Join me if you can: ClickHouse vs. Databricks vs. Snowflake - Part 2

T1Covered by 1 source · first reported by Databricks / ClickHouse / DuckDB / Supabase / Neon / PlanetScale at 25 Jun 2025, 00:00 UTC

We took the same JOIN-heavy benchmark from Part 1 and made ClickHouse even faster. By replacing JOINs with in-memory dictionaries, we saw up to 6.6× faster queries and over 60% cost savings, with no data reloading or schema rewrites required.

Sources

• T1Join me if you can: ClickHouse vs. Databricks vs. Snowflake - Part 2Databricks / ClickHouse / DuckDB / Supabase / Neon / PlanetScale25 Jun 2025, 00:00