MedLoCoMo - Cross-Admission: leaderboard

Metric: Score (%) on the 8,946 cross-admission questions (evidence from two or more admissions): item-weighted combination of judged accuracy on answerable questions (two per admission) and abstention accuracy on unanswerable ones (one per admission); full patient history in context (100 synthetic multi-admission doctor-patient conversations from MIMIC-IV, 74.5k tokens on average), short free-text answers; answerable items judged correct or not by a Gemini 3 Flash Preview judge, adversarial unanswerable items scored by abstention; higher is better. Source: arxiv.org. Saturation forecast: Around December 2026. 13 models tracked.

Top models

#ModelScore
1GPT-5.157
2Qwen 3.5 27B51.6
3Qwen 3.5 9B42.7
4Qwen 3.5 4B41.7
5Gemma 3 27B40.1
6Gemma 3 12B38.8
7MedGemma-4B15
8Lingshu-32B14.7
9Gemma 3 4B10.9

Interactive version: theaggregate.ai/benchmark?slug=medlocomo-cross-admission · How It Works · Data refreshed daily, snapshot 2026-09-29.