Large-scale generative models have demonstrated remarkable capabilities across image generation and editing tasks. However, their performance in low-level vision tasks, which require pixel-wise control, remains insufficiently studied. To address this gap, we introduce \textbf{LL-Bench}, a comprehensive \textbf{Benchmark} for evaluating the capabilities of large-scale generative models on \textbf{L}ow-\textbf{L}evel vision tasks. The benchmark comprises 2,469 real-world degraded images covering 16 low-level degradation tasks, and 28,919 restored images produced by 10 state-of-the-art large-scale generative models and 21 conventional restoration models, which are annotated with 152,020 expert-level pairwise human preferences and 28,334 quality scores. Built upon LL-Bench, we present a systematic diagnosis that reveals the performance boundaries and unique failure modes of large-scale generative models across diverse low-level vision tasks, compared with conventional representative restoration approaches. Moreover, we investigate the effectiveness of current quality evaluation metrics on LL-Bench, which exhibit significant discrepancy with human ratings. To better align restored-image quality assessment with human preferences, we further propose \textbf{LL-Score}, an MLLM-based evaluator that captures both restoration quality and hallucination existence. Extensive experiments demonstrate that LL-score not only outperforms existing image quality assessment metrics, but also serves as a promising reward model for training generative models on low-level vision tasks.

翻译：大规模生成模型在图像生成和编辑任务中展现出卓越能力。然而，其在需要像素级控制的低级视觉任务中的性能仍未得到充分研究。为弥补这一空白，我们提出**LL-Bench**，一个用于评估大规模生成模型在**低级视觉**任务上能力的综合**基准**。该基准包含2,469张覆盖16种低级退化任务的真实世界退化图像，以及由10个最先进的大规模生成模型和21个传统恢复模型生成的28,919张恢复图像，并配有152,020对专家级成对人类偏好和28,334个质量评分。基于LL-Bench，我们进行系统诊断，揭示了大规模生成模型在各类低级视觉任务中的性能边界和独特失效模式，并与传统代表性恢复方法进行对比。此外，我们研究了当前质量评估指标在LL-Bench上的有效性，发现其与人类评分存在显著差异。为更好地使恢复图像质量评估与人类偏好对齐，我们进一步提出**LL-Score**，一种基于MLLM的评估器，可同时捕捉恢复质量和伪影存在性。大量实验表明，LL-Score不仅优于现有图像质量评估指标，还可作为有前景的奖励模型，用于训练生成模型处理低级视觉任务。