Rowan Benchmarks

All Folmsbee Results

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.

NameBenchmarked By
OMol25's eSEN Conserving Small0.210.330.850.8676
UMA Small (OMol task)0.210.340.850.8576
ωB97X-D/def2-TZVP0.240.390.830.8580link
B3LYP/def2-TZVP0.250.410.830.8476link
B97-3c0.300.530.800.8277link
Egret-1e0.310.500.780.81115
Egret-10.310.530.780.81115
MACE-ANI-CC0.320.550.770.79437
Egret-1t0.340.590.760.79115
AIMNet2 (ωB97M-D3, new)0.540.930.640.6576
AIMNet2 (ωB97M-D3, old)0.540.930.640.6576
Prescient's StrainRelief MACE0.571.020.600.63115
GFN2-xTB0.721.320.570.5976link
eSEN-OAM0.841.710.560.55115
Orb-v3 (Conservative Inf. OMat)0.881.710.510.50115
MACE-MP-0b2(Large)-D3BJ0.811.450.490.47115
Orb-v3 (Conservative 20 OMat)1.052.110.490.44115
MACE-MP-0(Large)-D3BJ0.881.590.490.45115
MACE-MP-0b2(Medium)0.971.830.470.44115
OMat24 eqV2-L0.871.440.470.50115
MACE-MP-0b2(Small)1.032.010.460.41115
MACE-MP-0b2(Large)1.082.060.460.37115
MACE-MP-0b(Medium)1.021.890.460.43115
MACE-MP-0b(Small)1.252.580.450.40115
MACE-MP-0(Large)1.162.220.450.34115
MACE-MP-0(Medium)1.081.960.440.37115
Orb-v3 (Direct Inf. OMat)1.152.060.440.41115
Orb-d3-v20.941.560.430.41115
MACE-MP-0(Small)1.252.420.430.34115
Orb-v21.172.150.420.36115
Orb-v3 (Direct 20 OMat)1.302.330.400.36115
SO3LR2.654.850.280.18149