MCQ medical diagnostic reasoning on Lung CT PET Chest (test)
52Overall Accuracygemini-3.1-flash-preview
Evaluation Results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| gemini-3.1-flash-previewTrack=Viewer-Only, Evaluation Protocol=MCQ Protocol2026.03 | 52 | 19.6 | 42 | 21 | 83 | 72 | 44 | |
| GPT-5.4Track=Viewer-Only, Evaluation Protocol=MCQ Protocol2026.03 | 32 | 11.5 | 46 | 32 | 38 | 36 | 7 | |
| gemini-3.1-pro-previewTrack=Viewer-Only, Evaluation Protocol=MCQ Protocol2026.03 | 31 | 11.7 | 43 | 31 | 35 | 34 | 11 | |
| GPT-5-miniTrack=Viewer-Only, Evaluation Protocol=MCQ Protocol2026.03 | 20 | 1.85 | 14 | 17 | 9 | 6 | 4 |