Add S30L benchmark #147
Merged
Add S30L benchmark #147
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
ElliottKasoar
added
the
new benchmark
Collaborator
Author
|
This also includes weights, which hopefully work once #109 is merged, so only the overall MAE is used by default. |
joehart2001
reviewed
Nov 12, 2025
joehart2001
previously approved these changes
Nov 12, 2025
Collaborator
joehart2001
left a comment
joehart2001
left a comment
There was a problem hiding this comment.
all good, just need to update analysis after gmtkn is in main
ElliottKasoar
force-pushed
the
add-supra-S30L
branch
from
3a34898 to
463e3a3
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Pre-review checklist for PR author
PR author must check the checkboxes below when creating the PR.
Summary
Add S30L benchmark, including MAEs for neutral and charged complexes.
Linked issue
Resolves #100
Progress
Testing
Tested on MACE models, Orb, MatterSim and UMA models. MACE and Orb results agree with https://arxiv.org/pdf/2510.25380 for overall MAE.
MatterSim differs slightly, and UMA differs significantly, but is closer to the result here: http://mlip-testing.stfc.ac.uk:8050 (which does not include D3 correction.
New decorators/callbacks
None