Skip to content

Model for open catalyst project 100k dataset

  • Description: This is a benchmark to evaluate how accurately an AI model can predict the relaxed energy a subset (~100k) Open Catalyst Project dataset. Here we use mean absolute error (MAE) to compare models with respect to DFT accuracy. External links: https://pubs.acs.org/doi/10.1021/acscatal.0c04525


Reference(s): https://github.com/Open-Catalyst-Project/ocp, https://www.nature.com/articles/s41524-021-00650-1, https://doi.org/10.1021/acscatal.0c04525

Model benchmarks

Model nameDataset MAE Team name Dataset size Date submitted Notes
ocp_schnet_100kocp100k0.7139OCP14988601-14-2023CSV, JSON, run.sh, Info
alignn_modelocp100k0.6289ALIGNN14988601-14-2023CSV, JSON, run.sh, Info
ocp_cgcnn_100kocp100k0.6826OCP14988601-14-2023CSV, JSON, run.sh, Info