Recursion vs Schrödinger (2026)
Both put computation at the center of drug discovery, from opposite starting points. Recursion generates its own biology at scale: automated labs run up to two million experiments a week, and foundation models trained on more than 50 petabytes of cellular images, transcriptomics and chemistry pick what to test next, with each lab result fed back into training. Schrödinger starts from physics. Its simulation software, including Glide for docking, FEP+ for binding affinity and LiveDesign for collaborative design, is licensed to pharmaceutical, biotechnology and academic teams, with machine learning used alongside the physics rather than in place of it. The practical difference is what you buy. Recursion is a partner and a drug developer with its own clinical programs; Schrödinger sells software a team runs itself, and develops a pipeline of its own on it.
- Automated labs running up to two million experiments a week, feeding foundation models trained on more than 50 petabytes of the company's own data.
- Published methods and public releases, including Phenom, MolE, TxPert, RxRx3 and OpenPhenom.
- Seven internal programs in oncology and rare disease, several in clinical studies.
- Physics based simulation software a team licenses and runs itself: Maestro, Glide, FEP+, LiveDesign and BioLuminate.
- Machine learning paired with physics, including an ML module in LiveDesign for predictive models on a team's own data.
- A therapeutics pipeline of its own built on the same platform, and a materials science line beside it.
This comparison is published by AI Health Index, an independent research platform that compares healthcare AI vendors objectively. Recursion and Schrödinger 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 | Recursion | Schrödinger |
|---|---|---|
| Primary category | Drug Discovery AI | Drug Discovery AI |
| Headquarters | Salt Lake City, UT | New York, NY |
| Website | recursion.com | schrodinger.com |
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.
Recursion (Nasdaq: RXRX) is a Salt Lake City drug discovery company built around the Recursion OS, which pairs automated wet labs running up to 2 million experiments a week with machine learning foundation models trained on the resulting 50 petabyte plus dataset of cellular images, transcriptomics and chemistry, in a loop where predictions are tested in the lab and fed back into training. Its combination with Exscientia in November 2024 added generative chemistry design and automated synthesis.
Source: AI Health Index, September 2026
Computational chemistry software company (Nasdaq: SDGR) whose physics based molecular simulation platform is licensed to pharmaceutical, biotechnology, industrial and academic organizations, alongside a proprietary therapeutics pipeline built on the same platform.
Source: AI Health Index, September 2026
Questions buyers ask
How are Recursion and Schrödinger priced and sold?
Recursion sells no software license; it works with pharmaceutical partners through discovery collaborations and also develops its own pipeline, and the partners page describes pharmaceutical, technology and data partnerships.
As a listed company Schrödinger reports software revenue, customer metrics and pipeline spend, which describes its own economics rather than what a licensee pays. 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 do Recursion and Schrödinger handle patient data?
Recursion's home page features a post on "leveraging the power of patient data" in drug discovery, and its data corpus includes material licensed from companies holding human genomic and clinical data. No published statement covers consent provenance for that licensed data, the de-identification standard applied, permitted secondary uses, retention, or what happens to trained model representations if a license ends.
For Schrödinger, patient data does not enter the platform; the company's separate clinical trial policy covers participants in its own trials. 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 Recursion and Schrödinger leave to the clinician?
Predictions from the Recursion OS are tested in the company's automated labs, a wet and dry "lab-in-the-loop" run by what it calls bilingual teams of scientists and technologists, so model output meets physical evidence before a program moves on. Human judgment over the portfolio is visible in practice: the company has publicly deprioritized and paused clinical programs.
In Schrödinger's case, the decision to make a molecule stays with the customer's scientists. 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. Neither company publishes a price: Recursion works through partnerships, and Schrödinger licenses software on terms agreed with each customer.
Ask both how a prediction that looked strong computationally and failed in the lab is recorded and fed back into the models.