pdebench/PDEBench

PDEBench: An Extensive Benchmark for Scientific Machine Learning

70
/ 100
Verified

This project provides a comprehensive benchmark for evaluating machine learning models designed to solve Partial Differential Equations (PDEs). It offers a wide range of realistic physical problems, along with ready-to-use datasets containing various initial/boundary conditions and PDE parameters. Scientists, engineers, and researchers working with scientific machine learning can use this to compare and develop methods for simulating complex physical phenomena.

1,082 stars. Actively maintained with 1 commit in the last 30 days. Available on PyPI.

Use this if you are developing or evaluating machine learning models for scientific simulations and need a diverse, challenging, and standardized set of physical problems and datasets.

Not ideal if you are looking for a standalone simulation tool or a deep learning library for general-purpose tasks outside of scientific machine learning benchmarks.

scientific-machine-learning computational-physics numerical-simulation differential-equations model-benchmarking
Maintenance 13 / 25
Adoption 10 / 25
Maturity 25 / 25
Community 22 / 25

How are scores calculated?

Stars

1,082

Forks

141

Language

Python

License

Last pushed

Feb 24, 2026

Commits (30d)

1

Dependencies

11

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/pdebench/PDEBench"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.