BioinformaticsbioRxivPreprint
LifeSciBench: Evaluating Language Models on Realistic, Expert-Level Tasks in the Life Sciences
Amelia Liu, Andrew Ho, Anne Marie Droste…·Yunyun Wang
LifeSciBench evaluates language models on 750 expert-authored tasks across seven life science domains and workflows, revealing significant gaps in model performance.
DOI 10.64898/2026.08.13.744657