AI for Bio · Model

Latent-X / Latent-X2

Closed platform models for binder, macrocycle and antibody design, testing only tens of designs per target

ProteinsAI-native biotechUnited KingdomActive中文

Overview

NameLatent-X / Latent-X2 · aliases: Latent-X, Latent-X2
Full nameTwo model generations in one record, so there is no single full name
Ambiguous names (not auto-linked)Latent-Y
FamilyCovers Latent-X and Latent-X2 only; the Latent-Y design agent built on top is a separate product and its campaign figures belong to the Latent-Y preprint.
  • Latent-X · †
  • Latent-X2 · †
OrganizationLatent Labs
Organization typeAI-native biotech
CountryUnited Kingdom
Model classDesign (binder / antibody / macrocycle)
DomainProteins (also: Antibodies, Molecule generation)
First release† partly verified
Basis: Latent-X company press release (the preprint, 2025-07-25, is listed separately)
Note: Unverified: that date belongs to the predecessor Latent-X while the X2 press release is 2025-12-16; treated as a family entry source
Other milestones
  • First public evidence: † · Latent-X company press release (the preprint, 2025-07-25, is listed separately) source
  • Preprint v1: † · Latent-X preprint (the X2 preprint is 2025-12-23) source
  • Official announcement: † · Latent-X2 company press release source
Latest update† partly verified · product update
Basis: Company press release: Latent-Y opened to researchers worldwide
Latent-Y, the antibody design agent built on X2 (launched 2026-03-23), opened to researchers worldwide with free daily allowances; no new X2 version or weights were found.
Note: A product event, not a model version update to X2 source
The most recent sourced event, not a claim that nothing changed since.
StatusActive · Product release events within 12 months, though no model version update
OpennessCode: Closed
Weights: Closed
Weights are closed and access runs through a no-code platform; X2 requires an application or a commercial agreement
Benchmarks reported0 counted · none of the 44
Wet-lab validation3 recorded campaigns
Unverified fields† first_release, latest_update, training_data.a_public, training_data.b_private_licensed, training_data.c_own_wetlab_for_training
As of2026-11-16

What it does

Latent-X targets mini-binders and macrocyclic peptides; X2 extends to drug-like antibodies (VHH, scFv) and reports unoptimised developability measures plus one ex vivo immunogenicity assessment. It shares the closed platform route with Chai-2 and JAM/JAM-2; unlike open models such as BoltzGen, its figures cannot be reproduced externally.

Benchmarks reported

None of the 44 benchmarks. This model is on the zero-pairing list.

How it evaluates itself: Latent-X mini-binder / macrocycle campaign; Latent-X2 VHH/scFv campaign; Developability panel; Immunogenicity assay; Latent-Y agent campaigns

Other evaluations (outside the 44)

  • Latent-X mini-binder / macrocycle campaign (Wet-lab validation) Self-reported: A self-built target set with 30-100 designs per target, compared against other design models under matched conditions (self-reported)
  • Latent-X2 VHH / scFv campaign (Wet-lab validation) Self-reported: Eighteen targets with 4-24 designs per target per modality and binders on nine; macrocycle binders were also made for one hard target
  • Developability panel (Own task set) Self-reported: Expression, aggregation, polyreactivity, hydrophobicity and thermal stability versus approved antibodies, with no optimisation or selection
  • Immunogenicity assay (Case study) Self-reported: T-cell proliferation and cytokine release on de novo VHH binders for one target in a human donor panel
  • Latent-Y agent campaigns (user or partner report) Self-reported: Target-level success across nine nanobody campaigns, sourced to the Latent-Y preprint rather than the X2 paper

Developers report: Developers report zero-shot VHH and scFv designs reaching picomolar to nanomolar affinity from tens of designs per target, with developability close to approved antibodies and low ex vivo immunogenicity (self-reported).

Independent evidence: No independent evidence found. Weights are closed and no third-party evaluation or independent replication was found

Training data

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

ClassValueDetail
a. Public databasesNot disclosedTraining data sources and scale are not disclosed source
b. Private or licensed dataNot disclosedWhether private or licensed data is used is not disclosed source
c. Own wet-lab data used for trainingNot disclosedNot disclosed; must not be written up as 'public data only' source
d. Wet lab used only for validationYesYes: the wet lab is used for validation and no feedback into training is claimed 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.

Latent-X macrocycle and mini-binder campaign (Latent-X (predecessor))
Targets — · Designs tested — · Hits — · Success — · Best affinity low nanomolar to picomolar (mini-binders, self-reported)

Denominator basis: A self-built target set with 30-100 designs per target; the source gives only an aggregate hit rate with no per-target numerators or denominators, so no rate is quoted
Belongs to the predecessor model, and the head-to-head comparisons were run by the developer, not independently

Self-reported · † · verified · source
Latent-X2 VHH / scFv campaign (Latent-X2)
Targets 18 · Designs tested — · Hits 9 · Success binders on 9 of 18 targets (target-level rate) · Best affinity picomolar to nanomolar (self-reported)

Denominator basis: Eighteen targets with only 4-24 designs tested per target per modality
The source says VHH and scFv and never 'nanobody'; self-reported with no independent replication

Self-reported · † · verified · source
Latent-Y agent campaigns (Latent-Y (separate preprint))
Targets 9 · Designs tested — · Hits 6 · Success binders on 6 of 9 targets (target-level rate) · Best affinity single-digit nanomolar (self-reported)

Denominator basis: Nine targets with candidates generated by X2 and no human filtering; per-target hit rates run about 1%-28% of tested sequences
Source attribution corrected: these figures come from the Latent-Y preprint, not the 2025-12 press release and not the Latent-X2 paper

Self-reported · † · verified · source

Background

  • Organization: The company was founded in 2023, headquartered in London with a San Francisco team, and positions itself as an AI-native protein design company; headcount is about 20 on aggregator data (2026-03, profile counts only).
  • Funding: It emerged from stealth in 2025-02 with $50M, including a $40M Series A co-led by two funds with several other investors; no later round has been announced.
  • Products and partnerships: The products are Latent-X, Latent-X2 and the Latent-Y design agent launched 2026-03 and opened to researchers worldwide in 2026-07; no pharma deal values are public.
  • Related models: Chai-2, JAM / JAM-2, AlphaProteo, BoltzGen

Reading notes

  1. The predecessor's comparison with AlphaProteo is self-reported on company-chosen targets and is not better on every target.
  2. Binders on 9 of 18 targets is a target-level rate, a different measure from per-target hit rates.
  3. Neither the training data nor the developability data can be checked externally.
  4. Both dates hold but mean different things: the company press release is 2025-12-16 and the preprint 2025-12-23.

Caveats

  1. Zero pairings: no site benchmark score and no competition entry record.
  2. One record covers two generations; the first-release date belongs to the predecessor Latent-X and is marked unverified.
  3. The Latent-Y campaign figures belong to a separate preprint and must not be counted as X2 results.
  4. Only 4-24 designs are tested per target, so target-level success is highly sensitive to the design budget.

Sources

  1. Latent-X2 preprint (preprint)
  2. Latent-X preprint (preprint)
  3. Latent-X2 company press release (press) · †
  4. Latent-X company press release (press)
  5. Latent-Y preprint (source of the campaign figures) (preprint)
  6. Latent-Y availability announcement (press)

Corrections

2 corrections
FieldWasNowBasisFound
wetlab_validationThe nine campaigns and 67% target success were attributed to the 2025-12 press release or the Latent-X2 paperAttribution corrected to the Latent-Y preprint and written as 6 of 9 targetssource2026-11-16
first_releaseThe first-release date was taken as Latent-X2's own release dateThat date belongs to the predecessor Latent-X; the record becomes a family entry with an explicit boundary (unverified)source2026-11-16

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