SOURCE-LINKED INTELLIGENCE

What Looks Like a Capability Limit in Vision-Language Models Is a Readout Limit

arXiv · AI, language, vision and robotics · article · Sep 23, 2026 · UTC

Benchmarks for vision-language models offer their answer choices in some convention: a letter, a color name, a pixel coordinate. That convention is treated as neutral. We find it is not, and that the limits a benchmark reports can belong to the readout rather than to the model. On 200 COCO photographs, Qwen3-VL-4B picks the correct one of nine locations for a named object 68.5% of the time when the locations are given in English and 20.0% when the same locations are given as pixel coordinates. Chance is 11.1%. The cost arises when the answer options are coordinates; giving the model a coordina

Read original source ↗ Open in workspace

recordType

paper

region

Global