Ranks models on health using its own composite index.
LLM-Stats, 20261 verified conflict
Key facts
| What it measures | Ranks models on health using its own composite index. |
| Who should care | Nobody making a clinical decision. |
| Use it when | Casual orientation only. |
| Do not use it for | Any decision that matters. Method and underlying sources are undocumented. |
| Score scale | Undocumented composite. Not comparable to anything else on this page. |
| Grader method | unknown |
| First released | 2026 |
| Languages | English |
| Use cases | aggregator |
| Citation | LLM-Stats, 2026 |
| Status | active |
Verified conflicts of interest
Independence assessment
Scoring method and source of underlying numbers not documented on the public page. Scale is not comparable to MedHELM mean win rate despite both being presented as healthcare rankings.
Scope
Commercial aggregator publishing a healthcare model ranking on its own composite scale.
Frequently asked questions
What does LLM-Stats Healthcare Leaderboard measure?
Ranks models on health using its own composite index.
Who should use LLM-Stats Healthcare Leaderboard?
Nobody making a clinical decision. Casual orientation only.
What should LLM-Stats Healthcare Leaderboard not be used for?
Any decision that matters. Method and underlying sources are undocumented.
How are LLM-Stats Healthcare Leaderboard scores reported?
Undocumented composite. Not comparable to anything else on this page. Scores from different benchmarks are not comparable to each other.
Is LLM-Stats Healthcare Leaderboard independent?
Not fully. Scoring method not published.
Compare with
Aggregates published medical benchmark scores into one ranking table.
