Skip to main content

TPC-H Benchmark: Databend Cloud vs. Snowflake

Quick Overview


The TPC-H benchmark is a standard for evaluating decision support systems, focusing on complex queries and data maintenance. In this analysis, we compare Databend Cloud with Snowflake using the TPC-H SF100(SF1 = 6 Million Rows) dataset, encompassing 100GB of data and approximately 600 million rows across 22 queries.


The TPC Benchmark™ and TPC-H™ are trademarks of the Transaction Processing Performance Council (TPC). Our benchmark, while inspired by TPC-H, is not directly comparable to official TPC-H results.

Snowflake and Databend Cloud

  • Snowflake: Snowflake is renowned for its advanced features such as separating storage and compute, scalable computing on demand, data sharing, and cloning capabilities.

  • Databend Cloud: Databend Cloud offers similar functionalities to Snowflake, being a cloud-native data warehouse that also separates storage from computing and provides scalable computing as needed. It is developed from the open-source Databend project, positioning itself as a modern, cost-effective alternative to Snowflake, especially for large-scale analytics.

Performance and Cost Comparison

  • Data Loading Costs: Databend achieves a 67% cost reduction in data loading compared to Snowflake.
  • Query Execution Costs: Databend approximately 60% less expensive for query execution than Snowflake.

For this benchmark, no special tuning was applied. Both Snowflake and Databend Cloud were used with their default settings. And remember, don't just take our word for it — you're encouraged to run and verify these results yourself.

Data Loading Benchmark


TableSnowflake(695s, Cost $0.77)Databend Cloud(446s, Cost $0.25)Rows
Total Time695s446s
Total Cost$0.77$0.25
Storage Size20.8GB24.5GB

Query Benchmark: Cold Run


QuerySnowflake(Total 207s, Cost $0.23)Databend Cloud(Total 166s, Cost $0.09)
TPC-H 111.7038.036
TPC-H 24.5243.786
TPC-H 38.9086.040
TPC-H 48.1084.462
TPC-H 59.2027.014
TPC-H 61.2373.234
TPC-H 79.0827.345
TPC-H 810.8868.976
TPC-H 918.15213.340
TPC-H 1013.52512.891
TPC-H 112.5822.183
TPC-H 1210.0998.839
TPC-H 1313.4587.206
TPC-H 148.0014.612
TPC-H 158.7374.621
TPC-H 164.8641.645
TPC-H 175.36314.315
TPC-H 1819.97112.058
TPC-H 199.89312.579
TPC-H 208.5388.836
TPC-H 2116.43912.270
TPC-H 223.7441.926
Total Time207s166s
Total Cost$0.23$0.09

Query Benchmark: Hot Run


QuerySnowflake (Total 138s, Cost $0.15)Databend Cloud (Total 124s, Cost $0.07)
TPC-H 18.9347.568
TPC-H 23.0183.125
TPC-H 36.0895.234
TPC-H 44.9143.392
TPC-H 55.8004.857
TPC-H 60.8912.142
TPC-H 75.3814.389
TPC-H 85.7245.887
TPC-H 910.2839.621
TPC-H 1010.3688.524
TPC-H 111.1651.364
TPC-H 127.0525.352
TPC-H 1312.8296.180
TPC-H 143.2882.725
TPC-H 153.4752.748
TPC-H 164.0941.124
TPC-H 174.20313.757
TPC-H 1818.58311.630
TPC-H 193.8887.881
TPC-H 206.3795.797
TPC-H 2110.2879.806
TPC-H 221.5731.122
Total Time138s124s
Total Cost$0.15$0.07

Reproduce the Benchmark

You can reproduce the benchmark by following the steps below.

Benchmark Environment

Both Snowflake and Databend Cloud was tested under similar conditions:

ParameterSnowflakeDatabend Cloud
Warehouse SizeSmallSmall
AWS Regionus-east-2us-east-2
StorageAWS S3AWS S3
  • The TPC-H SF100 dataset, sourced from Amazon Redshift, was loaded into both Databend Cloud and Snowflake without any specific tuning.

Benchmark Methodology

We conducted both Cold and Hot runs for query execution:

  1. Cold Run: The data warehouse was suspended and resumed before executing the queries.
  2. Hot Run: The data warehouse is not suspended, local disk cache is used.


Data Loading

  1. Snowflake Data Load:

  2. Databend Cloud Data Load:

TPC-H Queries

  1. Snowflake Queries:

  2. Databend Cloud Queries:

Did this page help you?