Overview
| Name | xTrimoPGLM · aliases: xTrimoPGLM, xTrimoPGLM-100B, xT-Fold, xTrimoPGLM-Fold |
|---|---|
| Full name | The paper gives no expanded name |
| Ambiguous names (not auto-linked) | xTrimo |
| Family | Not a family entry. Several sizes and the folding branch are treated as versions within one record |
| Organization | BioMap, Tsinghua University, MBZUAI |
| Organization type | Mixed |
| Country | China, United Arab Emirates |
| Model class | Protein LM / folding |
| Domain | Proteins (also: Structure & co-folding) |
| First release | · paper revision Basis: bioRxiv preprint v1 source |
| Other milestones | |
| Latest update | · journal Basis: Nature Methods online Journal version published; arXiv v2 had been posted on 2024-12-09 source The most recent sourced event, not a claim that nothing changed since. |
| Status | Maintained only · Most recent sourced event is the 2025-04 journal paper |
| Openness | Code: Partly open Weights: Unclear Some sizes have weights on Hugging Face and several are in the ProteinGym table; licence not retrieved this round |
| Benchmarks reported | 4 counted (board 1, self 1, retrospective 2) |
| Wet-lab validation | None recorded |
| Unverified fields | † open_status.weights, open_status.code_license, open_status.weights_license, release_milestones.code_release |
| As of | 2026-11-17 |
What it does
Combines masked-language and autoregressive (GLM) objectives in one 100B-parameter model for both protein representation and sequence generation; the xT-Fold branch predicts structure from language-model representations. Compared with ESM3 it takes the single very large model route, far larger than contemporaneous ESM 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. 4 of 4 pairings are counted.
| Benchmark | Relation | Eval set / protocol | Source type | Note and evidence |
|---|---|---|---|---|
| 02 ProteinGym | Official leaderboard or results | — | Board | Entry on the official summary table · evidence |
| 26 FLIP / FLIP2 | Developer report, official protocol | — | Self-reported | Self-reported after fine-tuning on the random control split · evidence |
| 01 CASP | Retrospective dataset use | — | Third-party | Post hoc on CASP15 (n=56) · evidence |
| 15 CAMEO | Retrospective dataset use | — | Third-party | CAMEO 2022-04 to 06 static set, n=194. · evidence |
Other evaluations (outside the 44)
- 18 protein understanding tasks (Own task set) Self-reported: The authors report beating prior state of the art on 15 of 18; mostly fine-tuned, not comparable with zero-shot boards
- Folding branch vs single-sequence methods (Comparison against baselines only) Self-reported: Compared with ESMFold and OmegaFold; still behind MSA/template methods (author-reported)
Developers report: one 100B model covers understanding and generation, beats prior state of the art on most understanding tasks, and its folding branch beats other single-sequence methods.
Independent evidence: The ProteinGym maintainers' summary table lists several sizes and shows the 100B size no better than smaller ones, consistent with the observation that pLM scaling plateaus after roughly 1B to 4B.
Training data
Group in Figure 7: Public data only.
| Class | Value | Detail |
|---|---|---|
| a. Public databases | Yes | About 939M protein sequences, 200B tokens: UniRef90 plus ColabFoldDB clusters and members source |
| b. Private or licensed data | No | The paper lists only two public databases source |
| c. Own wet-lab data used for training | No | source |
| d. Wet lab used only for validation | No | source |
Wet-lab validation
None. The developers report no wet-lab validation.
Background
- Organization: BioMap was founded in Beijing in 2020 as an AI life-science company that positions itself as an enabler rather than a drug developer; paper authors also come from Tsinghua University and MBZUAI.
- Funding: A $100M Series A in 2021 led by GGV; a 2024-06 strategic round of undisclosed size; a 2026-03 media report of a confidential Hong Kong IPO filing, not announced by the company.
- Products and partnerships: A 2023-10 Sanofi deal for AI modules ($10M upfront, milestones over $1B); the series also includes xTrimoSCPerturb/scFoundation, and a multimodal xTrimo V3 was announced in 2026-10.
- Related models: ESM3, xTrimoSCPerturb / scFoundation
Reading notes
- The 100B scale shows no edge on ProteinGym; in the official table it trails the group's own 3B size.
- Folding results are small-sample, self-reported post-hoc evaluations, not CASP/CAMEO entries.
- FLIP covers only the GB1 subtask after fine-tuning and does not mean leading on the full suite.
Caveats
- "Ahead on 15 of 18" is author-reported and mostly fine-tuned.
- CASP15 and CAMEO are post-hoc data reuse, not counted as participation.
- Weight availability and licences were not checked item by item.
- An earlier site figure of "about 94B unique sequences" was an order-of-magnitude error and is corrected from the paper.
Sources
- arXiv preprint (preprint)
- Nature Methods paper (journal)
- bioRxiv version record (preprint)
- ProteinGym official summary table (leaderboard)
- Sanofi collaboration press release (press)
Corrections
2 corrections
Part of the AI for Bio benchmarks survey · all 112 models · open in the explorer. Record as of 2026-11-17.