MI-CXR - Trajectory Summary (Single Abnormality): leaderboard

Metric: Global Trajectory Summarization for one abnormality across all visits, five-option multiple-choice accuracy (%, times 100; chance 20) on MI-CXR, longitudinal reasoning over five-visit chest X-ray timelines from MIMIC-CXR (5,311 questions), zero-shot single-step prompting with all five images, temperature 0; higher is better. Source: arxiv.org. Saturation forecast: Around May 2027. 14 models tracked.

Top models

#ModelScore
1GPT-5.255.8
2Gemini 3 Pro (Preview)55.6
3Claude Sonnet 4.538.9
4Lingshu-32B38.8
5MedGemma-4B25.9
6MedGemma-27B-IT25.5

Interactive version: theaggregate.ai/benchmark?slug=mi-cxr-trajectory-summary-single-abnormality · How It Works · Data refreshed daily, snapshot 2026-10-07.