Overview
| Name | ESMFold2 · aliases: ESMFold2, ESMFold2-Fast, ESMFold2 Pro |
|---|---|
| Full name | Official materials use ESMFold2 only; no expanded name |
| Ambiguous names (not auto-linked) | ESMFold, ESM |
| Family | Not a family entry. Covers ESMFold2 with its Fast and Pro variants; ESM C and the ESM Atlas are separate entries |
| Organization | Biohub, EvolutionaryScale team |
| Organization type | Nonprofit institute |
| Country | United States |
| Model class | Co-folding (single-sequence PLM) |
| Domain | Structure & co-folding (also: Proteins) |
| First release | · product update Basis: Research-institute release page (HF repos created 2026-05-13, not used as first release) source |
| Other milestones | |
| Latest update | · patch Basis: esm SDK v3.4.3 v3.4.3 is bug fixes plus a transformers dependency bump; the new weights belong to the previous release v3.4.2 (2026-10-30, with the 2025-cutoff weights and the Pro folding API), and HF weights were updated 2026-09-14 Note: Read the SDK and weights axes separately source The most recent sourced event, not a claim that nothing changed since. |
| Status | Active · The SDK still ships patch releases |
| Openness | Code: Unclear Weights: Open Weights are public on Hugging Face, but licence metadata is inconsistent across the organisation's model cards, so neither term is settled |
| Benchmarks reported | 2 counted (board 1, self 1) |
| Wet-lab validation | 1 recorded campaign |
| Unverified fields | † wetlab_validation[0].success_rate, benchmarks_reported[1].source_url, open_status.code |
| As of | 2026-11-16 |
What it does
Puts evolutionary information inside a pretrained protein language model, predicts multi-chain complexes without MSA retrieval at inference, and ships a binder design pipeline. Unlike AlphaFold3 and Boltz-2 it needs no MSA and runs faster; ESM3 and ESM C are its siblings.
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. 2 of 2 pairings are counted.
| Benchmark | Relation | Eval set / protocol | Source type | Note and evidence |
|---|---|---|---|---|
| 34 AbBiBench | Official leaderboard or results | AbBiBench structure-prediction entry | Board | Benchmark-registered ipSAE entry †unverified · no source link |
| 31 FoldBench | Developer report, official protocol | FoldBench no-MSA complexes / antibody-antigen | Self-reported | Model-card figures are second-hand; another paper reports figures on its own antibody subset †partly verified · evidence |
Other evaluations (outside the 44)
- Sequence and structure atlas released alongside (resource release) Self-reported: The release includes an atlas of 6.8B sequences and 1.1B predicted structures; these are official scale figures, not benchmark results
- Competitor-run evaluation (competitor reported) Third-party: The OpenDDE report evaluates this model on a self-defined antibody subset under a different protocol, with no independent replication
- Hosting and second-hand accounts (second hand) Third-party: A third-party platform hosts the model, and its card figures mostly reach readers through platform and community write-ups (second-hand)
Developers report: Developers report matching or beating AlphaFold3 and Protenix-v1 on protein-protein and antibody-antigen targets without MSAs (self-reported, no independent replication).
Independent evidence: No independent evidence found. Both figure sets are self-reported, by developer and competitor; neither was replicated
Training data
Group in Figure 7: Public data + wet lab for validation only.
| Class | Value | Detail |
|---|---|---|
| a. Public databases | Yes | PDB plus AFDB (cut-off 2021-09), with the ESM C sequence corpus for the language model source |
| b. Private or licensed data | No | |
| c. Own wet-lab data used for training | No | No claim that wet-lab results were fed back into training |
| d. Wet lab used only for validation | Yes | Binder designs for five targets were assayed in the wet lab (unverified) 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.
Denominator basis: Denominators undisclosed; the preprint full text is rate-limited and the campaign is shared across several models in one release, so it cannot be attributed to a single model (unverified)
Not an ESMFold2-specific wet-lab paper and not an independent replication; no hit-rate figures are given (unverified)
Background
- Organization: Biohub is a philanthropically funded nonprofit medical research organization that consolidated related biomedical research in 2025-11; the EvolutionaryScale team joined on 2025-11-06 in a strategic transaction with undisclosed terms.
- Funding: Nonprofit funded by its philanthropic backer; amounts undisclosed
- Products and partnerships: Released 2026-05-27 together with ESM C and the atlas and hosted free on the organisation's own platform; the developers also ran the pipeline to design binders for five cancer and immunology targets.
- Related models: ESM3, ESM C, AlphaFold 3, Boltz-2
Reading notes
- Self-reported numbers sit on FoldBench and are not comparable with PoseBusters-style protocols.
- The antibody-antigen claim exists in two different protocols, one from the developer and one from a competitor.
- The real value of dropping MSAs is speed and ease of use; the accuracy claim still awaits independent evaluation.
- The design-validation denominators are undisclosed, so hit rates cannot be cited.
Caveats
- The wet-lab campaign is shared across the release's models and the preprint is rate-limited, so no figures are given (unverified).
- The Runs N' Poses claim has no matching figure in official material and is treated as unconfirmed.
- Licence metadata is inconsistent across the organisation's models, so openness cannot be settled.
- The AbBiBench line rests on the site's own page and is shown as unverified.
Sources
- Institute release page: a world model of protein biology (official site) ·
- Hugging Face model card (repository)
- esm SDK releases (repository)
- Community write-up (second-hand) (second-hand) second-hand
- Announcement of the team joining (press)
Corrections
3 corrections
| Field | Was | Now | Basis | Found |
|---|---|---|---|---|
| latest_update | 2026-10-30 | 2026-11-09 (v3.4.3 is the later release) | source | 2026-11-16 |
| latest_update.event_kind | new weights | Patch: v3.4.3 is only bug and dependency fixes; the new weights belong to the 2026-10-30 release | source | 2026-11-16 |
| wetlab_validation | hit-rate ranges for minibinders and antibody-derived formats | No figures: the preprint is rate-limited and the campaign is shared across the release's models (unverified) | source | 2026-11-16 |
Part of the AI for Bio benchmarks survey · all 112 models · open in the explorer. Record as of 2026-11-16.