MedAgentBench — leaderboard
Interactive EHR-agent benchmark with physician-written tasks over healthcare data and FHIR-style clinical workflows.
Metric: Overall SR (self-reported). Source: benchmarklist.com. Status: saturation imminent. 12 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude 3.5 Sonnet | 69.67 |
| 2 | GPT-4o | 64 |
| 3 | DeepSeek V3 | 62.67 |
| 4 | Gemini 1.5 Pro | 62 |
| 5 | GPT-4o Mini | 56.33 |
| 6 | O3 Mini | 51.67 |
| 7 | Llama 3.3 70B | 46.33 |
| 8 | Gemini 2.0 Flash | 38.33 |
Interactive version: theaggregate.ai/benchmark?slug=medagentbench · How the rankings work · Data refreshed daily, snapshot 2026-07-22.