PhysicianBench
Progress Over Time
Interactive timeline showing model performance evolution on PhysicianBench
State-of-the-art frontier
Open
Proprietary
PhysicianBench Leaderboard
2 models
| Context | Cost | License | ||||
|---|---|---|---|---|---|---|
| 1 |  Anthropic | — | 1.0M | $2.00 / $10.00 | ||
| 2 | Anthropic | — | 1.0M | $0.10 / $0.50 |
Notice missing or incorrect data?
What is PhysicianBench?
PhysicianBench is a public benchmark of 100 physician tasks carried out in an electronic health record (EHR), measuring agentic clinical task completion.
PhysicianBench is a text benchmark evaluating models on healthcare and agents tasks. LLM Stats tracks 2 models on this benchmark, scored on a 0–1 scale. The current average is 0.5, with the leader at 0.6.
Compare leaders on the best AI for healthcare and best AI for agents leaderboards.
Current leaders
Claude Sonnet 5.5 from Anthropic currently leads the PhysicianBench leaderboard with a score of 0.632 across 2 evaluated AI models.
FAQ
Common questions about the PhysicianBench benchmark and leaderboard.