Recent advances in large audio language models (LALMs) have greatly enhanced multimodal conversational systems. However, existing benchmarks remain limited -- they are mainly English-centric, rely on synthetic speech, and lack comprehensive, discriminative evaluation across multiple dimensions. To address these gaps, we present Voice Chat Bot Bench (VCB Bench) -- a high-quality Chinese benchmark built entirely on real human speech. VCB Bench evaluates LALMs from three complementary perspectives: instruction following (including speech-level control beyond text commands), knowledge understanding (general knowledge, reasoning, and daily dialogue), and robustness (stability under perturbations in content, environment, and speaker traits). Experiments on representative LALMs reveal notable performance gaps and highlight future directions for improvement. VCB Bench provides a reproducible and fine-grained evaluation framework, offering standardized methodology and practical insights for advancing Chinese voice conversational models.

翻译：近期大规模音频语言模型（LALMs）的进展显著提升了多模态对话系统的性能。然而，现有评估基准仍存在局限——主要集中于英语、依赖合成语音，且缺乏跨多个维度的全面判别性评估。为弥补这些不足，我们提出语音对话机器人基准（VCB Bench）——一个完全基于真实人类语音构建的高质量中文基准。VCB Bench从三个互补维度评估LALMs：指令遵循（涵盖超越文本指令的语音层级控制）、知识理解（通用知识、推理能力及日常对话）以及鲁棒性（在内容、环境与说话人特征扰动下的稳定性）。在代表性LALMs上的实验揭示了显著的性能差距，并指明了未来改进方向。VCB Bench提供了可复现的细粒度评估框架，为推进中文语音对话模型的发展提供了标准化方法论与实践洞见。