Overview
| Name | OpenFold3 · aliases: OpenFold3, OpenFold3-preview, OpenFold3-preview2, OF3 |
|---|---|
| Full name | No expanded name; official materials use OpenFold3 |
| Ambiguous names (not auto-linked) | OpenFold |
| Family | Not a family entry. Single model line; preview, preview2 and 0.5.x are versions of one model |
| Organization | OpenFold Consortium, Open Molecular Software Foundation, Columbia University, Lawrence Livermore National Laboratory, Seoul National University |
| Organization type | Nonprofit institute |
| Country | United States |
| Model class | Co-folding (protein / nucleic acid / small molecule) |
| Domain | Structure & co-folding (also: Small molecules) |
| First release | · code release Basis: GitHub preview release, consortium press release the same day source |
| Other milestones | |
| Latest update | · code release Basis: GitHub release 0.5.1 v0.5.1 patch: lower inference/validation memory (MSA/template features as compact indices) and deterministic inference, no new weights; OpenBind-0 weights belong to v0.5.0 (2026-08-21) Note: Commits continue to 2026-11-16; preview2 was 2026-03-13 source The most recent sourced event, not a claim that nothing changed since. |
| Status | Active · Releases and ongoing commits within 12 months |
| Openness | Code: Open · Apache-2.0 Weights: Open · Apache-2.0 Code and weights Apache-2.0, commercial use allowed; the 0.5.x default weights OpenBind-0 are also Apache-2.0 |
| Benchmarks reported | 3 counted (board 1, self 1, retrospective 1) |
| Wet-lab validation | None recorded |
| Unverified fields | † release_milestones.weights_release, training_data.b_private_licensed |
| As of | 2026-11-16 |
What it does
Open PyTorch reproduction of AlphaFold 3 for protein, nucleic-acid and small-molecule complexes, with reproducible training and distillation pipelines. Unlike Protenix it adds federated fine-tuning on pharma private data; unlike AlphaFold 3 it differs in licence and reproducibility. AQAffinity is built on it.
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. 3 of 3 pairings are counted.
| Benchmark | Relation | Eval set / protocol | Source type | Note and evidence |
|---|---|---|---|---|
| 31 FoldBench | Official leaderboard or results | maintainer leaderboard (preview) | Board | Maintainer leaderboard (preview) · evidence |
| 30 PLINDER / PINDER / Runs N' Poses | Developer report, official protocol | Runs N' Poses (protein-ligand) | Self-reported | Runs N' Poses appears in a README bar chart; no numbers in text †partly verified · evidence |
| 01 CASP | Retrospective dataset use | CASP16 protein and RNA monomers (post hoc) | Third-party | CASP16 protein/RNA monomers, README figure only, post hoc †partly verified · evidence |
Other evaluations (outside the 44)
- AF3 antibody-antigen set (Public benchmark not among the 44) Self-reported: preview2 protocol, figures only
- Federated fine-tuning holdout (Own task set) partner: Evaluation on 1,056 held-out private structures, self-reported by Apheris, not independently verified
Developers report: the preview is the only model matching AlphaFold 3 on CASP16 RNA monomers, under a commercially usable Apache-2.0 licence with reproducible training.
Independent evidence: The FoldBench maintainer leaderboard lists the preview, run by the board; federated fine-tuning gains lack independent verification.
Training data
Group in Figure 7: Private or licensed data.
| Class | Value | Detail |
|---|---|---|
| a. Public databases | Yes | 300,000+ experimental structures plus 40M+ synthetic/distilled entries (incl. 13M MGnify) source |
| b. Private or licensed data | Yes | Federated fine-tuning by five pharma firms on 20,167 private structures, 1,056 held out (Apheris self-reported) source |
| c. Own wet-lab data used for training | Not disclosed | Whether OpenBind-0 uses newly measured data is not stated source |
| d. Wet lab used only for validation | No |
Wet-lab validation
None. The developers report no wet-lab validation.
Background
- Organization: OpenFold is a non-profit AI research consortium hosted by the Open Molecular Software Foundation, with academic and industry members (NVIDIA cites 40+ organizations). OpenFold3 was co-developed by a US university lab, a US national laboratory and a South Korean university group.
- Funding: Members contribute funding, compute and expertise; public materials name no specific grantor.
- Products and partnerships: The AISB network, run by Apheris, has AbbVie, Astex, BMS, J&J and Takeda continue training via federated learning (source lists differ slightly); Apheris also offers ApherisFold; NVIDIA ships a NIM package; default weights OpenBind-0 were trained by the UK OpenBind project with a 2025-06 cutoff.
- Related models: AlphaFold 3, Protenix, RF3, Boltz-1 / Boltz-1x, AQAffinity
Reading notes
- Its most informative feature is the federated route: whether private data that never leaves the owner improves a general model; the only evidence so far is Apheris's own account.
- The developers' own evaluations are figures without numbers and cannot be compared directly with other models.
- The 2026-10-28 release 0.5.1 is only a patch; new weights belong to 0.5.0 (2026-08-21); do not conflate them.
- Apache-2.0 plus reproducible training gives it distinct value where self fine-tuning is needed, independent of leaderboard rank.
Caveats
- No PoseBusters result; it is not in the official evaluation set.
- Sources disagree slightly on the list of federated pharma partners.
- The CASP16 pairing is post-hoc dataset reuse, not participation.
Sources
- OpenFold3 GitHub repository (repository)
- OpenFold3 GitHub releases (repository)
- OpenFold Consortium press release (2025-10-28) (press)
- OpenFold3-preview2 technical report (preprint)
- OpenFold3 on Hugging Face (repository)
- NVIDIA OpenFold3 model card (official site)
- AISB federated fine-tuning report (press)
- OpenBind third-party platform page (second-hand) (second-hand) second-hand
Corrections
3 corrections
| Field | Was | Now | Basis | Found |
|---|---|---|---|---|
| latest_update | 2026-08-21 | 2026-10-28 (tag 0.5.1) | source | 2026-11-16 |
| latest_update.description | v0.5.0 OpenBind model release: OpenBind-0 weights and recipes | v0.5.1 patch: memory reduction and deterministic inference, no new weights; OpenBind-0 weights belong to v0.5.0 (2026-08-21) | source | 2026-11-16 |
| latest_update.event_kind | new-weights | code-release | 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.