OMol25 Family

5 datasets | 142M total configurations

Open Molecules 2025 datasets from Meta/FAIR Chemistry. Datasets created to train models with more diverse molecular structures with highly accurate calculations.

Overview

Datasets

Total Downloads

2,498

Total Configurations

142M

Unique Elements

Property Types

Methods Used

Elements Included

83 Elements

Ag Al Ar As Au B Ba Be Bi Br C Ca Cd Ce Cl Co Cr Cs Cu Dy Er Eu F Fe Ga Gd Ge H He Hf Hg Ho I In Ir K Kr La Li Lu Mg Mn Mo N Na Nb Nd Ne Ni O Os P Pb Pd Pm Pr Pt Rb Re Rh Ru S Sb Sc Se Si Sm Sn Sr Ta Tb Tc Te Ti Tl Tm V W Xe Y Yb Zn Zr

Calculated Properties

2 Property Types

Energy (5 datasets) Atomic Forces (5 datasets)

Methods

1 Methods

DFT-ωB97M-V

Software

1 Software

ORCA

Related Families

1 Related Families

Member Datasets

5 Datasets

Format:

Dataset Name	Downloads	Configurations	Elements	Properties	Links
OMol25_neutral_validation The neutral validation set from OMol25. From the dataset creator: OMol25 represents the largest high quality molecular D...	139	27,697	17	2	View DOI
OMol25_train The full-size training set from OMol25. From the dataset creator: OMol25 represents the largest high quality molecular D...	1,547	101,666,280	83	2	View DOI
OMol25_train_4M The Train 4M set from OMol25 (~4 million structure training subset). From the dataset creator: OMol25 represents the lar...	621	3,986,754	83	2	View DOI
OMol25_train_neutral The Train neutral set from OMol25. From the dataset creator: OMol25 represents the largest high quality molecular DFT da...	150	34,335,828	17	2	View DOI
OMol25_validation The validation set from OMol25. From the dataset creator: OMol25 represents the largest high quality molecular DFT datas...	41	2,762,021	83	2	View DOI