eSEN-OAM is a neural network potential (NNP) method from Xiang Fu and co-workers at Meta's FAIR Chemistry in 2025.
Read the eSEN-OAM preprint. See the eSEN-OAM code.
| About eSEN-OAM | |
|---|---|
| Architecture | eSEN |
| Dataset | OMat24, Alexandria, and MPtrj |
| Dataset Level of Theory | PBE+U |
| Dataset Size | 113M |
GMTKN55 (download) is a high-accuracy molecular benchmark that measures basic properties, reaction energies, and noncovalent interactions. The GMTKN55 benchmark comprises 55 subsets. Each subset contains a number of relative energy measurements computed at the CCSD(T) level of theory. When viewing subset-level results, the mean absolute deviation/error (MAD/MAE) in kcal/mol is shown. Each subset is assigned a difficulty weight (see Section 4). When viewing category-level results, the weighted total mean absolute deviation (using the WTMAD-2 weights) is shown. See all GMTKN55 results.
| Name | Incomplete Subsets | Benchmarked By | ||||||
|---|---|---|---|---|---|---|---|---|
| ωB97M-D3BJ/def2-QZVP | 2.86 | 5.77 | 2.34 | 4.54 | 3.63 | 4.04 | link | |
| B3LYP-D3BJ/def2-QZVP | 7.99 | 10.16 | 4.11 | 5.65 | 4.82 | 6.18 | link | |
| B97-3c | 11.99 | 10.51 | 9.17 | 8.62 | 11.89 | 10.16 | link | |
| GFN2-xTB | 20.02 | 19.77 | 13.66 | 24.58 | 11.44 | 18.65 | link | |
| eSEN-OAM | 16.71 | 23.97 | 11.31 | 23.91 | 26.29 | 22.16 | 1 |
The Folmsbee conformers benchmark (GitHub) is a high-accuracy molecular benchmark that evaluates the accuracy of predicting and ranking conformer relative energies. The benchmark contains 708 subsets of 10 conformers each, 632 of which have energies computed at the DLPNO-CCSD(T) level of theory. DLPNO-CCSD(T) calculations were not finished for 76 subsets, so every level of theory will show at least 76 incomplete subsets. Mean absolute error (MAE) and root mean square error (RMSE) are shown in kcal/mol. See all Folmsbee results.
| Name | Incomplete Subsets | Benchmarked By | ||||
|---|---|---|---|---|---|---|
| ωB97X-D/def2-TZVP | 0.24 | 0.39 | 0.83 | 0.85 | 80 | link |
| B97-3c | 0.30 | 0.53 | 0.80 | 0.82 | 77 | link |
| GFN2-xTB | 0.72 | 1.32 | 0.57 | 0.59 | 76 | link |
| eSEN-OAM | 0.84 | 1.71 | 0.56 | 0.55 | 115 |
This is a benchmark that evaluates the average speed of running energy and force calculations on 10-, 100-, and 1000-atom molecular and periodic systems. All calculations were run on Nvidia A10G GPUs through Modal. Click items in legend to show/hide. See all periodic speed results.
TorsionNet206 is a high-accuracy molecular benchmark that evaluates the accuracy of predicting and ranking of dihedral energy profiles. The benchmark contains 206 subsets of 24 conformers each computed at the CCSD(T)/def2-TZVP level of theory. Mean absolute error (MAE) and root mean square error (RMSE) are shown in kcal/mol. See all TorsionNet206 results.
| Name | Incomplete Subsets | Benchmarked By | ||||
|---|---|---|---|---|---|---|
| ωB97M-D3BJ/vDZP | 0.15 | 0.18 | 0.99 | 0.98 | ||
| B97-3c | 0.35 | 0.45 | 0.98 | 0.97 | ||
| eSEN-OAM | 0.69 | 0.85 | 0.90 | 0.89 | 1 | |
| GFN2-xTB | 0.73 | 0.91 | 0.85 | 0.85 |
Wiggle150 is a high-accuracy molecular benchmark that evaluates the accuracy of predicting and ranking of highly-strained conformers. The benchmark contains 150 highly-strained conformations of adenosine, benzylpenicillin, and efavirenz computed at the DLPNO–CCSD(T)/CBS level of theory. Mean absolute error (MAE) and root mean square error (RMSE) are shown in kcal/mol. See all Wiggle150 results.
| Name | Benchmarked By | ||
|---|---|---|---|
| ωB97M-D3BJ/def2-QZVP | 1.18 | 1.59 | link |
| B3LYP-D3BJ/def2-QZVP | 1.41 | 1.84 | link |
| B97-3c | 2.32 | 2.96 | link |
| eSEN-OAM | 7.05 | 8.10 | |
| GFN2-xTB | 14.60 | 15.20 | link |
X23b is a revised verison of X23, a periodic benchmark that evaluates the accuracy of reproducing experimental lattice energies and unit-cell volumes for 23 organic molecular crystals. Lattice energy (MAE) is shown in kcal/mol. Cell volume (MAPE, or mean average percent error) is shown in percentage. See all X23b results.