Multimodal
3EED
128K objects and 22K referring expressions for 3D grounding across vehicle, drone, quadruped.
8,359items
1subjects
100%observed
Modelsubject type
Response matrix
Every model, scored item by item.
Each row is an AI model and each column an item, ordered so the strongest models and easiest items gather toward one corner. 1 subjects × 8,359 items, 100% of cells evaluated.
Fit to width. Hover for subject & item; click a cell for details.
lowhighUnobserved
Scale: 0 to 1 (per split): 3D Intersection-over-Union of the predicted vs. ground-truth localization across vehicle / drone / quadruped views.
Sample items
What the questions look like — and how subjects answer.
A spread of items across the difficulty range. This benchmark does not publish per-answer traces, so each item shows which subjects succeeded.
Subjects
The models, agents, and reward models evaluated.
1 subjects, ranked by mean response across this benchmark's items.
- 191b90bde0.312