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
GroundingME: Multi-Dimensional Visual Grounding. Every model the catalog carries a published GroundingME value for, ranked by that value.
A visual grounding benchmark of 1,005 examples that tests whether multimodal models localize objects across four dimensions: discriminative look-alikes, spatial relations, occluded or tiny targets, and ungroundable rejection queries. 8 models in the ModelChoice catalog have a published value.
Each point is a model with a published GroundingME value and complete token prices, on the 75% input / 25% output blend. Frontier models are spaced evenly along the cost axis.
8 models with a published GroundingME value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.
| Rank | Model | Provider | Accuracy@0.5 (%) |
|---|---|---|---|
| 1 | Alibaba | 45.1 | |
| 2 | Alibaba | 26.9 | |
| 3 | 20.7 |
What the benchmark measures and how its value is published, from the source’s own record.
GroundingME (GroundingME: Multi-Dimensional Visual Grounding) is an external benchmark published by GroundingME: Exposing the Visual Grounding Gap in MLLMs through Multi-Dimensional Evaluation. A visual grounding benchmark of 1,005 examples that tests whether multimodal models localize objects across four dimensions: discriminative look-alikes, spatial relations, occluded or tiny targets, and ungroundable rejection queries. Its evaluation set is described by the source as 1,005 multi-dimensional visual grounding examples. The source rates its difficulty as fine-grained object localization and ungroundable rejection.
Each model's result is published by GroundingME: Exposing the Visual Grounding Gap in MLLMs through Multi-Dimensional Evaluation as accuracy@0.5 (%). ModelChoice prints that value to 1 decimal place, exactly as published, and never converts or rescales it. This page ranks the 8 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.
| 4 | 18.7 |
| 5 | Meta | 13.0 |
| 6 | Meta | 8.9 |
| 7 | 0.4 |
| 7 | Microsoft | 0.4 |
Evidence key: Observed
Rows are ordered by the value GroundingME: Exposing the Visual Grounding Gap in MLLMs through Multi-Dimensional Evaluation published, highest first. The source does not state whether a higher value is the better result, so this page does not either: for a benchmark that measures a rate of failure, read the table from the bottom.