Unconditional molecular generation is a stepping stone for conditional molecular generation, which is important in \emph{de novo} drug design. Recent unconditional 3D molecular generation methods report saturated benchmarks, suggesting it is time to re-evaluate our benchmarks and compare the latest models. We assess five recent high-performing 3D molecular generation methods (EQGAT-diff, FlowMol, GCDM, GeoLDM, and SemlaFlow), in terms of both standard benchmarks and chemical and physical validity. Overall, the best method, SemlaFlow, has a success rate of 87% in generating valid, unique, and novel molecules without post-processing and 92.4% with post-processing.
Cite
@article{arxiv.2505.00518,
title = {An evaluation of unconditional 3D molecular generation methods},
author = {Martin Buttenschoen and Yael Ziv and Garrett M. Morris and Charlotte M. Deane},
journal= {arXiv preprint arXiv:2505.00518},
year = {2025}
}