spatial reasoning benchmark
EmbSpatialBench
EmbSpatialBench evaluates embodied spatial understanding and reasoning capabilities.
Updated Aug 7, 2026
Published models8
Registry coverage8
MetricScore
EvidenceB
EmbSpatialBench leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | AC | 0.846 points | 100.0% | 8 | C | |
| 2 | AC | 0.845 points | 85.7% | 8 | C | |
| 3 | AC | 0.843 points | 71.4% | 8 | C | |
| 4 | AC | 0.843 points | 57.1% | 8 | C | |
| 5 | AC | 0.839 points | 42.9% | 8 | C | |
| 6 | BY | 0.834 points | 28.6% | 8 | C | |
| 7 | AC | 0.831 points | 14.3% | 8 | C | |
| 8 | BY | 0.825 points | 0.0% | 8 | C |
Score distribution
Top published rows on the benchmark's original scale.
EmbSpatialBench highlights
The top published results on this benchmark's own scale.
What is EmbSpatialBench?
Definition and scoring fields from the benchmark registry.
EmbSpatialBench evaluates embodied spatial understanding and reasoning capabilities.
Scores are shown in points. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- EmbSpatialBench
- Modality
- image
- Primary category
- spatial reasoning
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- embspatialbench|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about EmbSpatialBench.
Which model scores highest on EmbSpatialBench?
Qwen3.6-27B is currently ranked first with 0.846 points.
What does EmbSpatialBench measure?
EmbSpatialBench evaluates embodied spatial understanding and reasoning capabilities.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
8 unique published model results are currently shown.
Does this benchmark affect the overall score?
This benchmark is preserved as source-native evidence but is not eligible for the current overall score.