Ploba logo

Find the right AI tool for the job: apps, agents, APIs, MCP servers and datasets, explained plainly.

Get the AI Digest

Discover

  • Explore
  • Top Charts
  • Categories
  • Agents
  • MCP servers
  • Developer tools

Learn & community

  • Learn AI
  • AI Glossary
  • Blog
  • Hackathons
  • People
  • AI Digest

For makers

  • List your tool
  • Docs
  • Claim a listing
  • Advertise
  • Write for us

Company

  • About
  • Careers
  • Changelog
  • Trust
  • Security
  • Contact

© 2026 Ploba. All rights reserved.

  • Privacy
  • Terms
  • Cookies
  • Advertising
  • All policies
llms.txt
Ploba logo
DiscoverHackathonsPeopleLearnAI Digest
Sign inGet started
HomeTop ChartsExploreCategories
TypesWeb apps1,894Agents585Plugins416APIs376Mobile apps152Datasets85
AdvertisingYour product hereReach people browsing AI tools on Ploba.Advertise hereAdvertisingYour product hereReach people browsing AI tools on Ploba.Advertise here
  1. Explore
  2. /
  3. Data
  4. /
  5. Matbench Discovery
Data
Matbench Discovery icon

Matbench Discovery

by Materials Project

Matbench Discovery is a leaderboard that benchmarks machine-learning force fields on crystal discovery, geometry optimization, phonons, molecular dynamics and diatomics.

Dataset·Free

Visit matbench-discovery.materialsproject.org(opens in a new tab)

About Matbench Discovery

Key features of Matbench Discovery

  • Leaderboard of machine-learning force fields
  • Presets for discovery, geometry optimization, phonons, MD and diatomics
  • Combined score with published weights
  • Filters by training data, openness and targets
  • Adjustable score weights
  • Export of the table
  • Progress-over-time chart
  • Model submission and RSS feed

Who Matbench Discovery is for

  • Materials informatics researchers
  • Developers of machine-learning interatomic potentials
  • Teams choosing a force field for crystal discovery

How to use Matbench Discovery

  1. 1

    Step 1: Open the leaderboard and pick a column preset.

  2. 2

    Step 2: Choose the full test set or unique prototypes.

  3. 3

    Step 3: Filter by training data, openness or targets.

  4. 4

    Step 4: Adjust the score weights if you value a task differently.

  5. 5

    Step 5: Export the table, or use the submit a model link to add your own.

Matbench Discovery FAQ

How is the combined score built?

It weights discovery F1 at 50%, geometry RMSD at 10% and phonon thermal conductivity error at 40%. MD and diatomics are left out.

Can I change the weights?

Yes. The page has weight controls, and the other weights adjust proportionally so the total stays at 100%.

Can I submit my own model?

Yes. The page has a Submit a model link.

Can I filter the models?

Yes. You can filter by training data, openness and targets, and require models that predict forces.

Details

Pricing
Free
Type
Dataset
Categories
DataResearch
Added
Sep 16, 2026
Materials Project iconPublisherMaterials Project

Built from public sources

We put this page together from Matbench Discovery’s own website and docs so you can compare it with other tools. Ploba isn’t affiliated with Matbench Discovery.

Work at Matbench Discovery? Claim the listing to manage it yourself.

Something wrong here?

Related tools

See more
Claude Protein Binder Design iconClaude Protein Binder DesignAnthropic · FreeA data release of 1,440 de novo miniprotein binders designed by Claude models acting as autonomous protein-design agents, with wet-lab results from two contract research organizations. It covers 16 targets.Data · FreeQoQokedasQokedas · Contact for pricingTraining-data company that turns real-world scientific signals and observations that are not normally written down into datasets for improving AI models in science.AI · Contact for pricingPBPretrain BehaviorsIFM · FreePretrain-Behaviors is a behavior-focused text dataset from IFM covering reasoning, planning, data science, games and format rewriting. It is part of the K2 Horizon collection.AI · Free