AgentEHR (ReAct) - Transfers: leaderboard
Metric: F1 (%; predicted transfers label set against the next recorded events, 538 MIMIC-IV-Common cases; standard ReAct agent). Source: arxiv.org. Saturation forecast: Around 2034. 5 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3 30B A3B | 27.72 |
| 2 | Qwen 3 Next 80B A3B | 23.46 |
| 3 | GPT-5 Mini | 20.53 |
| 4 | Grok 4.1 Fast | 18.26 |
Interactive version: theaggregate.ai/benchmark?slug=agentehr-react-transfers · How It Works · Data refreshed daily, snapshot 2026-09-26.