materialsproject/matbench

Matbench: Benchmarks for materials science property prediction

58
/ 100
Established

This helps materials scientists and researchers fairly compare and test different machine learning models designed to predict material properties. It provides a standardized set of materials science datasets and tasks, allowing you to feed in your model and get out a robust performance evaluation against established benchmarks. Materials engineers, computational chemists, and academic researchers focused on material discovery and design will find this valuable.

190 stars. Used by 1 other package. No commits in the last 6 months. Available on PyPI.

Use this if you are developing or evaluating machine learning models for materials property prediction and need a reliable, standardized way to benchmark their performance against others.

Not ideal if you are looking for a tool to develop or train new materials science machine learning models, as this project focuses on benchmarking existing models.

materials-science materials-discovery computational-materials materials-informatics property-prediction
Stale 6m
Maintenance 0 / 25
Adoption 11 / 25
Maturity 25 / 25
Community 22 / 25

How are scores calculated?

Stars

190

Forks

59

Language

Python

License

MIT

Last pushed

Aug 20, 2024

Commits (30d)

0

Dependencies

4

Reverse dependents

1

Get this data via API

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

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