Reproduce “OmicsBench: a long-horizon multi-turn benchmark of AI agents on research-study-scale bioinformatics” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Gideon Shaked, Siddharth Nagisetty
OmicsBench evaluates agents on research-scale bioinformatics workflows by turning dependent analyses into successive requests in one continuing session, with an optional gated retry after feedback. Across 97 tasks and 12 models, Opus 5 on OpenCode averages 0.57 in single-pass mode and 0.67 in gated mode. The gain may reflect answer-searching, not corrected analysis, and does not establish reliable autonomous research.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.