PMO-Dock
Standardized benchmark extending the PMO protocol to docking-based objectives, evaluating docking score optimization, target specificity, and generalization for molecular generative/optimization models under a unified protocol.
Composite
43.5
Experimental validation
Retrospective
Stages
Hit IDLead ID / ADMET
Modalities
small molecule
Task types
generationdocking
Size
oracles: 0
splits: {'train': 0, 'val': 0, 'test': 0}
note: Suite of docking-based oracle tasks; counts per camera-ready
splits: {'train': 0, 'val': 0, 'test': 0}
note: Suite of docking-based oracle tasks; counts per camera-ready
License
CC-BY
First release
2026-03-02
Last updated
2026-05-26
Official site
Leaderboard
→ leaderboard
Dataset
→ dataset
Code / GitHub
→ repository
HuggingFace
→ HF
Paper
PMO-Dock: Benchmarking Docking, Specificity and Generalization in Molecular Optimization · Gor Simonyan, Tatevik Abrahamyan, Narek Abelyan, Tigran Fahradyan, Hrant Khachatrian · 2026 · paper · doi:N/A — ICLR 2026 Workshop GEM (OpenReview KTjveJQe96) · 0 citations
Flags
none
Experts
—
Groups
—
Hosted by
—
Related benchmarks
Rubric (7-criterion)
rigor
3
coverage
3
maintenance
3
adoption
1
quality
3
accessibility
3
industry_relevance
3
Notes
ICLR 2026 GEM workshop paper (published Mar 2026, last revised 26 May 2026). Useful upgrade to PMO by adding docking-based oracles and explicit specificity/generalization axes, which PMO's simple property oracles lacked. Workshop-tier venue and no citations yet, so adoption and rigor scored conservatively; direct successor framing to PMO gives it a clear niche.