Skip to content

Model for surface energy of CHIPSFF dataset

  • Description: This is a benchmark to evaluate how accurately an AI model can predict the surface energy (J/m^2) using the CHIPSFF subset of JARVIS-DFT (dft_3d) dataset. The dataset contains different types of chemical formula and atomic structures of materials common to semiconductor device components. Here we use mean absolute error (MAE) to compare models with respect to DFT accuracy.


Reference(s): https://github.com/usnistgov/chipsff, https://doi.org/10.48550/arXiv.2305.11842, https://www.nature.com/articles/s41524-020-00440-1

Model benchmarks

Model name Dataset ACC Team name Dataset size Date submitted Notes
matgldft_3d_chipsff0.8858JARVIS8211-01-2024CSV, JSON, run.sh, Info
eqV2_31M_omatdft_3d_chipsff0.3199JARVIS8211-01-2024CSV, JSON, run.sh, Info
eqV2_153M_omatdft_3d_chipsff0.3261JARVIS8211-01-2024CSV, JSON, run.sh, Info
eqV2_86M_omatdft_3d_chipsff0.3652JARVIS8211-01-2024CSV, JSON, run.sh, Info
mace-alexandriadft_3d_chipsff0.6939JARVIS8211-01-2024CSV, JSON, run.sh, Info
orb-v2dft_3d_chipsff0.245JARVIS8211-01-2024CSV, JSON, run.sh, Info
chgnetdft_3d_chipsff0.665JARVIS8211-01-2024CSV, JSON, run.sh, Info
macedft_3d_chipsff0.4617JARVIS8211-01-2024CSV, JSON, run.sh, Info
matgl-directdft_3d_chipsff0.713JARVIS8211-01-2024CSV, JSON, run.sh, Info
eqV2_31M_omat_mp_salexdft_3d_chipsff0.2144JARVIS8211-01-2024CSV, JSON, run.sh, Info
alignn_ff_5_27_24dft_3d_chipsff1.4826JARVIS8211-01-2024CSV, JSON, run.sh, Info
alignn_ff_12_2_24dft_3d_chipsff1.9218JARVIS8211-01-2024CSV, JSON, run.sh, Info
sevennetdft_3d_chipsff0.3319JARVIS8211-01-2024CSV, JSON, run.sh, Info
eqV2_86M_omat_mp_salexdft_3d_chipsff0.2141JARVIS8211-01-2024CSV, JSON, run.sh, Info