DrugPlayGround
Unified platform benchmarking LLMs and molecular embeddings across 4 drug discovery tasks: drug function analysis, drug-target interaction, synergistic combinations, and perturbation prediction.
Composite
66.8
Experimental validation
Retrospective
Stages
Hit IDTarget IDLead ID / ADMET
Modalities
small-molecule
Task types
classificationregressionretrieval
Size
tasks: 4
drugs_evaluated: unknown — paper pending full release
drugs_evaluated: unknown — paper pending full release
License
Other
First release
2026-02-11
Last updated
2026-04-07
Official site
Leaderboard
→ leaderboard
Dataset
→ dataset
Code / GitHub
→ repository
HuggingFace
→ HF
Paper
DrugPlayGround: Benchmarking Large Language Models and Embeddings for Drug Discovery · Tianyu Liu, Sihan Jiang, Fan Zhang, Kunyang Sun, Teresa Head-Gordon, Hongyu Zhao · 2026 · paper · doi:N/A · 0 citations
Flags
none
Experts
—
Groups
—
Hosted by
—
Related benchmarks
Rubric (7-criterion)
rigor
4
coverage
4
maintenance
3
adoption
2
quality
3
accessibility
3
industry_relevance
4
Notes
First unified platform to benchmark both LLMs and molecular embeddings for drug discovery. Includes Head-Gordon lab (Berkeley) — reputable. Early days for adoption. Addresses a timely question.