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：近年来，大型音频语言模型（LALMs）的进展极大地增强了多模态对话系统。然而，现有基准仍存在局限——它们主要以英语为中心，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，我们提出了语音聊天机器人基准（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从三个互补的视角评估LALMs：指令遵循（包括超越文本命令的语音层面控制）、知识理解（通用知识、推理与日常对话）以及鲁棒性（在内容、环境和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，并指明了未来的改进方向。VCB Bench提供了一个可复现且细粒度的评估框架，为推进中文语音对话模型的发展提供了标准化方法和实践洞见。