spatial reasoning benchmark
RealWorldQA
RealWorldQA is a benchmark designed to evaluate basic real-world spatial understanding capabilities of multimodal models. The initial release consists of over 700 anonymized images taken from vehicles and other real-world scenarios, each accompanied by a question and easily verifiable answer. Released by xAI as part of their Grok-1.5 Vision preview to test models' ability to understand natural scenes and spatial relationships in everyday visual contexts.
Updated Aug 7, 2026
Published models26
Registry coverage26
MetricScore
EvidenceB
RealWorldQA leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
Score distribution
Top published rows on the benchmark's original scale.
RealWorldQA highlights
The top published results on this benchmark's own scale.
What is RealWorldQA?
Definition and scoring fields from the benchmark registry.
RealWorldQA is a benchmark designed to evaluate basic real-world spatial understanding capabilities of multimodal models. The initial release consists of over 700 anonymized images taken from vehicles and other real-world scenarios, each accompanied by a question and easily verifiable answer. Released by xAI as part of their Grok-1.5 Vision preview to test models' ability to understand natural scenes and spatial relationships in everyday visual contexts.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- RealWorldQA
- Modality
- multimodal
- Primary category
- spatial reasoning
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- realworldqa|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about RealWorldQA.
Which model scores highest on RealWorldQA?
Qwen3.8 Max is currently ranked first with 88.0%.
What does RealWorldQA measure?
RealWorldQA is a benchmark designed to evaluate basic real-world spatial understanding capabilities of multimodal models. The initial release consists of over 700 anonymized images taken from vehicles and other real-world scenarios, each accompanied by a question and easily verifiable answer. Released by xAI as part of their Grok-1.5 Vision preview to test models' ability to understand natural scenes and spatial relationships in everyday visual contexts.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
26 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.