$200 in free credits when you sign up with a work emailHow to read this leaderboard
Dataset Note:
- For "1M Dataset" below, we refer to the "Cohere Medium" (Click to copy S3 URI) Dataset (1M * 768 float dense vectors).
- For "10M" Dataset below, we refer to the "Cohere Large" (Click to copy S3 URI) Dataset (10M * 768 float dense vectors).
Streaming Performance
Copy link to this sectionThis chart benchmarks search performance on the Cohere-10M dataset under constant ingestion pressure. We measure p99 serial search latency and maximum concurrent QPS at 90% data capacity while the insertion workload remains active. These 'streaming' results are then contrasted with the 'static' performance on a fully indexed database.
Plot values
QPS
- static
- constant ingestion (500 rows/s)
- constant ingestion (1000 rows/s)
ZillizCloud
8cu-perf
Milvus
16c64g-sq8-force_merge
ElasticCloud
8c60g-force_merge
Pinecone
p2.x8-1node
TurboPuffer
2026-03-31
OpenSearch
16c128g
QdrantCloud
16c64g
Run VDBBench on your own data
These results use public datasets. Your vectors, filters and traffic decide what you actually get—run the same open-source benchmark on them.
Test Zilliz Cloud
Benchmark Zilliz Cloud on your data
- Sign up for Zilliz Cloud—$200 in free credits with a work email.
- Create a cluster and copy its endpoint and API key.
- Install VDBBench with
pip install vectordb-benchand start it withinit_bench. - Load your vectors as Parquet files on the Custom Dataset page and run the case against your cluster.
Test other databases
Benchmark the database you use today
- VDBBench is open source and supports Milvus, Elasticsearch, OpenSearch, pgvector, Pinecone, Qdrant, Weaviate, turbopuffer and more.
- Run the same case and dataset against your current database.
- Put the two results side by side: QPS, P99 latency, recall and cost.
Talk to us
Run it with a Zilliz engineer
Evaluating a migration from Elasticsearch, OpenSearch or pgvector, or running more than 100M vectors? A Zilliz engineer runs the benchmark on your data with you.
See these numbers on your workload
Start on Zilliz Cloud with $200 in free credits, or size a production workload with an engineer.