Skip to main content
ModelScale

Multimodal & Grounded benchmark

ImageMining leaderboard

Every model the catalog carries a published ImageMining value for, ranked by that value.

CategoryMultimodal & Grounded
MeasureImage-grounded retrieval and extraction
TasksVisual retrieval tasks
DifficultyMultimodal retrieval
Published byGLM-5V-Turbo

A multimodal retrieval and extraction benchmark over image-heavy task settings.

No model in the catalog has a published ImageMining score.

The benchmark is defined by GLM-5V-Turbo, but the catalog carries no value for it yet. An absent value is shown as absent here rather than as a zero.

All leaderboards