Benchmark
VLADBench
VLADBench is a vision-language autonomous-driving benchmark evaluating understanding of dynamic traffic scenes and participants.
- Modality
- multimodal
- Categories
- multimodal, reasoning, vision
- Openness
- unknown
- Source
- llm_stats
- Reported scores
- 1
Reported scores
llm_stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| Qwen3.7-Plus | Qwen | 0.772 | 2026-05-31 | 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.