The ability to reason from audio, including speech, environmental sounds, and music, is essential for AI agents to interact effectively in real-world scenarios. Existing benchmarks mainly focus on static or single-scene settings and English audio data and do not fully capture scenarios where multiple speakers, unfolding events, and heterogeneous audio sources interact. To address these challenges, we introduce CMDAR, a Chinese benchmark for evaluating models on complex, multi-scene, and dynamically evolving audio reasoning tasks. CMDAR comprises 3,000 carefully curated question-answer pairs linked to diverse audio clips, covering five categories of complex reasoning and spanning three question types. We benchmark 26 state-of-the-art audio language models on CMDAR and observe that they exhibit limitations in complex reasoning tasks. In CMDAR-main, Qwen2.5-Omni achieves 76.67% accuracy, whereas GPT-4o Audio reaches 68.47%. However, GPT-4o Audio substantially outperforms Qwen2.5-Omni on the more challenging multiple-choice with multiple audios and open-ended tasks. And we provide detail analysis corresponding suggestions for the future development of large audio language models.

翻译：从音频（包括语音、环境声音和音乐）进行推理的能力，对于AI智能体在现实场景中有效交互至关重要。现有基准主要关注静态或单场景设置以及英语音频数据，未能充分捕捉多个说话者、持续展开的事件以及异构音频源相互作用的场景。为应对这些挑战，我们提出了CMDAR，一个用于评估模型在复杂、多场景且动态演变的音频推理任务上的中文基准。CMDAR包含3000个精心构建的问答对，关联到多样化的音频片段，涵盖五类复杂推理并跨越三种问题类型。我们在CMDAR上对26个最先进的音频语言模型进行了基准测试，发现它们在复杂推理任务中存在局限性。在CMDAR-main中，Qwen2.5-Omni达到了76.67%的准确率，而GPT-4o Audio则为68.47%。然而，在更具挑战性的多音频多项选择和开放式任务上，GPT-4o Audio显著优于Qwen2.5-Omni。我们提供了详细分析，并对未来大型音频语言模型的发展提出了相应建议。