# GraphBench: Next-generation graph learning benchmarking

arXiv: https://arxiv.org/abs/2512.04475 · HTML: https://mlsanity.com/paper/2512.04475/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Dec 2025.

## Built on by (most cited first, 8 of 8)

- [A Fair Evaluation of Graph Foundation Models for Node Property Prediction](https://mlsanity.com/paper/2606.24509/) (2026)
- [Rethinking GNNs and Missing Features: Challenges, Evaluation and a Robust Solution](https://mlsanity.com/paper/2601.04855/) (2026)
- [Position: Don't be Afraid of Over-Smoothing And Over-Squashing](https://mlsanity.com/paper/2601.07419/) (2026)
- [Surprisingly Simple and Effective Multi-Domain Graph Foundation Model through Graph-to-Table Alignment](https://mlsanity.com/paper/2607.11374/) (2026)
- [GraIP: A Benchmarking Framework For Neural Graph Inverse Problems](https://mlsanity.com/paper/2601.18917/) (2026)
- [A Fresh Look at Lamarckian Evolution and the Baldwin Effect](https://mlsanity.com/paper/2605.28703/) (2026)
- [When Vision Meets Graphs: A Survey on Graph Reasoning and Learning](https://mlsanity.com/paper/2609.03816/) (2026)
- [The Universal Classifier for Graph Learning](https://mlsanity.com/paper/2609.36302/) (2026)

## Abstract (arXiv)

Machine learning on graphs has made substantial progress across domains such as molecular property prediction and chip design. Yet benchmarking practices remain fragmented, often relying on narrow, task-specific datasets and inconsistent evaluation protocols, hindering reproducibility and broader progress. With the recent popularity of graph foundation models, these weaknesses have become apparent, as existing benchmarks are insufficient for thorough evaluation. To address these challenges, we introduce GraphBench, a comprehensive benchmark suite spanning diverse real-world domains and task settings, including node-level, edge-level, graph-level, and generative tasks. GraphBench provides standardized evaluation protocols, including consistent dataset splits and metrics for assessing out-of-distribution generalization across selected tasks, as well as a unified hyperparameter-tuning framework. We further evaluate GraphBench with recent message-passing neural networks and graph transformer models, establishing principled baselines for future research. See www.graphbench.io for further details.