Benchmark
Nuscene Benchmark
What is Nuscene?
A multimodal benchmark for scene understanding and reasoning over the nuScenes autonomous driving domain. Benchmark Radar tracks 3 reported scores for Nuscene…
- Released
- 2019-03-26
- Modality
- multimodal
- Evaluates
- multimodal, reasoning, spatial, vision
- Openness
- unknown
- Importer
- LLM Stats
- Reported scores
- 3
Source provenance
- Original evidence https://api.zeroeval.com/leaderboard/benchmarks/nuscene?top_n=500
Nuscene results and reported scores
LLM Stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| Qwen3.5-122B-A10B | Qwen | 0.154 | 2026-02-24 | evidence |
| Qwen3.5-27B | Qwen | 0.152 | 2026-02-24 | evidence |
| Qwen3.5-35B-A3B | Qwen | 0.146 | 2026-02-24 | evidence |
Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.