ClinTraceBench - Retrospective Propagation: leaderboard

Metric: Accuracy (%; task T4, retrospective propagation: list the earlier findings supporting a later diagnosis, scored 1 only for an exact event-ID set, 53 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 2035. 4 models tracked.

Top models

#ModelScore
1GPT-4o Mini28.3
2Claude Sonnet 4.624.5
3DeepSeek V3.122.6
4Claude Haiku 4.518.9

Interactive version: theaggregate.ai/benchmark?slug=clintracebench-retrospective-propagation · How It Works · Data refreshed daily, snapshot 2026-09-26.