Table 3. Category-specific accuracy comparison.
| Category | Questions (n) | Claude Accuracy | ChatGPT-4 Accuracy | Difference |
| Cardiac Electrophysiology | 35 | 34.3% (12/35) | 25.7% (9/35) | +8.60% |
| Pacemaker Programming | 25 | 36.0% (9/25) | 24.0% (6/25) | +12.00% |
| Perioperative Complications | 20 | 30.0% (6/20) | 20.0% (4/20) | +10.00% |
| Antiarrhythmic Pharmacology | 12 | 25.0% (3/12) | 16.7% (2/12) | +8.30% |
| Mechanical Support Devices | 8 | 25.0% (2/8) | 25.0% (2/8) | +0.00% |