Avian influenza remains a persistent threat to global health security, with serious consequences for food systems, trade, and pandemic preparedness. To address gaps in public health communication and stakeholder-specific decision-making, this study evaluated the capacity of large language models (LLMs) to provide accurate, context-sensitive, and ethically sound guidance in the context of avian influenza. Employing a multi-model, stakeholder-stratified evaluation framework, we tested four advanced generative AI models, namely, ChatGPT-4o (OpenAI), Grok (xAI), Gemini 1.5 Pro (Google), and DeepSeek R1 (DeepSeek), across two complementary tasks: (i) structured querying of 34 domain-specific items covering virological, epidemiological, veterinary, and global public health domains; and (ii) response generation to 16 synthetic vignettes simulating outbreak scenarios involving diverse societal roles. Results showed that Gemini 1.5 Pro demonstrated the highest factual accuracy (91.2% fully correct responses), followed by Grok (85.3%), ChatGPT-4o (82.4%), and DeepSeek R1 (82.4%). Vignette analysis further revealed model-specific communicative strengths and ethical orientations, ranging from procedural pragmatism to stakeholder-mapping and human-centered design. While Gemini excelled in blending empathetic and pedagogical reasoning, Grok offered implementation-oriented guidance, ChatGPT-4o emphasized legal-normative clarity, and DeepSeek R1 favored structural and institutional analysis. Collectively, our findings highlight the promise and limitations of current LLMs as tools for biosurveillance, risk communication, and cross-sectoral pandemic preparedness. They also emphasize the necessity of rigorous, role-aware benchmarking to ensure equitable and contextually appropriate integration of generative AI in public health infrastructures.