Benchmarks
Vector benchmark
#1 at 1M and 10M
VectorDBBench, Milvus's benchmark for vector databases
- 1 Infino
- 2 OceanBase
- 3 Elasticsearch
- 4 Milvus
- 5 pgvector
- 1 Infino
- 2 Milvus
- 3 pgvecto.rs
- 4 pgvector
- 5 Qdrant
Full-text search benchmark
54% faster than Lucene on top-k
Search Benchmark, the Game: Tantivy's benchmark for full-text search engines
- 1 Infino 0.11.26
- 2 Lucene, reordered
- 3 Lucene
- 4 Tantivy
- 1 Infino 0.11.26
- 2 Tantivy
- 3 Lucene, reordered
- 4 Lucene
Analytical benchmark
#1 of 6 search engines
ClickBench, ClickHouse's benchmark for analytical workloads
- 1 Infino
- 2 OpenSearch
- 3 Quickwit
- 4 Elasticsearch
- 5 SigLens
- 6 ParadeDB
Embedded vector benchmark
0.963 recall@10 at 1.5 ms
retrievalbench, a benchmark for embedded vector search libraries
- 1 Infino flat_ivf
- 2 FAISS PQ 8-bit
- 3 turbovec 4-bit
- 4 turbovec 2-bit
- 5 FAISS PQ fastscan
- Infino flat_ivf
- turbovec 4-bit
- turbovec 2-bit
- FAISS PQ fastscan
- FAISS PQ 8-bit
Accuracy benchmark
#1 in accuracy
OfficeQA Pro, Databricks' benchmark for grounded reasoning over documents
- 1 Supermodel + Claude Opus 5.5
- 2 Mixedbread Toast + GPT-5.6 Sol
- 3 Databricks Genie + Claude Fable 5
- 4 Snowflake Cortex Agent
- 5 Claude Opus 5.5 alone
Questions
Can I reproduce these numbers?
Yes for the four engine benchmarks. Each page has the command, and every published result names the engine version it ran. The OfficeQA page links Databricks' benchmark repository.
Where is Infino behind?
On ClickBench, Infino is in the top 15% of all systems for hot query speed on c8g.metal-48xl. Umbra, CedarDB, DuckDB and ClickHouse are ahead.
Measured. Now try it on your own data.
or run it yourself: pip install infino · Apache-2.0 · quickstart →