Text-to-Audio-Video (T2AV) generation is rapidly becoming a core interface for media creation, yet its evaluation remains fragmented. Existing benchmarks largely assess audio and video in isolation or rely on coarse embedding similarity, failing to capture the fine-grained joint correctness required by realistic prompts. We introduce AVGen-Bench, a task-driven benchmark for T2AV generation featuring high-quality prompts across 11 real-world categories. To support comprehensive assessment, we propose a multi-granular evaluation framework that combines lightweight specialist models with Multimodal Large Language Models (MLLMs), enabling evaluation from perceptual quality to fine-grained semantic controllability. Our evaluation reveals a pronounced gap between strong audio-visual aesthetics and weak semantic reliability, including persistent failures in text rendering, speech coherence, physical reasoning, and a universal breakdown in musical pitch control. Code and benchmark resources are available at http://aka.ms/avgenbench.

翻译：文本到音视频（T2AV）生成正迅速成为媒体创作的核心接口，但其评估方法仍存在碎片化问题。现有基准主要孤立评估音频与视频，或依赖粗粒度的嵌入相似度，未能捕捉真实提示所需的细粒度联合正确性。我们提出AVGen-Bench——一个针对T2AV生成的任务驱动基准，涵盖11类真实场景的高质量提示。为支持全面评估，我们提出一种结合轻量级专用模型与多模态大语言模型（MLLMs）的多粒度评估框架，实现从感知质量到细粒度语义可控性的评估。我们的评估揭示了音视频美学表现与语义可靠性之间的显著差距，包括文本渲染、语音连贯性、物理推理层面的持续失败，以及音乐音高控制方面的普遍性失效。相关代码与基准资源已发布于http://aka.ms/avgenbench。