EvolutionaryScale vs Profluent (2026)
Both build protein language models that generate new proteins, and both have shown a designed protein working in the lab. EvolutionaryScale, now part of Chan Zuckerberg Biohub, publishes the ESM family: ESM3, trained on 2.78 billion protein sequences at 98 billion parameters and published in Science in 2025, models sequence, structure and function together, and its esmGFP is a fluorescent protein far from any natural one. Profluent builds on its ProGen models, pairs them with task specific ones and an in house lab, and its OpenCRISPR-1 gene editor, published in Nature in 2025, matched SpCas9's on target editing while cutting off target editing from 6.1 to 0.32 percent. EvolutionaryScale offers its models through the Biohub Platform with a free credit tier. Profluent licenses OpenCRISPR-1 free and otherwise works on terms it does not publish.
- ESM3, which takes any combination of sequence, structure and function as a prompt, published in Science in 2025.
- Models served through the Biohub Platform with a free credit tier, and model cards that state intended use and clinical limits.
- A model family that extends to ESM Cambrian for representations and ESMFold2 for structure prediction.
- A published, measured result: OpenCRISPR-1's editing and off target rates against SpCas9 (Nature, 2025).
- An in house wet lab that tests what the models generate.
- OpenCRISPR-1 available to license free of charge.
This comparison is published by AI Health Index, an independent research platform that compares healthcare AI vendors objectively. EvolutionaryScale and Profluent are each graded against the same capability taxonomy, from each vendor's own public materials and the regulatory record, under the AI Health Index verification standard. No vendor pays for placement, and no vendor has reviewed this page. How this evidence is graded
Plain facts
| Fact | EvolutionaryScale | Profluent |
|---|---|---|
| Primary category | Drug Discovery AI | Drug Discovery AI |
| Founded | Not recorded | 2022 |
| Headquarters | New York, NY | Emeryville, CA |
| Website | evolutionaryscale.ai | profluent.bio |
Side by Side
Select any grade to read the note behind it.
Each vendor in one paragraph
Written to be quoted whole. Each paragraph opens the AI Health Index profile of the vendor: what the product is, who buys it and what it does.
AI research lab building protein language models, founded by researchers who developed the ESM family at Meta and now part of Chan Zuckerberg Biohub, which serves the models and their documentation on the Biohub Platform under Biohub's terms. ESM3 models a protein's sequence, structure and function together, so a scientist can supply any combination of the three as a prompt and generate a protein with specified properties; it was published in Science in January 2025 and trained on 2.78 billion protein sequences at 98 billion parameters.
Source: AI Health Index, September 2026
Protein design company in Emeryville, California, built on the ProGen family of protein language models, which grew out of research first showing that large language models can generate functional proteins across diverse families, published in Nature Biotechnology in 2023. The company pairs its generative models with task specific ones (ProseLM for structure conditioned design, Protein2PAM for the DNA motifs a gene editor recognizes) and an in house wet lab that tests what the models write.
Source: AI Health Index, September 2026
Questions buyers ask
Which settings and specialties do EvolutionaryScale and Profluent cover?
For EvolutionaryScale, the models work on proteins as a class rather than on a disease area, and the company names the uses it is built for: designing enzymes that break down plastic, proteins that capture carbon, antibodies, and new medicines, with the ESM Atlas covering proteins across all of life.
With Profluent, the company states that its platform is pointed first at CRISPR and gene editing, and names applications from new therapeutics to industrial enzymes across medicine, agriculture and beyond, with designs spanning gene editors, antibodies and broader enzymes and a partnership on recombinases for genetic medicine announced in April 2026. Modality is proteins rather than small molecules, which is the real boundary. From the AI Health Index, drawn from each vendor's own published materials and the regulatory record, verified September 28, 2026. No vendor pays for placement.
What evidence is published for EvolutionaryScale and Profluent?
In EvolutionaryScale's case, the platform's scale is visible in the ESM Atlas, an open database of annotations for more than 6.8 billion proteins with 1.1 billion predicted structures.
For Profluent, the founding method paper, showing that language models generate functional proteins across diverse families, appeared in Nature Biotechnology in 2023. From the AI Health Index, drawn from each vendor's own published materials and the regulatory record, verified September 28, 2026. No vendor pays for placement.
How much do EvolutionaryScale and Profluent leave to the clinician?
With EvolutionaryScale, the model cards and the Limitations page state that outputs are computational predictions, not experimentally validated, and not intended for clinical or therapeutic use without further validation, and the ESM Atlas search is flagged as using an agent that may answer inaccurately. Nothing acts on its own: a design is a proposal until the user expresses and characterizes it.
In Profluent's case, the oversight is demonstrated in the flagship case rather than specified as a standing practice a partner can hold the company to. From the AI Health Index, drawn from each vendor's own published materials and the regulatory record, verified September 28, 2026. No vendor pays for placement.
Related comparisons
Other published head to head assessments involving these vendors or their closest peers. The full set for this category is on the Drug Discovery AI page.
Both records were reviewed on this site in September 2026. EvolutionaryScale's models now run under Biohub's terms, so check which organization you contract with.
Ask both what share of generated designs work in the lab, not only the best example.