Table 3 Overall performances (RMSE) on regression downstream tasks. The best results are denoted in bold, and the second-best are indicated with underlining

AttentiveFP

0.877 ± 0.029

2.073 ± 0.183

0.721 ± 0.001

DMPNN

1.050 ± 0.008

2.082 ± 0.082

0.683 ± 0.016

N-Gram_RF

1.074 ± 0.107

2.688 ± 0.085

0.812 ± 0.028

N-Gram_XGB

1.083 ± 0.082

5.061 ± 0.744

2.072 ± 0.030

GEM

0.798 ± 0.029

1.877 ± 0.094

0.660 ± 0.008

Uni-Mol

0.788 ± 0.029

1.620 ± 0.035

0.603 ± 0.010

MolCLR

1.113 ± 0.023

2.301 ± 0.247

0.789 ± 0.009

MolCLR_CMPNN

0.911 ± 0.082

2.021 ± 0.133

0.875 ± 0.003

Unimodality_avg

0.924 ± 0.083

1.707 ± 0.126

0.587 ± 0.021

Unimodality_Max

0.761 ± 0.068

1.437 ± 0.134

0.537 ± 0.005

MMFRL_early

1.037 ± 0.170

2.093 ± 0.090

0.607 ± 0.034

MMFRL_intermediate

0.730 ± 0.023

1.465 ± 0.117

0.552 ± 0.017

MMFRL_late

0.763 ± 0.035

1.741 ± 0.191

0.525 ± 0.018