Multiple-choice Question Answering on Cardiology Examination All
77.54AccuracyGemini 2.0 Pro
Evaluation results
| Method | Links | |
|---|---|---|
| Gemini 2.0 Prosetting=zero-shot2025.03 | 77.54 | |
| GPT-4osetting=zero-shot2025.03 | 75.16 | |
| Claude 3.5 Sonnetsetting=zero-shot2025.03 | 74.73 | |
| Gemini 2.0 Flashsetting=zero-shot2025.03 | 70.19 | |
| Gemini 1.5 Prosetting=zero-shot2025.03 | 69.11 | |
| Gemini 1.5 Flashsetting=zero-shot2025.03 | 59.18 |