MCQ Diagnostic Accuracy on Stanford CMR (test)
88AccuracyMARCUS
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| MARCUSN=502026.03 | 88 | 78 | — | |
| GPT-5N=502026.03 | 58 | 44 | — | |
| Gemini 2.5 ProN=502026.03 | 44 | 30 | — | |
| MARCUS vs Gemini (McNemar p)N=502026.03 | — | — | 0.001 | |
| MARCUS vs GPT-5 (McNemar p)N=502026.03 | — | — | 0.001 |