Overview
| Name | RF3 · aliases: RF3, RoseTTAFold3, RoseTTAFold 3 |
|---|---|
| Full name | RoseTTAFold3 |
| Ambiguous names (not auto-linked) | RoseTTAFold |
| Family | Not a family entry. Single model; design models sharing the repository have their own entries |
| Organization | University of Washington Institute for Protein Design, RosettaCommons |
| Organization type | Academic lab |
| Country | United States |
| Model class | Co-folding (arbitrary biomolecular complexes) |
| Domain | Structure & co-folding (also: Small molecules) |
| First release | · preprint Basis: bioRxiv preprint v1 (AtomWorks and RF3) source |
| Other milestones |
|
| Latest update | · maintenance only Basis: Foundry repository commit log Foundry repository restructure (shared infrastructure moved into model packages); latest tag remains v0.2.0 (2026-06-05); commits to 2026-11-04 are docs; no RF3 weight change Note: No 'Foundry 1.0' tag exists source The most recent sourced event, not a claim that nothing changed since. |
| Status | Active · Shared repository has a release and maintenance commits within 12 months |
| Openness | Code: Open · BSD Weights: Open · BSD Code, weights and data pipeline under BSD; exact BSD variant not recorded this round |
| Benchmarks reported | 1 counted (board 1) |
| Wet-lab validation | None recorded |
| Unverified fields | † release_milestones.code_release, release_milestones.weights_release, open_status.code_license, open_status.weights_license |
| As of | 2026-11-16 |
What it does
Successor to RoseTTAFold All-Atom, retrained on the AtomWorks data framework to predict arbitrary biomolecular complexes with better chirality handling. AtomWorks serves both structure prediction and design and is also used by RFdiffusion2/3. Like OpenFold3 and Protenix it is an open reproduction route, but it comes from a design lab sharing one data pipeline with design models.
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.
| Benchmark | Relation | Eval set / protocol | Source type | Note and evidence |
|---|---|---|---|---|
| 31 FoldBench | Official leaderboard or results | maintainer leaderboard (2024-01+ subset) | Board | Maintainer leaderboard (2024-01+ subset) · evidence |
Other evaluations (outside the 44)
- Gap to AlphaFold 3 (Comparison against baselines only) Self-reported: The preprint says it narrows the gap between closed AF3 and open implementations; no values taken this round
Developers report: it narrows the gap between closed AlphaFold 3 and open implementations and improves chirality handling and atom-distance conditioning.
Independent evidence: Listed on the FoldBench maintainer leaderboard, run by the board.
Training data
Group in Figure 7: Public data only.
| Class | Value | Detail |
|---|---|---|
| a. Public databases | Yes | PDB, processed through the AtomWorks pipeline source |
| b. Private or licensed data | No | |
| c. Own wet-lab data used for training | No | |
| d. Wet lab used only for validation | No |
Wet-lab validation
None. The developers report no wet-lab validation.
Background
- Organization: The University of Washington Institute for Protein Design (IPD) is an academic protein design institute whose director shared the 2024 Nobel Prize in Chemistry; RF3 was developed by two of its labs with the Microsoft AI for Good lab.
- Funding: Predecessor RoseTTAFold All-Atom acknowledged The Audacious Project, HHMI, the Gates Foundation, Open Philanthropy, Schmidt Futures, the Helmsley Trust and a Microsoft donation; RF3's full funding statement was not transcribed.
- Products and partnerships: Product line: RoseTTAFold All-Atom (predecessor), the RFdiffusion series (design) and RF3 (open-weight co-folding), with code in the Foundry repository; collaboration with Microsoft.
- Related models: RFdiffusion2 / RFdiffusion3, OpenFold3, Protenix, AlphaFold 3
Reading notes
- No verifiable self-reported numbers exist, so it cannot be called better or worse than AlphaFold 3 or Boltz.
- The point is AtomWorks: a unified data and training pipeline matters more for design models.
- Foundry has tags up to v0.2.0 only; the claim that 'Foundry 1.0 was released' is unsupported.
- Design-side enzyme active-site results belong to RFdiffusion2/3, not RF3 itself.
Caveats
- The date follows bioRxiv (2025-08-14); some second-hand sources say 2025-09.
- No PoseBusters result was found in two search rounds.
- No journal version and no RF3-specific new weights found.
Sources
- AtomWorks and RF3 bioRxiv preprint (preprint)
- RosettaCommons: AtomWorks and RF3 open-sourced in Foundry (official site)
- Foundry GitHub releases (repository)
- Foundry commit log (repository)
- Third-party service page: RoseTTAFold3 (second-hand) (second-hand) second-hand
Corrections
3 corrections
| Field | Was | Now | Basis | Found |
|---|---|---|---|---|
| latest_update | 2026-06-05 (v0.2.0) | 2026-10-16 (repository restructure commit) | source | 2026-11-16 |
| latest_update.description | Foundry 1.0 restructure / Foundry 1.0 released | Removed: no Foundry 1.0 tag exists; latest is v0.2.0 (2026-06-05) | source | 2026-11-16 |
| benchmarks_reported | No verified site benchmark pairing | Listed on the FoldBench maintainer leaderboard (official participation) | 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.