# CardBench: A Benchmark for Learned Cardinality Estimation in Relational Databases

arXiv: https://arxiv.org/abs/2408.16170 · HTML: https://mlsanity.com/paper/2408.16170/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 21 references that are in the map.
- First posted on arXiv 28 Aug 2024.

## Builds on (most cited first, 6 of 6)

- [Graph Transformer Networks](https://mlsanity.com/paper/1911.06455/) (2019)
- [Learned Cardinalities: Estimating Correlated Joins with Deep Learning](https://mlsanity.com/paper/1809.00677/) (2018)
- [Cardinality Estimation in DBMS: A Comprehensive Benchmark Evaluation](https://mlsanity.com/paper/2109.05877/) (2021)
- [Flow-Loss: Learning Cardinality Estimates That Matter](https://mlsanity.com/paper/2101.04964/) (2021)
- [Balsa: Learning a Query Optimizer Without Expert Demonstrations](https://mlsanity.com/paper/2201.01441/) (2022)
- [One Model to Rule them All: Towards Zero-Shot Learning for Databases](https://mlsanity.com/paper/2105.00642/) (2021)

## Built on by (most cited first, 4 of 4)

- [Is it Bigger than a Breadbox: Efficient Cardinality Estimation for Real World Workloads](https://mlsanity.com/paper/2510.03386/) (2025)
- [Optimize Cardinality Estimation Model Pretraining by Simplifying the Training Datasets](https://mlsanity.com/paper/2502.14350/) (2025)
- [Rel-HNN: Split Parallel Hypergraph Neural Network for Learning on Relational Databases](https://mlsanity.com/paper/2507.12562/) (2025)
- [TiCard: Deployable EXPLAIN-only Residual Learning for Cardinality Estimation](https://mlsanity.com/paper/2512.14358/) (2025)

## Abstract (arXiv)

Cardinality estimation is crucial for enabling high query performance in relational databases. Recently learned cardinality estimation models have been proposed to improve accuracy but there is no systematic benchmark or datasets which allows researchers to evaluate the progress made by new learned approaches and even systematically develop new learned approaches. In this paper, we are releasing a benchmark, containing thousands of queries over 20 distinct real-world databases for learned cardinality estimation. In contrast to other initial benchmarks, our benchmark is much more diverse and can be used for training and testing learned models systematically. Using this benchmark, we explored whether learned cardinality estimation can be transferred to an unseen dataset in a zero-shot manner. We trained GNN-based and transformer-based models to study the problem in three setups: 1-) instance-based, 2-) zero-shot, and 3-) fine-tuned. Our results show that while we get promising results for zero-shot cardinality estimation on simple single table queries; as soon as we add joins, the accuracy drops. However, we show that with fine-tuning, we can still utilize pre-trained models for cardinality estimation, significantly reducing training overheads compared to instance specific models. We are open sourcing our scripts to collect statistics, generate queries and training datasets to foster more extensive research, also from the ML community on the important problem of cardinality estimation and in particular improve on recent directions such as pre-trained cardinality estimation.