SMDD-Bench is a new multi-turn benchmark for LLM agents on small molecule drug design where the best tested model solves 40.2% of 502 tasks.
Then, I'll project a vector from this midpoint towards the center of the pocket
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
SMDD-Bench: Can LLMs Solve Real-World Small Molecule Drug Design Tasks?
SMDD-Bench is a new multi-turn benchmark for LLM agents on small molecule drug design where the best tested model solves 40.2% of 502 tasks.