Benchmarking Universal Machine Learning Interatomic Potentials on Elemental Systems

Benchmarking Universal Machine Learning Interatomic Potentials on Elemental Systems | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Article Benchmarking Universal Machine Learning Interatomic Potentials on Elemental Systems Hossein Tahmasbi, Andreas Knüpfer, Thoams D. Kühne, Hossein Mirhosseini This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8763679/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 11 You are reading this latest preprint version Abstract The rapid emergence of universal Machine Learning Interatomic Potentials (uMLIPs) has transformed materials modeling. Nevertheless, a comprehensive understanding of their generalization behavior across configurational space remains an open challenge.In this work, we introduce a benchmarking framework to evaluate both the equilibrium and far-from-equilibrium performance of state-of-the-art uMLIPs, including two MACE-based models, two PET-based models, MatterSim, and a custom MACE model trained exclusively on elemental data. Our assessment utilizes Equation-of-State (EOS) tests to evaluate near-equilibrium properties, such as equilibrium volumes and bulk moduli, alongside extensive Minima Hopping (MH) structural searches to probe the Potential Energy Surface (PES). Here, we assess universality within the fundamental limit of elemental systems, which serve as a necessary baseline for broader chemical generalization and provide a framework that can be systematically extended to multicomponent materials. We find that while most models exhibit high accuracy in reproducing equilibrium volumes for transition metals, significant performance gaps emerge in alkali and alkaline earth metal groups as well as reactive nonmetals. Crucially, our MH results reveal a decoupling between search efficiency and structural fidelity, highlighting that smoother learned PESs do not necessarily yield more accurate energetic landscapes. Physical sciences/Chemistry Physical sciences/Materials science Physical sciences/Physics benchmarking universal machine learning interatomic potential foundation model equation of state minima hopping Full Text Additional Declarations No competing interests reported. Supplementary Files FMSI.pdf Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 15 Mar, 2026 Reviews received at journal 13 Mar, 2026 Reviews received at journal 11 Mar, 2026 Reviews received at journal 04 Mar, 2026 Reviewers agreed at journal 15 Feb, 2026 Reviewers agreed at journal 13 Feb, 2026 Reviewers agreed at journal 13 Feb, 2026 Reviewers invited by journal 13 Feb, 2026 Editor assigned by journal 06 Feb, 2026 Submission checks completed at journal 06 Feb, 2026 First submitted to journal 02 Feb, 2026 You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-8763679","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":591954847,"identity":"e813d007-71aa-463d-848f-624986ae0039","order_by":0,"name":"Hossein Tahmasbi","email":"","orcid":"","institution":"Center for Advanced Systems Understanding","correspondingAuthor":false,"prefix":"","firstName":"Hossein","middleName":"","lastName":"Tahmasbi","suffix":""},{"id":591954848,"identity":"be920043-22a5-45b5-a9b3-665e5033cba6","order_by":1,"name":"Andreas Knüpfer","email":"","orcid":"","institution":"Center for Advanced Systems Understanding","correspondingAuthor":false,"prefix":"","firstName":"Andreas","middleName":"","lastName":"Knüpfer","suffix":""},{"id":591954849,"identity":"bc147073-2288-4b59-9882-17731d6fd8b9","order_by":2,"name":"Thoams D. Kühne","email":"","orcid":"","institution":"Center for Advanced Systems Understanding","correspondingAuthor":false,"prefix":"","firstName":"Thoams","middleName":"D.","lastName":"Kühne","suffix":""},{"id":591954850,"identity":"1e6e4821-afa2-4fd9-ab5c-37571293103e","order_by":3,"name":"Hossein Mirhosseini","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA2UlEQVRIiWNgGAWjYBACAyA+wNgAYgLJhIoDQC4DgwQJWs4QqYUBogXEaCNCizkDd+Lhyh029vLtzW0PHs67Y893+wDjjQ94tFg28G44ePZMWuKGMwfbDRK3PWOWPJfAbDkDn8MOALU0th1OMJBIbJNI3HaYzeAMA5s0DxFa7OXnPwRqmXOYB6zlDxFaGBtuMAK1NByWAGvB532Dw2AtIL8AHZZw7LCB5BnGZssefFqO927+2NgGCrHjzyR/1By25zvDfPDGD3zWMGMKwaNpFIyCUTAKRgG5AADjDFhF+6DduwAAAABJRU5ErkJggg==","orcid":"","institution":"Center for Advanced Systems Understanding","correspondingAuthor":true,"prefix":"","firstName":"Hossein","middleName":"","lastName":"Mirhosseini","suffix":""}],"badges":[],"createdAt":"2026-02-02 10:27:39","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8763679/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8763679/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":103049420,"identity":"a61bb227-327e-4430-9658-3e69772f658c","added_by":"auto","created_at":"2026-02-20 07:41:04","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":5202458,"visible":true,"origin":"","legend":"","description":"","filename":"FM.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8763679/v1_covered_c8dc8d61-9cab-4476-a16a-b78bac7aa493.pdf"},{"id":102899481,"identity":"7798756a-bd71-4e2a-9d50-d6e1842db66a","added_by":"auto","created_at":"2026-02-18 07:48:33","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":716005,"visible":true,"origin":"","legend":"","description":"","filename":"FMSI.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8763679/v1/a2289425a6339a3da0586349.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Benchmarking Universal Machine Learning Interatomic Potentials on Elemental Systems","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"npj-computational-materials","isNatureJournal":false,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"npjcompumats","sideBox":"Learn more about [npj Computational Materials](http://www.nature.com/npjcompumats/)","snPcode":"41524","submissionUrl":"https://mts-npjcompumats.nature.com/","title":"npj Computational Materials","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"ejp","reportingPortfolio":"NPJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"benchmarking, universal machine learning interatomic potential, foundation model, equation of state, minima hopping","lastPublishedDoi":"10.21203/rs.3.rs-8763679/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8763679/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"The rapid emergence of universal Machine Learning Interatomic Potentials (uMLIPs) has transformed materials modeling. Nevertheless, a comprehensive understanding of their generalization behavior across configurational space remains an open challenge.In this work, we introduce a benchmarking framework to evaluate both the equilibrium and far-from-equilibrium performance of state-of-the-art uMLIPs, including two MACE-based models, two PET-based models, MatterSim, and a custom MACE model trained exclusively on elemental data. Our assessment utilizes Equation-of-State (EOS) tests to evaluate near-equilibrium properties, such as equilibrium volumes and bulk moduli, alongside extensive Minima Hopping (MH) structural searches to probe the Potential Energy Surface (PES). Here, we assess universality within the fundamental limit of elemental systems, which serve as a necessary baseline for broader chemical generalization and provide a framework that can be systematically extended to multicomponent materials. We find that while most models exhibit high accuracy in reproducing equilibrium volumes for transition metals, significant performance gaps emerge in alkali and alkaline earth metal groups as well as reactive nonmetals. Crucially, our MH results reveal a decoupling between search efficiency and structural fidelity, highlighting that smoother learned PESs do not necessarily yield more accurate energetic landscapes.","manuscriptTitle":"Benchmarking Universal Machine Learning Interatomic Potentials on Elemental Systems","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-02-18 07:48:28","doi":"10.21203/rs.3.rs-8763679/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-03-15T20:17:09+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-03-13T10:51:12+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-03-11T17:02:30+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-03-05T01:03:41+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"242926715516928523928374983752138707642","date":"2026-02-15T22:07:09+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"82867253438438736341358814819676910712","date":"2026-02-13T09:09:49+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"87215364599088964871512816827510850098","date":"2026-02-13T08:02:24+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-02-13T07:19:52+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-02-07T01:10:27+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-02-06T11:52:42+00:00","index":"","fulltext":""},{"type":"submitted","content":"npj Computational Materials","date":"2026-02-02T10:19:10+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"npj-computational-materials","isNatureJournal":false,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"npjcompumats","sideBox":"Learn more about [npj Computational Materials](http://www.nature.com/npjcompumats/)","snPcode":"41524","submissionUrl":"https://mts-npjcompumats.nature.com/","title":"npj Computational Materials","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"ejp","reportingPortfolio":"NPJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"ca63b12c-921e-4aef-be9f-c2ecf04860c9","owner":[],"postedDate":"February 18th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":62987234,"name":"Physical sciences/Chemistry"},{"id":62987235,"name":"Physical sciences/Materials science"},{"id":62987236,"name":"Physical sciences/Physics"}],"tags":[],"updatedAt":"2026-05-05T16:08:45+00:00","versionOfRecord":[],"versionCreatedAt":"2026-02-18 07:48:28","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8763679","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8763679","identity":"rs-8763679","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}