Insilico Medicine vs Recursion (2026)
Two listed companies running the same double business, platform vendor and clinical stage biotech at once, and the comparison comes down to how far each has got a molecule. Insilico has the cleaner end to end story: its target identification engine picked the target, its generative chemistry engine designed the molecule, the discovery was published in peer reviewed literature and the asset holds orphan drug designation. Recursion has the deeper data asset, generating its own biology at scale and learning from cellular images and multiomic data rather than from public sources, with disclosed partnership economics that show what pharmaceutical companies have actually paid. Both structures carry the same conflict: the company that chooses the target also designs the molecule, runs the analysis and reports the result. Judge both on assets that clear human trials, not on platform architecture.
- It is the clearest end to end case in the category: one engine prioritised the target, another generated the molecule, and the resulting drug reached the clinic, with the discovery published in peer reviewed literature.
- The regulatory position is real rather than prospective, with orphan drug designation held on a lead asset, which is the kind of external checkpoint this category rarely reaches.
- The platform is sold as software as well as run internally, with named engines and disclosed methods, so a pharmaceutical customer can license the same tools rather than only partner.
- The data flywheel is the asset: high throughput cellular experimentation feeding machine learning on imaging and multiomic data, so the platform generates its own training data rather than mining public sources.
- Partnership economics are disclosed as a listed registrant, so the market's valuation of the platform is visible rather than described in a press release.
- The oversight is empirical by construction, with model hypotheses tested in the wet laboratory before they advance.
This comparison is published by AI Health Index, an independent research platform that compares healthcare AI vendors objectively. Insilico Medicine and Recursion 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 | Insilico Medicine | Recursion |
|---|---|---|
| Primary category | Drug Discovery AI | Drug Discovery AI |
| Founded | 2014 | Not recorded |
| Headquarters | Cambridge, Massachusetts | Salt Lake City, UT |
| Website | insilico.com | recursion.com |
Side by Side
Each record in one paragraph
Written to be quoted whole. Each paragraph states what the AI Health Index verified about the vendor, with the caveats attached. Generated from this pair’s live capability grades, so it moves when a grade moves.
The AI Health Index awards Insilico Medicine its top capability grade on AI Centrality, Clinical and Operational Evidence and FDA and Regulatory Status. Set against Recursion, Insilico Medicine grades higher on several axes, including Clinical and Operational Evidence, FDA and Regulatory Status and AI Liability and Recourse. Grades reflect evidence the AI Health Index could verify at the last review, so a low grade records disclosure the vendor has not published rather than a capability it has been shown to lack.
Source: AI Health Index, August 2026
The AI Health Index awards Recursion its top capability grade on AI Centrality and Commercial Transparency. Set against Insilico Medicine, Recursion grades higher on several axes, including Model Supply Chain Disclosure, Security Certifications and Trust Center and AI Governance and Bias Disclosure. Its thinnest published disclosure sits on AI Liability and Recourse. Grades reflect evidence the AI Health Index could verify at the last review, so a low grade records disclosure the vendor has not published rather than a capability it has been shown to lack.
Source: AI Health Index, August 2026
Questions buyers ask
Should we choose Insilico Medicine or Recursion?
On the axes where the AI Health Index separates them, Insilico Medicine grades higher on several axes, including Clinical and Operational Evidence, FDA and Regulatory Status and AI Liability and Recourse, and Recursion grades higher on several axes, including Model Supply Chain Disclosure, Security Certifications and Trust Center and AI Governance and Bias Disclosure. Neither leads on the greater share of scored axes, so the decision turns on which constraint is binding rather than on an overall winner.
Where do Insilico Medicine and Recursion differ most?
The widest separation the AI Health Index records between Insilico Medicine and Recursion is on Commercial Transparency, where Insilico Medicine grades C and Recursion grades A. That axis sits in the Commercial group, so it should carry the most weight for a buyer whose binding constraint is contracting, scope and what the price actually covers.
Where do Insilico Medicine and Recursion grade the same?
The AI Health Index grades Insilico Medicine and Recursion the same on several axes, including AI Centrality, Autonomy and Oversight Model and Model and Technology Transparency. Neither holds an advantage the index can evidence on those axes, so they should not carry weight in a selection between these two.
What have Insilico Medicine and Recursion not disclosed?
At the last review, at least one of Insilico Medicine and Recursion published thin or absent detail on AI Liability and Recourse. The AI Health Index treats an absent disclosure as a gap in the public record rather than a failure of the product, so these are the axes to get in writing during diligence instead of inferring from the grade.
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 companies are simultaneously platform vendors and clinical stage biotechs, which is the structural conflict worth understanding before reading any of their evidence: the same organisation selects the target, designs the molecule, runs the analysis and reports the result. Neither publishes a security attestation or trust centre. Insilico publishes extensively and still leaves the governance question unanswered, which are different things.
Recursion narrowed its internal pipeline in 2025, so any breadth claim predating that should be checked. Pipeline progress is the only evidence that ultimately matters in this category and both should be judged on assets that clear human trials rather than on platform descriptions.