GPT-6 Astra 跨计算机视觉评测揭示通用模型的能力边界

View PDF HTML (experimental)

Abstract: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.

Subjects:	Computer Vision and Pattern Recognition (cs.CV)
Cite as:	arXiv:2609.35718 [cs.CV]
	(or arXiv:2609.35718v1 [cs.CV] for this version)
	https://doi.org/10.48550/arXiv.2609.35718 arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Hanoona Bangalath Rasheed Ms [view email]
[v1] Mon, 28 Sep 2026 17:46:57 UTC (17,249 KB)