CareTransition-Audit - Completeness Ranking: leaderboard
Metric: Spearman correlation (-1 to 1) between the per-summary documentation completeness (share of Yes labels) the model assigns and the one the clinician assigns, over the 50 MIMIC-IV discharge summaries of the 46-question DISCHARGED audit checklist; higher is better. Source: arxiv.org. Saturation forecast: Around September 2027. 11 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Flash (Preview) | 0.54 |
| 2 | Claude Sonnet 4.5 | 0.43 |
| 3 | DeepSeek V3.2 | 0.41 |
| 4 | GPT-5.4 | 0.37 |
| 5 | Nova 2.0 Lite (Non-reasoning) | 0.36 |
| 6 | GPT-4o | 0.34 |
| 7 | Llama 4 Maverick | 0.34 |
| 8 | Grok 4.1 Fast | 0.26 |
| 9 | Qwen 2.5 7B Instruct | 0.25 |
| 10 | Phi-4 | 0.1 |
Interactive version: theaggregate.ai/benchmark?slug=caretransition-audit-completeness-ranking · How It Works · Data refreshed daily, snapshot 2026-10-07.