发表机构
Mohamed bin Zayed University of Artificial Intelligence; Apertix（穆罕默德·本·扎耶德人工智能大学; Apertix）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文评估GPT-6 Astra等六个前沿通用系统在34项视觉能力上的表现，发现语义推理任务接近专用模型，而几何精度与保真感知仍具挑战。
AI 中文摘要
前沿通用系统正迅速从视觉理解扩展到传统上由专用计算机视觉模型处理的能力。随着这些能力的扩展，计算机视觉社区面临的核心问题是：这种扩展能走多远，以及哪些方面仍然困难。我们评估了GPT-6 Astra以及另外五个前沿通用人工智能系统，涵盖计算机视觉九个领域的34项能力和55个基准。我们将它们的性能与专用模型和人类（在存在合适参考的情况下）进行比较。Astra展示了广泛的视觉能力，在视觉和空间推理以及多种结构化预测方面显著优于其他前沿系统。在所有最先进系统中，出现了一致模式：涉及语义解释、推理和以对象为中心的预测的能力日益接近或达到现有参考水平。相比之下，当任务需要度量几何精度、忠实重建、时间一致密集预测或专门的细粒度视觉知识时，差距仍然较大。额外的推理和专家工具能缩小部分差距，但其收益因能力而异。这些结果描绘了计算机视觉不断变化的格局，其中日益复杂的视觉任务可通过通用接口访问，而精确且对保真度敏感的感知仍是重要的前沿领域。
英文摘要
Frontier general-purpose systems are rapidly expanding beyond visual understanding into capabilities traditionally handled by dedicated computer-vision models. As these capabilities expand, a central question for the computer-vision community is how far this reach extends, and what remains hard. We evaluate GPT-6 Astra alongside five frontier general-purpose AI systems across 34 capabilities and 55 benchmarks spanning nine areas of computer vision. We compare their performance with dedicated models and humans where suitable references are available. Astra demonstrates broad visual capability, with substantial gains over other frontier systems in visual and spatial reasoning and several forms of structured prediction. Across the state-of-the-art systems, a consistent pattern emerges. Capabilities involving semantic interpretation, reasoning, and object-centric prediction increasingly approach or reach available reference levels. In contrast, larger gaps remain when tasks require metric geometric accuracy, faithful reconstruction, temporally consistent dense prediction, or specialized fine-grained visual knowledge. Additional reasoning and specialist tools close selected gaps, but their benefits vary across capabilities. These results map a changing landscape of computer vision in which increasingly sophisticated visual tasks are accessible through a general-purpose interface, while precise and fidelity-sensitive perception remains an important frontier.
