MI-CXR - Interval-wise Change Reasoning: leaderboard
Metric: Interval-wise Change Reasoning: find the interval matching a described change, with the interval not given, and interpret it, 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 March 2028. 14 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Pro (Preview) | 45.7 |
| 2 | Claude Sonnet 4.5 | 44.2 |
| 3 | GPT-5.2 | 43.8 |
| 4 | MedGemma-27B-IT | 42.9 |
| 5 | MedGemma-4B | 28.1 |
| 6 | Lingshu-32B | 16.7 |
Interactive version: theaggregate.ai/benchmark?slug=mi-cxr-interval-wise-change-reasoning · How It Works · Data refreshed daily, snapshot 2026-10-07.