TDC ADMET Group
22-task ADMET benchmark suite with scaffold splits — core TDC leaderboard.
Composite score: 100.0
Rubric (1–5 per criterion)
rigor
5/5
coverage
5/5
maintenance
5/5
adoption
5/5
quality
5/5
accessibility
5/5
industry_relevance
5/5
Metadata
Stages
Lead ID / ADMET
Modalities
small-molecule
Task types
regressionclassification
License
MIT
First release
2021-02
Last updated
2025-04
Flags
none
Size & scope
- tasks: 22
- molecules: 130000
Primary paper
Title
Therapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Development
Authors
Huang K, Fu T, Gao W, et al.
Year
2021
DOI / arXiv
Citations
620
Links
- Official site: https://tdcommons.ai/benchmark/admet_group/overview/
- GitHub: https://github.com/mims-harvard/TDC
- Leaderboard: https://tdcommons.ai/benchmark/admet_group/overview/
Hosted by (initiatives)
Experts (primary authors / maintainers)
Groups (host labs / companies / consortia)
Related benchmarks
Notes (honest caveats)
Most-adopted ADMET benchmark. 100+ leaderboard submissions.