SOTAVerified

Formation Energy

On the QM9 dataset the numbers reported in the table are the mean absolute error in eV on the target variable U0 divided by U0's chemical accuracy, which is equal to 0.043.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–10 of 54 papers

TitleStatusHype
Advancing Magnetic Materials Discovery -- A structure-based machine learning approach for magnetic ordering and magnetic moment prediction—0
AutoMat: Enabling Automated Crystal Structure Reconstruction from Microscopy via Agentic Tool UseCode1
InvDesFlow-AL: Active Learning-based Workflow for Inverse Design of Functional MaterialsCode1
MatMMFuse: Multi-Modal Fusion model for Material Property PredictionCode0
The Vendiscope: An Algorithmic Microscope For Data Collections—0
A Cartesian Encoding Graph Neural Network for Crystal Structures Property Prediction: Application to Thermal Ellipsoid EstimationCode1
SynCoTrain: A Dual Classifier PU-learning Framework for Synthesizability Prediction—0
Material Property Prediction with Element Attribute Knowledge Graphs and Multimodal Representation Learning—0
Unleashing the power of novel conditional generative approaches for new materials discoveryCode0
Generative Hierarchical Materials Search—0
Show:102550
← PrevPage 1 of 6Next →
All datasetsQM9Materials ProjectJARVIS-DFT3BPAAcetylacetoneAspirinEthanolGeTeLiPSLiPS20NaphthaleneOQMD v1.2

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1HDAD+KRRMAE0.58—Unverified
2MPNNMAE0.49—Unverified
3SchNetMAE0.31—Unverified
4ALIGNNMAE0.3—Unverified
5MEGNet-simpleMAE0.28—Unverified
6HIP-NNMAE0.26—Unverified
7SchNet-edge-updateMAE0.24—Unverified
8MEGNet-FullMAE0.21—Unverified
9PhysNetMAE0.19—Unverified
10DimeNetMAE0.19—Unverified