janosh / matbench-discovery
An evaluation framework for machine learning models simulating high-throughput materials discovery.
Why this job: says: evaluation framework
What it does
Matbench Discovery is an interactive leaderboard that ranks ML interatomic potentials across crystal stability prediction, geometry optimization, phonons and thermal conductivity, molecular dynamics, and diatomic potential-energy curves.
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit 8 days ago
- Stars
- 259
- +1 this week
- Licence
- MIT
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- v1.3.1
- Released 2 years ago
- Built with
- Python
- 59% of the code
Is it looked after?
- Contributors
- 7
- Last 90 days
- Issues
- 100% closed
- 0 still open
- Pull requests
- 268 merged
- 0 waiting
- Releases
- 8
- 0 in the last year
- Contributing guide (opens in new tab)
- No security policy
- No code of conduct
More: languages, topics and project record
Languages
- Python 59%
- TypeScript 25%
- Svelte 12%
- Typst 4%
Topics
- bayesian-optimization
- convex-hull
- machine-learning
- materials-discovery
- high-throughput-search
- interatomic-potential
Project record
- JobEvals and observability
- StatusListed
- Commits629
- Forks79
- Watching10
- Stars in 28 days+5
- CreatedJun 20, 2022
- First seen by usNov 7, 2026
- CheckedNov 9, 2026