ClinTraceBench - Treatment Fact Recall: leaderboard

Metric: Accuracy (%; task T7, treatment fact recall: four-option clinical-management questions grounded in documented treatment events, 400 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: Estimated already saturated. 4 models tracked.

Top models

#ModelScore
1Claude Haiku 4.596.5
2Claude Sonnet 4.695.3
3DeepSeek V3.194.2
4GPT-4o Mini87.2

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