DriveSpatial - Reasoning: leaderboard
DriveSpatial (2026) tests whether vision-language models can build and reason over a coherent driving scene from synchronized multi-view camera frames, with human-verified questions generated from scene graphs of nuScenes, Waymo, TruckScenes, AV2 and ONCE. This board covers the spatiotemporal reasoning tasks on the full 15,670-question set, scored as accuracy in percent; higher is better.
Metric: Accuracy (%) on the spatiotemporal reasoning tasks (interactions and future dynamics) on the full benchmark (15,670 human-verified questions over 20 tasks from nuScenes, Waymo, TruckScenes, AV2 and ONCE); open-source generalist and driving or spatial specialist VLMs; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 12 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 3 VL 8B | 47.66 | #917 |
| 2 | InternVL3.5-8B | 41.31 | #1604 |
| 3 | Gemma 3 12B (IT) | 40.8 | #1887 |
| 4 | LLaVA-OneVision-7B | 40.34 | #2981 |
| 5 | RoboTron-Drive | 39.56 | |
| 6 | DeepSeek-VL2-Small | 39.26 | #2464 |
| 7 | LLaVA-Video-7B | 36.89 | #2276 |
| 8 | LongVA-7B | 35.25 | #3456 |
| 9 | DriveSpatial Ego3D (checkpoint unspecified) | 34.53 | |
| 10 | DriveSpatial SenseNova-SI (checkpoint unspecified) | 32.73 | |
| 11 | SpaceThinker | 31.65 | #1448 |
| 12 | InternVL3-8B | 30.65 | #1782 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=drivespatial-reasoning · How It Works · Data refreshed daily, snapshot 2026-11-21.