Analytical benchmark

ClickBench, ClickHouse's benchmark for analytical workloads.

dataset
100M rows · 43 queries
field
517 systems
snapshot
Nov 2, 2026

Search engines on ClickBench

  1. 1 Infino SQL score, lower is better: 1.55×
  2. 2 OpenSearch SQL score, lower is better: 16.40×
  3. 3 Quickwit SQL score, lower is better: 19.39×
  4. 4 Elasticsearch SQL score, lower is better: 28.52×
  5. 5 SigLens SQL score, lower is better: 90.11×
  6. 6 ParadeDB SQL score, lower is better: 95.80×

Against every system on the board

  1. c8g.metal-48xl hot query speed: top 15% storage size: top 7%
  2. c7a.metal-48xl hot query speed: top 20% storage size: top 7%
  3. c6a.4xlarge hot query speed: top 40% storage size: top 8%

Reproduce

git clone https://github.com/ClickHouse/ClickBench && cd ClickBench/infino
./benchmark.sh

Questions

Why is hot the number to compare on ClickBench?

ClickBench runs each query three times. Cold is the first run, and hot is the best of the other two. Infino drops the OS page cache before every cold run and the reference engines do not, so only hot is measured the same way for every engine.

Which engines are ahead of Infino on ClickBench?

Infino is in the top 15% for hot query speed on c8g.metal-48xl. Umbra, CedarDB, DuckDB and ClickHouse builds lead. Infino is ahead of every DataFusion build and every ClickHouse-on-Parquet variant.

Why does a search engine run an analytics benchmark?

Agents ask questions that mix search with counting, grouping and joining, and Infino answers both. ClickBench checks the SQL half against analytics engines.

Search and SQL in one engine. Try it on your own data.

or run it yourself: pip install infino · Apache-2.0 · quickstart →