AI for Bio · Model

NTv3

Genome foundation model with 1 Mb context doing track prediction, gene annotation and sequence generation in one

Genomics & RNAAI-native biotechUnited KingdomActive中文

Overview

NameNTv3 · aliases: NTv3, Nucleotide Transformer v3
Full nameNucleotide Transformer v3
Ambiguous names (not auto-linked)Nucleotide Transformer, NT
FamilyNot a family entry. 8M, 100M and 650M are sizes of one generation; the two earlier generations have no entity records
OrganizationInstaDeep (subsidiary of BioNTech)
Organization typeAI-native biotech
CountryUnited Kingdom
Model classGenome language model / sequence-to-function model
DomainGenomics & RNA (also: Molecule generation)
First release · paper revision
Basis: Preprint v1 posted date (version API); a technical report PDF appeared the same month
Note: The earlier 2025-12-22 was inferred from the DOI string, which this round forbids as a date source
Other milestones
  • First public evidence: · Preprint v1 posted source
  • Preprint v1: · Preprint v1 posted source
  • Code release: · Official blog with code and weights the same day source
  • Weights release: · Full model-family weights published to the model hub source
  • Official announcement: · Official blog source
Latest update · paper revision
Basis: Preprint v2 posted
Preprint v2 posted; the earlier event is the official blog and weights release (2026-02-18), which also published the developers' own multi-species task suite. Repository syncs through 2026-11-02 are maintenance
Note: The latest update was recorded as the 2026-02-18 product update; corrected to the later paper revision source
The most recent sourced event, not a claim that nothing changed since.
StatusActive · Paper revision, weights release and repository maintenance within 12 months
OpennessCode: Open
Weights: Research use only · custom licence (model hub label: other)
Weights are on the model hub under a custom licence (checked 2026-11-16) with a JAX code release; the companion task suite is non-commercial
Benchmarks reported1 counted (self 1)
Wet-lab validation1 recorded campaign
Unverified fields† wetlab_validation[0], open_status.code_license, background.funding
As of2026-11-16

What it does

Extends the two earlier generations from short-sequence classification to a 1 Mb context, with one model emitting functional tracks and gene-structure annotation and supporting conditional generation; post-training uses about 16,000 tracks and annotations across 24 species. It is far smaller than AlphaGenome but covers more species, and unlike Evo 2 it adds supervised track post-training.

Benchmarks reported

Every row is one pairing from the survey's relation file; a score belongs to the benchmark page's ranking, where it is shown with metric, eval set, source type and date. 1 of 1 pairings are counted.

BenchmarkRelationEval set / protocolSource typeNote and evidence
08 Basenji/Enformer test setDeveloper report, official protocol—Self-reportedSelf-report in a technical report, fine-tuned on re-folded splits · evidence

Other evaluations (outside the 44)

  • Developer-built multi-species task suite (Own task set) Self-reported: 106 tasks across 7 species with base-resolution outputs; released alongside the model, with competitors chosen by the developers and the win list paraphrased from the blog
  • GUE / NT short-sequence suite (Public benchmark not among the 44) Self-reported: Not a pairing: the report does not use that suite and compares gene annotation on an earlier in-house benchmark instead; that benchmark entry's new version was released alongside this model's preprint

Developers report: one 1 Mb-context model covers track prediction, gene annotation and generation, beating several specialised tools and a larger sequence model on their own multi-species task suite.

Independent evidence: No independent evidence found. No third-party evaluation under a site benchmark protocol was found, and the in-house suite has no third-party re-run

Training data

Group in Figure 7: Public data + wet lab for validation only.

ClassValueDetail
a. Public databasesYesPretrained on a public pan-genome dataset (the report cites 9T bases trained) and post-trained on public functional-genomics tracks and annotations, including human and mouse track sets plus plant and insect data source
b. Private or licensed dataNot disclosed
c. Own wet-lab data used for trainingNo source
d. Wet lab used only for validationYesGenerated enhancers validated by reporter sequencing in one insect cell line, for validation only source

Wet-lab validation

Every rate carries its numerator and denominator. Claims that could not be verified are shown as unverified, without numbers; different paper versions are separate entries.

Reporter-sequencing validation of generated enhancers (technical report (not peer reviewed))
Targets — · Designs tested 900† · Hits — · Success — · Best affinity —

Denominator basis: 900 sequences = 600 activity-bin designs (60 per bin x 5 bins x 2 promoters) + a 150 vs 150 head-to-head; one cell type
The source is internally inconsistent (one section says 1,000, the methods say 900); 900 is used per the methods and the discrepancy noted. No hit rate is reported, only binning and promoter-specificity ratios
Executor: Developer-run and not peer reviewed

Self-reported · † · †partly verified · source

Background

  • Organization: A decision-AI company founded in North Africa in 2014 and headquartered in London since 2015, with biology as a focus line; it became a subsidiary of an mRNA and immuno-oncology pharma company in 2023. At a 2025-10 event the developer said its nucleotide model family had over a million downloads and over five hundred citations. No citable official headcount, so none is given.
  • Funding: A $7M Series A in 2019-05; a $100M Series B in 2022-01 (lead investor framings differ: one outlet says two funds co-led, another names an internet company); acquired by the parent in 2023-01 for about $389M upfront with up to about $243M in milestones, closing 2023-07-31.
  • Products and partnerships: Builds on the family's two earlier nucleotide models (the previous generation was published in a journal in 2025-02); the developer also has a protein mass-spectrometry model, and the parent is an mRNA and immuno-oncology company. Three European and US research institutions collaborated. Comparators are Evo 2 and AlphaGenome.
  • Related models: Evo 2, AlphaGenome, Borzoi

Reading notes

  1. The 106-task suite was built by the developers and released with the model, so it only shows leadership on tasks they defined.
  2. There is no GUE/NT suite result; on the track set only relative gains are given and the other big-lab model is not compared directly.
  3. The largest size is only 650M, so an edge over a smaller competitor configuration cannot be extrapolated to that competitor's largest one.
  4. The wet lab covers about 900 sequences in one cell type and reports binning and specificity ratios rather than hit rates, with the source inconsistent on the count.

Caveats

  1. The main evaluation is a developer-built suite with no third-party re-run.
  2. The technical report is not peer reviewed and the preprint has no journal version.
  3. The wet-lab count conflicts within the source (1,000 vs 900).
  4. Weights carry a custom licence and the suite is non-commercial.

Sources

  1. Technical report (preprint)
  2. Preprint version record (preprint)
  3. Official blog and weights release (company blog)
  4. Code repository (repository)

Corrections

3 corrections
FieldWasNowBasisFound
first_release2025-12-22 (inferred from the DOI string)2025-12-25 (preprint v1 posted)source2026-11-16
latest_update2026-02-18, product update2026-10-29, preprint v2 (paper revision)source2026-11-16
wetlab_validation600 designs900 (600+150+150), noting that the source itself conflicts between 1,000 and 900source2026-11-16

Part of the AI for Bio benchmarks survey · all 112 models · open in the explorer. Record as of 2026-11-16.