What it is
Evo is a DNA foundation model that operates from nucleotides to whole genomes, predicting and designing across DNA, RNA and protein. Evo 2 (2025, with NVIDIA) scaled to 9.3 trillion base pairs across 128,000+ genomes spanning all domains of life — one of the largest biological models built. Evo designed a working CRISPR system (EvoCas9-1) that succeeded after just 11 tries.
Evidence trail
BioAtlas keeps the path from source to decision visible. A connection records provenance; it does not imply that evidence is sufficient for every context.
Model passport
How Evo / Evo 2 represents biology
Category is navigation. These fields describe the model-specific computational transformation and deliberately override broad category defaults.
Biological scale
Modalities & tasks
Registry, claims and frontier intelligence
Evo 2
2 version records · latest curated year 2025. Model-family identity remains separate from capability and access changes.
Explore version lineage →1 normalized claim
Genomic sequence modelling · Genomic sequence evaluations
Open claim intelligence →2 connected frontiers
Genome design · Peer-reviewed capability
Inspect research horizon →Connected research frontiers
These records describe active research directions, not guaranteed capabilities of this model. Evidence stages and unresolved questions are preserved separately.
Genome-scale generative biology
Arc Institute · Stanford · NVIDIA · 2026-03-01Can a foundation model read, predict and design biological sequence continuously from single nucleotides to megabase-scale genomes?
Evidence boundary and unresolved questions
Generative plausibility is not equivalent to biological viability, function or safety. Long generated sequences require extensive synthesis, containment and functional review.
- What biological constraints are learned versus memorized?
- How should whole-genome designs be evaluated before synthesis?
- Can mechanistic interpretability keep pace with model scale?
genome foundation model · long context · sequence design · biosafetyOpen frontier record →Bridge-RNA programmable DNA recombination
Arc Institute · UC Berkeley · Stanford · 2024-06-26Can RNA programmably specify both target and donor DNA to insert, excise or invert large sequences without relying on conventional CRISPR cutting and repair?
Evidence boundary and unresolved questions
The original 2024 work was early-stage and bacterial. Efficiency, specificity, delivery and control in mammalian cells require separate validation.
- Can the system work efficiently and specifically in human cells?
- How are off-target recombination and repeated sequences controlled?
- Can delivery support therapeutically relevant tissues and cargo sizes?
genome editing · bridge RNA · recombinase · large DNA editsOpen frontier record →Inputs and outputs
Inputs
DNA sequenceOutputs
Sequence predictionsEmbeddings or generated sequenceScientific and technical profile
Scientific principles
Technology
Scientific lineage
These are transparent concept matches—not claims that one scientist alone caused this model. Each connection is based on the model’s recorded domain, scientific principles, technical terms or an explicit lineage link.
DNA as the hereditary transforming principle
Oswald Avery, Colin MacLeod & Maclyn McCartyGenomics, variant interpretation, gene therapy and sequence foundation models depend on DNA being the durable molecular carrier of biological information.
The DNA double helix and complementary base pairing
James Watson & Francis CrickSequence analysis, variant prediction, genome design and nucleic-acid therapeutics all rest on this structural logic.
Reading the sequences of proteins and DNA
Frederick SangerBiological foundation models exist because proteins and genomes became readable, comparable and computable at scale.
The central dogma and directional information transfer
Francis CrickMulti-omic models and sequence foundation models connect genotype, transcript and protein through this information-flow framework.
Information, entropy and communication
Claude E. ShannonSequence modelling, cross-entropy training, language models, mutual information and representation learning all use Shannon’s framework.
X-ray evidence for the helical structure of DNA
Rosalind Franklin & Raymond GoslingStructural genomics and sequence-to-structure reasoning began with experimentally grounded molecular geometry.
Evaluation evidence
Task-specific evidence only; not comparable as a universal leaderboard score.
Genomic sequence evaluations
Evo 2 · Held-out genomic sequence evaluationsPeer-reviewed sequence-generation and prediction evaluations across biological scales.
Claim caveats
- Generation quality does not establish biological function or safety.
- Evo and Evo 2 require version-specific evaluation.
Known limitations
- Performance depends on the evaluation dataset and operating conditions.
- Task-specific benchmark results should not be compared across unlike domains.
- Outputs require task-specific scientific and experimental validation.
Milestones
Trained on 9.3T DNA base pairs (Evo 2).
Designed the functional EvoCas9-1 CRISPR system.