ResearchBenchmarksECG dialogue response quality evaluation on ECG-MTD Lead I (test)Follow3.76AccuracyECG-Agent1.53442.11222.693.2678Jan 28, 2026Evaluation ResultsMethodMethodLinksAccuracyCompletenessECG-AgentBase Model=Llama 3.2 1BBase Model=Llama 3.2 1B2026.013.762.7ECG-AgentBase Model=Qwen3 32BBase Model=Qwen3 32B2026.013.762.8ECG-AgentBase Model=Llama 3.2 3BBase Model=Llama 3.2 3B2026.013.712.84ECG-AgentBase Model=Llama 3.1 8BBase Model=Llama 3.1 8B2026.013.512.75Gemini-2.5-Flash2026.012.693.02PULSE2026.011.851.61GEM2026.011.621.47