spatial reasoning benchmark
SUNRGBD
SUNRGBD evaluates RGB-D scene understanding and 3D grounding capabilities.
Updated Aug 7, 2026
Published models4
Registry coverage4
MetricScore
EvidenceB
SUNRGBD leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | AC | 0.362 points | 100.0% | 4 | C | |
| 2 | AC | 0.354 points | 66.7% | 4 | C | |
| 3 | AC | 0.349 points | 33.3% | 4 | C | |
| 4 | AC | 0.334 points | 0.0% | 4 | C |
Score distribution
Top published rows on the benchmark's original scale.
SUNRGBD highlights
The top published results on this benchmark's own scale.
What is SUNRGBD?
Definition and scoring fields from the benchmark registry.
SUNRGBD evaluates RGB-D scene understanding and 3D grounding capabilities.
Scores are shown in points. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- SUNRGBD
- Modality
- image
- Primary category
- spatial reasoning
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- sunrgbd|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about SUNRGBD.
Which model scores highest on SUNRGBD?
Qwen3.5-122B-A10B is currently ranked first with 0.362 points.
What does SUNRGBD measure?
SUNRGBD evaluates RGB-D scene understanding and 3D grounding capabilities.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
4 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.