Skip to content

Model for Vacancy formation energy for oxides

  • Description: This is a benchmark to evaluate how accurately an AI model can predict vacancy formation energy for a subset of oxide materials. Here we use mean absolute error (MAE) to compare models with respect to DFT accuracy.


Reference(s): https://doi.org/10.48550/arXiv.2205.08366, https://pubs.rsc.org/en/content/articlehtml/2023/dd/d2dd00096b

Model benchmarks

Model name Dataset MAE Team name Dataset size Date submitted Notes
alignnff_pretrained_wt0.1vacancydb_oxides0.6091JARVIS6501-14-2023CSV, JSON, run.sh, Info