---
title: "Measuring real-time performance per dollar under continuous load: CostBench’s first end-to-end results"
description: "CostBench measures real-time performance per dollar by evaluating the full path from continuously arriving rows to query-ready data and query results. Its end-to-end workload streams more than 100 billion stock-market quotes at a target rate of 1 million rows per second while aggregate and drill-down queries run, comparing ClickHouse Cloud, Snowflake, BigQuery, and Redshift Serverless through their recommended push-based ingestion paths. The benchmark accounts for fresh-data-path work—columnar ingestion, pruning-friendly layouts, and current pre-aggregations—alongside query-serving cost and accumulated runtime. ClickHouse Cloud recorded the lowest fresh-data-path cost, query-serving cost, and accumulated runtime, while the alternatives showed 412–1,996× worse end-to-end performance per dollar; the source says it was the only tested system keeping both data representations current during ingestion. The post introduces follow-up architecture and billing analyses."
---

# Measuring real-time performance per dollar under continuous load: CostBench’s first end-to-end results

[Clickhouse](https://yomu.fyi/company/clickhouse) · Sep 8, 2026

**Type:** Benchmark

## Summary

CostBench measures real-time performance per dollar by evaluating the full path from continuously arriving rows to query-ready data and query results. Its end-to-end workload streams more than 100 billion stock-market quotes at a target rate of 1 million rows per second while aggregate and drill-down queries run, comparing ClickHouse Cloud, Snowflake, BigQuery, and Redshift Serverless through their recommended push-based ingestion paths. The benchmark accounts for fresh-data-path work—columnar ingestion, pruning-friendly layouts, and current pre-aggregations—alongside query-serving cost and accumulated runtime. ClickHouse Cloud recorded the lowest fresh-data-path cost, query-serving cost, and accumulated runtime, while the alternatives showed 412–1,996× worse end-to-end performance per dollar; the source says it was the only tested system keeping both data representations current during ingestion. The post introduces follow-up architecture and billing analyses.

## Context

Real-time analytics systems must ingest new rows and make them query-ready while users, applications, and agents continue running queries. The post identifies fresh-data-path work and query execution as both contributors to performance per dollar, because unfinished layout or pre-aggregation work can leave more filtering, grouping, and aggregation for queries.

## Approach / What changed

CostBench runs a continuous workload in which more than 100 billion stock-market quotes are streamed at a target rate of 1 million rows per second while aggregate and drill-down queries execute. It compares ClickHouse Cloud, Snowflake, BigQuery, and Redshift Serverless using each provider’s recommended push-based ingestion path, combining fresh-data-path cost with normalized query-serving cost and accumulated query runtime.

## Takeaways

- Query-ready analytical data uses columnar storage, pruning-friendly physical layouts, and current pre-aggregations to reduce data read and repeated query-time work.
- The benchmark’s end-to-end comparison expands the isolated query-side gap of 32–101× worse cost-performance to 412–1,996× when continuous ingestion and query-readiness work are included.
- ClickHouse Cloud had the lowest fresh-data-path cost, query-serving cost, and accumulated query runtime, and was the only tested system reported to keep both event-level and pre-aggregated data current during ingestion.

**Tags:** [ClickHouse](https://yomu.fyi/topic/clickhouse), [Performance](https://yomu.fyi/topic/performance), [Streaming](https://yomu.fyi/topic/streaming)

- Source: [Clickhouse](https://clickhouse.com/blog/costbench-real-time-performance-per-dollar)
- Source URL: https://clickhouse.com/blog/costbench-real-time-performance-per-dollar
- Ingested by Yomu: 2026-09-08T08:00:48.857Z

[Read original post](https://clickhouse.com/blog/costbench-real-time-performance-per-dollar)