Evo 2: a 40B-parameter genome language model trained on DNA from all domains of life
Arc Institute, Stanford and NVIDIA released Evo 2 (7B and 40B parameters) in Feb 2025, trained on genomes across bacteria, archaea and eukaryotes. It predicts variant effects and generates genome-scale sequences. Published in Nature on 4 Mar 2026, and used to design the first AI-generated viable phage genomes.
Key facts
- Open weights, 7B and 40B parameters, 1M-base context
- Nature publication 4 Mar 2026 (DOI 10.1038/s41586-026-10176-5)
- 88k+ GitHub downloads and 8M+ API requests in its first year, per Arc
Science result
- Field
- biology / genomics
- Problem
- General-purpose modelling and design of DNA across life
- Result
- Open genome foundation model enabling zero-shot variant-effect prediction and whole-genome generation.
- AI system
- Evo 2
- Human role
- Human-designed model
- Verification
- Peer-reviewed in Nature (2026)
- Status
- confirmed
What happened
Arc released one of the largest fully open biology models, trained on trillions of DNA bases.
Why it matters
It made genome-scale generative design possible, most notably whole viable bacteriophages.
Changelog
- 2026-09-29: created
Related events
- First AI-generated complete genomes: Evo models design viable bacteriophages that kill resistant E. coli ★★★★★
- Arc Institute announces first Virtual Cell Challenge winners; a 2026 zero-shot round follows ★★
Sources (2)
id: 2025-02-19-evo-2-genome-model · updated 2026-09-29 · open in the interactive timeline