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 Added Most Hyped Most Active Needs Verification Most Verified

Showing 1–25 of 54 papers

Title	Date	Tasks	Status	Hype
Matbench Discovery -- A framework to evaluate machine learning crystal stability predictions	Aug 28, 2023	BenchmarkingFormation Energy	CodeCode Available	3
TensorNet: Cartesian Tensor Representations for Efficient Learning of Molecular Potentials	Jun 10, 2023	Formation Energy	CodeCode Available	2
Crystal-GFN: sampling crystals with desirable properties and constraints	Oct 7, 2023	Formation Energy	CodeCode Available	2
Discovery of 2D materials using Transformer Network based Generative Design	Jan 14, 2023	Formation EnergySelf-Learning	CodeCode Available	2
AutoMat: Enabling Automated Crystal Structure Reconstruction from Microscopy via Agentic Tool Use	May 19, 2025	DenoisingFormation Energy	CodeCode Available	1
Distributed Representations of Atoms and Materials for Machine Learning	Jul 30, 2021	Band GapBIG-bench Machine Learning	CodeCode Available	1
Heterogeneous Molecular Graph Neural Networks for Predicting Molecule Properties	Sep 26, 2020	Formation EnergyGraph Neural Network	CodeCode Available	1
Periodic Graph Transformers for Crystal Material Property Prediction	Sep 23, 2022	Band GapFormation Energy	CodeCode Available	1
SchNet: A continuous-filter convolutional neural network for modeling quantum interactions	Jun 26, 2017	Formation EnergyTime Series	CodeCode Available	1
Pushing the Pareto front of band gap and permittivity: ML-guided search for dielectric materials	Jan 11, 2024	Band GapDielectric Constant	CodeCode Available	1
Directional Message Passing for Molecular Graphs	Mar 6, 2020	Drug DiscoveryFormation Energy	CodeCode Available	1
Molecular Mechanics-Driven Graph Neural Network with Multiplex Graph for Molecular Structures	Nov 15, 2020	Drug DiscoveryFormation Energy	CodeCode Available	1
A Cartesian Encoding Graph Neural Network for Crystal Structures Property Prediction: Application to Thermal Ellipsoid Estimation	Jan 30, 2025	ADP PredictionBand Gap	CodeCode Available	1
CrysGNN : Distilling pre-trained knowledge to enhance property prediction for crystalline materials	Jan 14, 2023	Formation EnergyGraph Neural Network	CodeCode Available	1
Neural Message Passing for Quantum Chemistry	Apr 4, 2017	Drug DiscoveryFormation Energy	CodeCode Available	1
Semi-supervised teacher-student deep neural network for materials discovery	Dec 12, 2021	Formation Energyregression	CodeCode Available	1
Crystal Graph Neural Networks for Data Mining in Materials Science	May 27, 2019	Band GapFormation Energy	CodeCode Available	1
Materials Property Prediction with Uncertainty Quantification: A Benchmark Study	Nov 4, 2022	Active LearningBand Gap	CodeCode Available	1
InvDesFlow-AL: Active Learning-based Workflow for Inverse Design of Functional Materials	May 14, 2025	Active LearningFormation Energy	CodeCode Available	1
OQM9HK: A Large-Scale Graph Dataset for Machine Learning in Materials Science	Sep 30, 2022	Band GapFormation Energy	CodeCode Available	1
Physics Guided Deep Learning for Generative Design of Crystal Materials with Symmetry Constraints	Mar 27, 2022	Data AugmentationDiversity	CodeCode Available	1
CrysAtom: Distributed Representation of Atoms for Crystal Property Prediction	Sep 7, 2024	Formation EnergyGraph Neural Network	—Unverified	0
Interpretable Ensemble Learning for Materials Property Prediction with Classical Interatomic Potentials: Carbon as an Example	Jul 24, 2023	Ensemble LearningFormation Energy	—Unverified	0
Hierarchical modeling of molecular energies using a deep neural network	Sep 29, 2017	Drug DiscoveryFormation Energy	—Unverified	0
Learning formation energy of inorganic compounds using matrix variate deep Gaussian process	Dec 22, 2018	Formation Energy	—Unverified	0

Show:10 25 50

← PrevPage 1 of 3Next →

All datasets QM9 Materials Project JARVIS-DFT 3BPA Acetylacetone Aspirin Ethanol GeTe LiPS LiPS20 Naphthalene OQMD v1.2

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	HDAD+KRR	MAE	0.58	—	Unverified
2	MPNN	MAE	0.49	—	Unverified
3	SchNet	MAE	0.31	—	Unverified
4	ALIGNN	MAE	0.3	—	Unverified
5	MEGNet-simple	MAE	0.28	—	Unverified
6	HIP-NN	MAE	0.26	—	Unverified
7	SchNet-edge-update	MAE	0.24	—	Unverified
8	MEGNet-Full	MAE	0.21	—	Unverified
9	PhysNet	MAE	0.19	—	Unverified
10	DimeNet	MAE	0.19	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	MT-CGCNN	MAE	41	—	Unverified
2	CGCNN	MAE	39	—	Unverified
3	SchNet	MAE	35	—	Unverified
4	SchNet	MAE	31.8	—	Unverified
5	MEGNet	MAE	28	—	Unverified
6	SchNet-edge-update	MAE	22.7	—	Unverified
7	Matformer	MAE	21.2	—	Unverified
8	PotNet	MAE	18.8	—	Unverified
9	CartNet	MAE	17.47	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	CGCNN	MAE	0.06	—	Unverified
2	SchNet	MAE	0.05	—	Unverified
3	ALIGNN	MAE	0.03	—	Unverified
4	Matformer	MAE	0.03	—	Unverified
5	PotNet	MAE	0.03	—	Unverified
6	CartNet	MAE	0.03	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	BOTNet	MAE	5	—	Unverified
2	Allegro	MAE	4.13	—	Unverified
3	MACE	MAE	4	—	Unverified
4	NequIP	MAE	3.15	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	BOTNet	MAE	2	—	Unverified
2	MACE	MAE	2	—	Unverified
3	NequIP	MAE	1.38	—	Unverified
4	Allegro	MAE	0.92	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Allegro	MAE	14.36	—	Unverified
2	MACE	MAE	13.79	—	Unverified
3	BOTNet	MAE	12.63	—	Unverified
4	NequIP	MAE	9.27	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	MACE	MAE	209.96	—	Unverified
2	BOTNet	MAE	203.83	—	Unverified
3	Allegro	MAE	6.94	—	Unverified
4	NequIP	MAE	4.99	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	BOTNet	MAE	3,034	—	Unverified
2	MACE	MAE	2,670	—	Unverified
3	NequIP	MAE	1,780.95	—	Unverified
4	Allegro	MAE	1,009.4	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	NequIP	MAE	165.43	—	Unverified
2	Allegro	MAE	31.75	—	Unverified
3	MACE	MAE	30	—	Unverified
4	BOTNet	MAE	28	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Allegro	MAE	33.17	—	Unverified
2	NequIP	MAE	26.8	—	Unverified
3	BOTNet	MAE	24.59	—	Unverified
4	MACE	MAE	14.05	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	BOTNet	MAE	182.55	—	Unverified
2	MACE	MAE	161.74	—	Unverified
3	Allegro	MAE	5.82	—	Unverified
4	NequIP	MAE	2.66	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	CGNN-128	MAE	35.7	—	Unverified
2	CGNN-160	MAE	35.1	—	Unverified
3	CGNN-192	MAE	34.6	—	Unverified
4	CGNN Ensemble	MAE	30.5	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	MACE	MAE	165.29	—	Unverified
2	BOTNet	MAE	153.06	—	Unverified
3	Allegro	MAE	8.59	—	Unverified
4	NequIP	MAE	6.29	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	SchNet	MAE	0.31	—	Unverified
2	CGNN Trio Ensemble	MAE	0.04	—	Unverified
3	CGNN Full Ensemble	MAE	0.03	—	Unverified