Skip to content

Model for ehull

  • Description: This is a benchmark to evaluate how accurately an AI model can predict the energy above the convex hull (Ehull) using the JARVIS-DFT (dft_3d) dataset. The dataset contains different types of chemical formula and atomic structures. Here we use mean absolute error (MAE) to compare models with respect to DFT accuracy.


Model benchmarks

Model nameDataset MAE Team name Dataset size Date submitted Notes
potnetdft_3d0.0522DIVE@TAMU5536406-02-2023CSV, JSON,, Info
kgcnn_coGNdft_3d0.0466kgcnn5536405-06-2023CSV, JSON,, Info
cgcnn_modeldft_3d0.173CGCNN5536401-14-2023CSV, JSON,, Info
alignn_modeldft_3d0.0763ALIGNN5536401-14-2023CSV, JSON,, Info
kgcnn_schnetdft_3d0.1014kgcnn5536409-26-2023CSV, JSON,, Info
matminer_rfdft_3d0.112UofT5536405-22-2023CSV, JSON,, Info
kgcnn_dimenetPPdft_3d0.3685kgcnn5536405-06-2023CSV, JSON,, Info
kgcnn_coNGNdft_3d0.0485kgcnn5536405-06-2023CSV, JSON,, Info
kgcnn_megnetdft_3d0.0569kgcnn5536405-06-2023CSV, JSON,, Info
kgcnn_cgcnndft_3d0.059kgcnn5536409-26-2023CSV, JSON,, Info
matminer_xgboostdft_3d0.0601UofT5536405-22-2023CSV, JSON,, Info