Overview
| Name | AlphaFold 3 · aliases: AlphaFold 3, AlphaFold3, AF3 |
|---|---|
| Full name | No expanded name; official materials use AlphaFold 3 |
| Ambiguous names (not auto-linked) | AlphaFold, AlphaFold Server |
| Family | Not a family entry. Single-model record; the earlier complex model AF2-Multimer has its own record |
| Organization | Google DeepMind, Isomorphic Labs |
| Organization type | Big-tech lab |
| Country | United Kingdom |
| Model class | Co-folding (protein / nucleic acid / small molecule / ion) |
| Domain | Structure & co-folding (also: Small molecules) |
| First release | † partly verified · journal Basis: Journal paper online with the official server the same day; code and weights followed with v3.0.0 on 2024-11-11 Note: No primary metadata for this date was saved this round, so it is marked unverified source |
| Other milestones | |
| Latest update | · code release Basis: GitHub release v3.0.5 v3.0.5 speeds up search and MSA featurisation and adds a CPU flag and a shard helper; v3.0.3 (2026-06-09) relicensed the code to Apache-2.0 source The most recent sourced event, not a claim that nothing changed since. |
| Status | Active · Code releases within 12 months, no new generation |
| Openness | Code: Partly open · Apache-2.0 from v3.0.3 (2026-06-09) Weights: On request · on request, non-commercial per earlier note, not re-verified Licence change: · code release Basis: v3.0.3 release notes relicensed the code to Apache-2.0 source Code and weights terms must be stated separately: code is Apache-2.0, weights are on request and their terms are still unconfirmed (unverified) |
| Benchmarks reported | 6 counted (board 3, self 1, retrospective 2, cited only 2, unconfirmed 2) |
| Wet-lab validation | None recorded |
| Unverified fields | † first_release, open_status.weights_license, release_milestones.weights_release, benchmarks_reported[2], benchmarks_reported[4], benchmarks_reported[9] |
| As of | 2026-11-16 |
What it does
A diffusion module generates all-atom coordinates directly, covering protein-ligand, protein-nucleic-acid and antibody-antigen complexes in one model. It is the de facto co-folding standard: open efforts such as Boltz-1/1x, Chai-1, Protenix and OpenFold3 set out to reproduce or approach 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. 6 of 10 pairings are counted.
| Benchmark | Relation | Eval set / protocol | Source type | Note and evidence |
|---|---|---|---|---|
| 15 CAMEO | Official leaderboard or results | operator-run complex and ligand baseline, 2024-01 to 2025-06 | Board | CAMEO operators ran AF3 as a baseline (2025 assessment paper); maintainer-run, not a developer submission. †partly verified · evidence |
| 31 FoldBench | Official leaderboard or results | maintainer leaderboard | Board | Maintainer leaderboard (FoldBench repo) · evidence |
| 34 AbBiBench | Official leaderboard or results | registered interface-score entry | Board | Benchmark-registered ipSAE correlation (not structure accuracy), read from paper figure, not rerun †unverified · no source link |
| 05 PoseBusters | Developer report, official protocol | PoseBusters V1 (428), official set | Self-reported | Self-report on the official V1 set; V2 numbers are third-party recomputations · evidence |
| 01 CASP | Retrospective dataset use | CASP15 public RNA targets | Third-party | AF3 paper used CASP15 RNA targets post hoc; in CASP16 AF3 is only a component of other groups, no own entry · evidence |
| 33 PoseX | Retrospective dataset use | self-docking / cross-docking, benchmark authors' run | Third-party | PoseX authors ran AF3 under the same protocol (third party) †partly verified · evidence |
| 25 RNA-Puzzles | Cited as comparison only (not counted) | CASP15 RNA, quoted in another paper | Third-party | CASP15 RNA value from its own paper, quoted by NeuralPLexer3; not RNA-Puzzles proper †partly verified · evidence |
| 30 PLINDER / PINDER / Runs N' Poses | Cited as comparison only (not counted) | Runs N' Poses, best@5 | Third-party | Numbers quoted second-hand from the Pearl paper †partly verified · evidence |
| 12 DUD-E / LIT-PCBA | Unconfirmed (not counted) | — | Unconfirmed source | Only a second-hand pose claim in an RSC 2026 paper; no numbers; the benchmark paper does not evaluate AF3 †disputed · no source link |
| 22 CAPRI | Unconfirmed (not counted) | CASP16 complexes | Unconfirmed source | No standalone entry appears in the official CAPRI assessment material; only secondary sources call it a component of most pipelines. †disputed · evidence |
Other evaluations (outside the 44)
- Third-party prospective crystal-structure evaluation (third party prospective evaluation) Third-party: A prospective comparison on about 551-557 newly solved complexes: good pose quality, but confidence is not fit for virtual-screening ranking (preprint plus second-hand)
- Role as a control in 2026 boards (Comparison against baselines only) Third-party: Most new models' papers list it as the main control, while the developers rarely report new evaluations
Developers report: protein-ligand docking is significantly better than classical docking tools, with protein, nucleic acid, small-molecule and ion complexes unified in one model.
Independent evidence: Several third-party papers recomputed it under stricter protocols and a maintainer leaderboard includes it; leakage-controlled splits show accuracy falling as similarity drops, indicating memorisation.
Training data
Group in Figure 7: Public data only.
| Class | Value | Detail |
|---|---|---|
| a. Public databases | Yes | Public PDB plus distillation data; the paper gives no per-database sizes source |
| b. Private or licensed data | Not disclosed | |
| c. Own wet-lab data used for training | No | |
| d. Wet lab used only for validation | No | The developers report no wet-lab work |
Wet-lab validation
None. The developers report no wet-lab validation.
Background
- Organization: The model was built by a big-tech AI lab together with its sister company, which was spun out of the same parent in 2021, is headquartered in London and positions itself as an AI drug-design company; it reports over 350 staff across London, Cambridge (Massachusetts) and Lausanne (2026-05 reporting).
- Funding: 2025-03-31 first external round of $600M led by Thrive Capital with GV and Alphabet; 2026-05-12 a $2.1B Series B again led by Thrive Capital, adding MGX, Temasek, CapitalG and a UK sovereign AI fund; valuation undisclosed.
- Products and partnerships: 2024-01 deals with two large pharma companies totalling $82.5M upfront and up to about $2.9B in milestones, excluding royalties. The internal engine IsoDDE (disclosed 2026-02-10) extends it; the official blog gives no numbers page.
- Related models: AF2-Multimer, OpenFold3, Protenix, Boltz-1 / Boltz-1x, Chai-1, IsoDDE
Reading notes
- Its docking results differ widely across papers because PoseBusters V1 and V2, sample counts and pose-selection rules differ; the numbers are not comparable across papers.
- All co-folding models degrade once results are stratified by similarity to training data, so its high scores should be read per similarity bin.
- In third-party prospective evaluations pose quality is good, but confidence is not sufficient for virtual-screening ranking on its own.
- The code is Apache-2.0 while the weights remain on request with unconfirmed terms, so commercial usability turns on the weights side.
Caveats
- Code and weights terms are separate: the weights terms are unconfirmed and must not be inferred from the code licence (unverified).
- The first-release date lacks primary metadata and is marked partially verified.
- Two pairings rest only on the site's own pages and must display as unverified.
- Challenges whose official assessments contain no entry of its own are not counted as established relations here.
Sources
- The model's original journal paper (journal)
- Paper full text (public archive) (paper)
- Official repository releases (repository)
- One of the third-party recomputation papers (third-party paper)
- A second third-party recomputation paper (third-party paper)
- Baseline paper by the continuous-evaluation operators (third-party paper)
- Maintainer leaderboard repository (leaderboard)
- Re-run paper by the benchmark's authors (third-party paper)
- Official announcement of the first external round (official site)
Corrections
3 corrections
| Field | Was | Now | Basis | Found |
|---|---|---|---|---|
| open_status | Code and weights are both limited to non-commercial academic request | Code is Apache-2.0 from v3.0.3 (2026-06-09); weights are on request with their own, still unconfirmed terms | source | 2026-11-16 |
| first_release | The first release was treated as fully verified from the journal date | The date stands, but with no primary metadata this round it is downgraded to partially verified | source | 2026-11-16 |
| benchmarks_reported | Third-party recomputations and developer self-reports were merged into one cell | Split across the seven relation types: official board, self-report on the official protocol, third-party re-run and unconfirmed each stand alone | no source link | 2026-11-16 |
Part of the AI for Bio benchmarks survey · all 112 models · open in the explorer. Record as of 2026-11-16.