Table 4. Performance of the models summarized in Tab. 2 on the Astex Diverse Set scoring benchmark. We only report evaluation results from the original reference. RMSEs are expressed in pK units.

Model	Reference	Pearson’s r	RMSE
Pafnucy	Stepniewska-Dziubinska et al. (2018)	0.57	1.37
DeepAtom	Li et al. (2019c)	0.77	1.03
RosENet	Hassan-Harrirou et al. (2020)	0.48	1.65