Binary Disease Diagnosis on ChestX-ray14 OOD
72.7Macro AccHulu-Med-Flash-Preview-27B
Evaluation results
| Method | Links | ||
|---|---|---|---|
| Hulu-Med-Flash-Preview-27B2026.05 | 72.7 | 27.7 | |
| Qwen2.5-VL-7B-Instruct2026.05 | 72.2 | 15.5 | |
| CSRL2026.05 | 66.4 | 30.1 | |
| MedGemma-27B-IT2026.05 | 62 | 28 | |
| Best Tool per Pathology2026.05 | 61.7 | 27.8 | |
| Majority Voting (tie → neg)2026.05 | 60.8 | 27 | |
| CheXzero2026.05 | 60.3 | 27.4 | |
| Logistic Regression2026.05 | 58.6 | 25.6 | |
| InternVL3.5-38B-Instruct2026.05 | 58.5 | 22.8 | |
| MedKLIP2026.05 | 58 | 26.1 | |
| DenseNet-MIMIC2026.05 | 55.9 | 20.8 | |
| Gemini-3.1-Pro-Preview2026.05 | 53.5 | 25.4 | |
| Lingshu-7B2026.05 | 53.2 | 25.9 | |
| DenseNet-CheX2026.05 | 51.7 | 22.5 | |
| HuatuoGPT-Vision-7B2026.05 | 51.2 | 21.2 | |
| CheXagent-8B2026.05 | 50.7 | 26.3 | |
| GPT-4o2026.05 | 49.9 | 20.4 | |
| Majority Voting (tie → pos)2026.05 | 49.4 | 24.9 | |
| DenseNet-NIH2026.05 | 44 | 21.8 | |
| Qwen2.5-VL-72B-Instruct2026.05 | 37.5 | 17.4 | |
| Claude-Sonnet-4.62026.05 | 33 | 19.2 |