MolSafeEval
Explore score history ↗MolSafeEval evaluates safety risks in AI-generated molecules across four task types, using structured knowledge graphs and LLM-based reasoning to detect unsafe features.
- Released
- 2026-07-01
- Institutions
- Zhejiang University · University of Oxford
- Evaluates
- Biology & Drug Discovery, Materials & Chemistry, Safety, Safety & Trustworthiness
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- unreviewed
MolSafeEval paper
No reported scores are on record for this benchmark yet.