ResearchBenchmarksECG dialogue response quality evaluation on ECG-MTD Lead II (test)Follow3.88AccuracyECG-Agent1.55042.15522.763.3648Jan 28, 2026Evaluation ResultsMethodMethodLinksAccuracyCompletenessECG-AgentBase Model=Llama 3.2 3BBase Model=Llama 3.2 3B2026.013.883ECG-AgentBase Model=Qwen3 32BBase Model=Qwen3 32B2026.013.812.94ECG-AgentBase Model=Llama 3.2 1BBase Model=Llama 3.2 1B2026.013.762.85ECG-AgentBase Model=Llama 3.1 8BBase Model=Llama 3.1 8B2026.013.632.84Gemini-2.5-Flash2026.012.522.95PULSE2026.011.881.74GEM2026.011.641.69