Model for matpes_forces

• Description: This is an AI benchmark to evaluate how accurately a machine learning force-field (MLFF) can predict atomic forces of the MATPES dataset (single-point PBE energies, forces and stresses sampled from molecular-dynamics trajectories across the periodic table). Here we use multi-mean absolute error (multi-MAE) to compare MLFFs with respect to DFT (PBE) accuracy. External links: https://matpes.ai
  

Reference(s): https://github.com/atomgptlab/alignn, https://doi.org/10.48550/arXiv.2503.04070

Model benchmarks

Model name	Dataset	MAE	Team name	Dataset size	Date submitted	Notes
alignn2_radius	matpes	0.17754176955288084	AtomGPTLab	434712	07-30-2026	CSV, JSON, run.sh, Info
alignnff_matpes	matpes	0.16203718255865385	AtomGPTLab	434712	07-24-2026	CSV, JSON, run.sh, Info