MC-CXR - Misleading Prior Report: leaderboard

Metric: Accuracy under misleading context (%; the image plus a prior report rewritten toward a plausible wrong finding; 240 radiologist-reviewed MIMIC-CXR cases, one current chest X-ray and a fixed target finding each; zero-shot constrained single-letter answer from 12 CheXpert labels (chance about 8.3%), invalid answers scored wrong; greedy or temperature-0 decoding). Source: arxiv.org. Saturation forecast: Around 2031. 10 models tracked.

Top models

#ModelScore
1Gemini 3.5 Flash (Minimal)21.7
2Qwen 3.5 9B17.5
3MedGemma 1.5 4B13.3
4Claude Opus 4.711.2
5InternVL3-8B11.2
6Phi-4 Multimodal Instruct7.1
7Llama 3.2 11B Instruct4.6
8Gemma 3 12B (IT)3.8

Interactive version: theaggregate.ai/benchmark?slug=mc-cxr-misleading-prior-report · How It Works · Data refreshed daily, snapshot 2026-09-29.