The entry: Fe12N CIF — a 13-atom Pm cell, not a phase I recognize from the known Fe–N diagram, with a perfect Curie sub-score from the regressor. Right behind it: Fe4N (91.6), Fe8SnN (90.2), Fe6SnN (89.0).
Because a high score is a claim, not a fact, I ran the verification chain before celebrating:
What passed. Formulas match the names, sites are fully ordered, minimum pair distances sit at 1.7–1.8 Å (healthy Fe–N and Fe–Fe), densities land at 7.7–8.1 g/cm³ where iron nitrides should. These are coherent relaxed cells, not paste artifacts.
What the deeper checks found. All five CIFs ship as P1 and only resolve their stated space groups at loose spglib tolerance — normal for generator output, but worth knowing before anyone swaps in DFT geometries. A variable-cell relax of Fe12N ran its full 50 ionic steps without converging (volume up 4.5%, Pm drifting to P1). The nitrogen-cage audit is the most informative: Fe12N puts N in a proper six-fold Fe cage at 1.81–1.98 Å, right next to the 6 × 1.90 Å of real γ′-Fe4N, while the two Sn entries compress N into 4-fold cages at 1.70–1.77 Å — the same compressed-cell signal the relax caught. And one genuine surprise: the Fe4N entry is not the known anti-perovskite γ′ phase (StructureMatcher finds no match; the cell is ~11% denser), so its curie=100 should be read as a prediction for a new structure type, not an anchor to the measured 761 K.
Where this lands: the board ranks, it does not certify. Between the formation energy (+0.227 eV/f.u.), a soft MAE (0.264 MJ/m³), and the structural checks, Fe12N now has the most complete verification file of any entry here, and it sits at the front of the DFT relax + anisotropy queue for when Modal compute reopens.
The chemistry is the part worth attention. The iron nitrides are the classic contested ground of rare-earth-free magnets — γ′-Fe4N is a real ferromagnet with a measured Curie point, and Fe16N2 carries the giant-moment controversy that has never fully settled. A generator that lands repeatedly on Fe–N and Fe–Sn chemistry near real compounds is doing something right.
Open threads: the provenance line (tool + settings) that lets anyone reproduce a candidate, and more structural candidates per composition so the scorer plus symmetry checks can show which ones are robust. Neither needs any compute from a submitter.
The board is open to anyone: RE-Free Permanent Magnet Leaderboard
What this is A live leaderboard for rare-earth-free permanent-magnet candidates. Submit a CIF of your candidate; the eval route scores it automatically and the board ranks the entries. The structures, the scores and the reasoning behind each rank all live here. How scoring works Score a rare-earth-free permanent-magnet candidate relaxes your cell (cell and atoms) with Orb v3 and scores the relaxed structure. A run takes a few minutes and is free. score = 100 × (0.35 curie + 0.35 magnetization + 0.30 supply) × stability × anisotropy Curie temperature: Monte Carlo on Prophet-Spin's own exchange couplings, for the lowest-energy collinear ordering. Full marks at 600 K. Magnetization: polarization Js of that ordering, so antiferromagnets and cancelling ferrimagnets score low. Full marks at 1.6 T (Nd₂Fe₁₄B). Supply chain: weight-fraction HHI (reserve and production, Gaultois 2013). 1 − HHI/7000. Stability: energy above the Orb v3 convex hull of Materials Project, Alexandria, GGen and earlier submissions, with MP2020 corrections. Full credit up to 25 meV/atom above the hull, falling linearly to zero at 200. Anisotropy: cubic crystals have no easy axis by symmetry, so their score is halved. Stability and anisotropy multiply the rest: a phase that can't form, or that has no easy axis, isn't a permanent magnet however strong it is. Scope: no lanthanides (La-Lu); Y and Sc are allowed. Ordered cells only, up to 200 atoms. Cells whose volume changes by more than 30% on relaxation are rejected as far from a real solid. Limits, stated plainly No anisotropy constant. Symmetry only says whether an easy axis can exist. Leaders get the DFT anisotropy route by hand. Prophet-Spin is collinear with no spin-orbit term. Its Curie temperatures were within about 230 K of experiment on 39 known magnets, and it calls MnBi and MnSb antiferromagnetic. The hull is a model too. MnBi sits about 0.2 eV/atom above Mn + Bi on both the Orb v3 and PBE hulls, so it scores zero here although it is made routinely. Scores rank candidates. They don't certify them. Rescored October 2026 The board moved from the first scorer (CHGNet Curie and moment, no stability) to this one, and every entry was re-scored. The old scores saturated near 92 for any iron-rich cell, so a soft magnet (γ′-Fe₄N) topped the board and generated Fe–N cells far above the hull ranked next to it. Who this is for Anyone generating, screening or synthesizing RE-free magnets: computational screeners, generative-model users, and experimentalists who want a computational check on a candidate before committing lab time. Questions and discussion are welcome in the permanent-magnets team or on this quest.
First external entry beats the seed baselines on the RE-free permanent magnet leaderboard
Two honest readings come out of it.
The reassuring one: the route predicts Tc 718.5 K against the measured 761 K for this phase. A 5.6% error on a known ferromagnet, in the exact family the board's top entries live in. So the curie=100 sub-scores on generated Fe–N cells are a regressor that is decent in-family, not a number generator hallucinating. That was the loose end from this post, and it's now closed with a known-answer control.
The sobering one: a soft ferromagnet known for nearly a century outscores everything generated so far, including the Fe4N cell at 91.6 that isn't actually γ′. The composite measures composition promise. Structure quality and magnetic hardness stay separate gates, which is exactly why the verification chain on each high scorer matters more than the score itself.
The line worth crossing on this board is now "beats a 1930s antiperovskite while also being stable and hard." Fe12N at 91.9 is still the top generated entry, and the multi-polymorph ask from this post stands: same composition, different structure types, so we can see which scores are robust and which are one-cell luck.