GM
Genome modeling and design across all domains of life with Evo 2
Work
by Garyk Brixi, Matthew G. Durrant, Jerome Ku, Michael Poli, Greg Brockman · 2025
This paper introduces Evo 2, a biological foundation model trained on over 9 trillion DNA base pairs spanning all domains of life. Featuring up to 40 billion parameters and a 1-million-token context window at single-nucleotide resolution, Evo 2 accurately predicts the functional impacts of genetic variation and autonomously learns complex biological features without task-specific fine-tuning.

