Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
external benchmark
EyeBench v3: a vision exam for frontier models. Every model the catalog carries a published EyeBench value for, ranked by that value.
Adonis Singh's visual reasoning benchmark: 100 generated images, each with one question whose answer is a single number. Models count the differences between two nearly identical panels, count closed loops in a tangle of curves, count the connected parts of a graph drawing, pick the tile that completes a 4x4 pattern, and count the turns along a maze path. Scoring is exact match. 0 models in the ModelScale catalog have a published value.
The benchmark is defined by EyeBench v3: a vision exam for frontier models, but the catalog carries no value for it yet. An absent value is shown as absent here rather than as a zero.
What the benchmark measures and how its value is published, from the source’s own record.
EyeBench (EyeBench v3: a vision exam for frontier models) is an external benchmark published by EyeBench v3: a vision exam for frontier models. Adonis Singh's visual reasoning benchmark: 100 generated images, each with one question whose answer is a single number. Models count the differences between two nearly identical panels, count closed loops in a tangle of curves, count the connected parts of a graph drawing, pick the tile that completes a 4x4 pattern, and count the turns along a maze path. Scoring is exact match. Its evaluation set is described by the source as 100 generated images in five task types: spot the difference, closed loops, graph components, 4x4 pattern completion and maze turns (20 each). The source rates its difficulty as counting and tracing fine visual detail exactly: small differences between panels, crossing curves and long maze paths.
Each model's result is published by EyeBench v3: a vision exam for frontier models as one image and one question per request; the answer is a single integer. ModelScale prints that value to 0 decimal places, exactly as published, and never converts or rescales it. This page ranks the 0 models that carry a published value, highest value first; a model the source never scored is left out rather than ranked at zero. The source does not state whether a higher value is the better result, so neither does this page.