spatial reasoning benchmark
ARKitScenes
ARKitScenes evaluates 3D scene understanding and spatial reasoning in AR/VR contexts.
Updated Aug 7, 2026
Published models1
Registry coverage1
MetricScore
EvidenceB
ARKitScenes leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | AC | 0.537 points | 100.0% | 1 | C |
ARKitScenes highlights
The top published results on this benchmark's own scale.
What is ARKitScenes?
Definition and scoring fields from the benchmark registry.
ARKitScenes evaluates 3D scene understanding and spatial reasoning in AR/VR contexts.
Scores are shown in points. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- ARKitScenes
- Modality
- multimodal
- Primary category
- spatial reasoning
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- arkitscenes|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about ARKitScenes.
Which model scores highest on ARKitScenes?
Qwen3 VL 235B A22B Thinking is currently ranked first with 0.537 points.
What does ARKitScenes measure?
ARKitScenes evaluates 3D scene understanding and spatial reasoning in AR/VR contexts.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
1 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.