MindCube (tinybench)
MindCube (tinybench) as evaluated on the LFM3-VL-2B card (vision benchmark, with-thinking setting): Embodied reasoning category, with-thinking column. MindCube tinybench subset; no inventory record.
Category
Spatial Intelligence
Score type
percent
Scale
100%
higher is better
Models tested
1
What is MindCube (tinybench)?
MindCube (tinybench) is a benchmark for understanding where things are in space. The official description says: "MindCube (tinybench) as evaluated on the LFM3-VL-2B card (vision benchmark, with-thinking setting): Embodied reasoning category, with-thinking column". Below we describe in simple words what benchmarks of this type generally examine.
What does it test?
MindCube (tinybench) measures understanding where things are in space. In detail, it checks:
- locating and pointing to regions in images
- reasoning about positions, counts and relations between objects
- 3D-aware questions such as depth, perspective and room layout
- grounded perception tasks that must stay anchored to pixel locations
How to read the score
The score is accuracy: the percentage of tasks answered or solved correctly. 100% means every task was solved perfectly; higher is better.
Official methodology note: MindCube (tinybench) as evaluated on the LFM3-VL-2B card (vision benchmark, with-thinking setting): Embodied reasoning category, with-thinking column. MindCube tinybench subset; no inventory record.
Frequently asked questions
What is the MindCube (tinybench) benchmark?
MindCube (tinybench) is a benchmark for understanding where things are in space. The official description says: 'MindCube (tinybench) as evaluated on the LFM3-VL-2B card (vision benchmark, with-thinking setting): Embodied reasoning category, with-thinking column'. Below we describe in simple words what benchmarks of this type generally examine.
What does MindCube (tinybench) test?
MindCube (tinybench) mainly measures understanding where things are in space. Concretely, it checks: locating and pointing to regions in images; reasoning about positions, counts and relations between objects; 3D-aware questions such as depth, perspective and room layout.
How is the MindCube (tinybench) score calculated?
The score is accuracy: the percentage of tasks answered or solved correctly. 100% means every task was solved perfectly; higher is better. The declared maximum score of this benchmark is 100.0.
Where do I get MindCube (tinybench) data and scores?
The official benchmark page/reference is linked on this page. Every score on Open LLM Radar is also available as open data: download the scores JSON (http://open-llm-radar-api:8000/api/v1/benchmarks/mindcube-tinybench/scores) or pull it directly from the Open LLM Radar API with any HTTP client.
Benchmark data & downloads
Where to get, inspect and reuse the data behind this benchmark.
Model scores 1 model tested
| # | Model | Score | Date | Source | Verified |
|---|---|---|---|---|---|
| 1 |
LFM3-VL-2B
LiquidAI
|
56.5%
|
— | Report | Verified |