DB Smashes Pinecone in GenAI Performance
Astra DB significantly outperforms in throughput, latency, F1 relevance, and TCO (total cost-of-ownership)

This GigaOm report benchmarks Astra DB vector performance and TCO using several commonly-used vector benchmarking datasets that simulate production conditions. GigaOm then compares Astra DB performance to Pinecone, a widely used vector database.
The study finds that Astra DB had better performance than Pinecone, up to:
- 9x higher throughput than Pinecone when ingesting and indexing data
- 74x faster P99 query response time when ingesting and indexing data
- 20% higher F1 relevancy
- 80% lower total cost of ownership over a three-year period in three scenarios
Vector databases must deliver on four key metrics to successfully enable accurate generative AI and RAG (retrieval augmented generation) applications in production: throughput, latency, F1 relevancy, and total cost of ownership (TCO).