← All benchmarks

MoleculeNet

Multi-task molecular ML benchmark covering quantum, physical, biophysical, physiological properties.
Composite score: 78.0

Rubric (1–5 per criterion)

rigor
4/5
coverage
4/5
maintenance
2/5
adoption
5/5
quality
3/5
accessibility
5/5
industry_relevance
4/5

Metadata

Stages
Lead ID / ADMETHit ID
Modalities
small-molecule
Task types
regressionclassificationquantum
License
MIT
First release
2018-03
Last updated
2023-11
Flags
data-leakage-known

Size & scope

Primary paper

Title
MoleculeNet: A Benchmark for Molecular Machine Learning
Authors
Wu Z, Ramsundar B, Feinberg EN, et al.
Year
2018
DOI / arXiv
10.1039/C7SC02664A
Citations
3600

Links

Hosted by (initiatives)

Experts (primary authors / maintainers)

Groups (host labs / companies / consortia)

Related benchmarks

Notes (honest caveats)

Widely cited (3600+); aging splits with known scaffold leakage.