multimodal benchmark
Nuscene
A multimodal benchmark for scene understanding and reasoning over the nuScenes autonomous driving domain.
Updated Aug 11, 2026
Models3
Model coverage3
MetricScore
EvidenceB
Nuscene Ranking
Higher score ranks better on this benchmark.
| 01 | AC | 15.4% | 100.0% | 3 | C | |
| 02 | AC | 15.2% | 50.0% | 3 | C | |
| 03 | AC | 14.6% | 0.0% | 3 | C |
Nuscene Score Distribution
A closer view of the leading scores on this benchmark.
Nuscene Highlights
The leading models and scores on this benchmark.
What is Nuscene?
What Nuscene measures and how its scores work.
A multimodal benchmark for scene understanding and reasoning over the nuScenes autonomous driving domain.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- Nuscene
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- nuscene|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about Nuscene.
Which model scores highest on Nuscene?
Qwen3.5-122B-A10B is currently ranked first with 15.4%.
What does Nuscene measure?
A multimodal benchmark for scene understanding and reasoning over the nuScenes autonomous driving domain.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
3 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.