List your company

Multiple-choice Question Answering on Cardiology Examination Hard

56.85AccuracyGemini 2.0 Pro
41.894845.777449.6653.5426Mar 30, 2025

Evaluation results

MethodLinks
Gemini 2.0 Prosetting=zero-shot2025.0356.85
Claude 3.5 Sonnetsetting=zero-shot2025.0353.42
Gemini 1.5 Prosetting=zero-shot2025.0352.74
Gemini 2.0 Flashsetting=zero-shot2025.0352.74
GPT-4osetting=zero-shot2025.0350
Gemini 1.5 Flashsetting=zero-shot2025.0342.47