ClinTraceBench - Cross-Patient Comparison: leaderboard
Metric: Accuracy (%; task T6, cross-patient comparison: number of diagnoses, maximum lab value and lab delta across patients, 700 questions; full-context strategy: the whole multi-visit patient-clinician dialogue derived from MIMIC-IV records is given verbatim, models called through OpenRouter). Source: arxiv.org. Saturation forecast: Around 2029. 4 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | DeepSeek V3.1 | 54.3 |
| 2 | Claude Sonnet 4.6 | 52.3 |
| 3 | Claude Haiku 4.5 | 51 |
| 4 | GPT-4o Mini | 49.7 |
Interactive version: theaggregate.ai/benchmark?slug=clintracebench-cross-patient-comparison · How It Works · Data refreshed daily, snapshot 2026-09-26.