multimodal benchmark
SURDS
SURDS is a benchmark for spatial understanding and reasoning in autonomous-driving scenes.
Updated Aug 7, 2026
Published models1
Registry coverage1
MetricScore
EvidenceB
SURDS leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | AC | 77.2% | 100.0% | 1 | C |
SURDS highlights
The top published results on this benchmark's own scale.
What is SURDS?
Definition and scoring fields from the benchmark registry.
SURDS is a benchmark for spatial understanding and reasoning in autonomous-driving scenes.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- SURDS
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- surds|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about SURDS.
Which model scores highest on SURDS?
Qwen3.7-Plus is currently ranked first with 77.2%.
What does SURDS measure?
SURDS is a benchmark for spatial understanding and reasoning in autonomous-driving scenes.
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.