List your company

Multiple-choice Question Answering on Cardiology Examination Mod

81.71AccuracyClaude 3.5 Sonnet
58.247664.338870.4376.5212Mar 30, 2025

Evaluation results

MethodLinks
Claude 3.5 Sonnetsetting=zero-shot2025.0381.71
Gemini 2.0 Prosetting=zero-shot2025.0381.1
GPT-4osetting=zero-shot2025.0380.49
Gemini 2.0 Flashsetting=zero-shot2025.0371.34
Gemini 1.5 Prosetting=zero-shot2025.0367.68
Gemini 1.5 Flashsetting=zero-shot2025.0359.15