RoboSpatialHome
Progress Over Time
Interactive timeline showing model performance evolution on RoboSpatialHome
RoboSpatialHome Leaderboard
| Context | Cost | License | ||||
|---|---|---|---|---|---|---|
| 1 |  Alibaba Cloud / Qwen Team | 236B | — | — |
What is RoboSpatialHome?
RoboSpatialHome evaluates spatial understanding for robotic home navigation and manipulation.
RoboSpatialHome is a image benchmark evaluating models on robotics, spatial reasoning, embodied, and vision tasks. LLM Stats tracks 1 models on this benchmark, scored on a 0–100 scale. The current average is 0.7, with the leader at 0.7.
Compare leaders on the best AI for robotics, best AI for spatial reasoning, best AI for embodied and best AI for vision leaderboards.
Current leaders
Qwen3 VL 235B A22B Thinking from Alibaba Cloud / Qwen Team currently leads the RoboSpatialHome leaderboard with a score of 0.739 across 1 evaluated AI models.
FAQ
Common questions about the RoboSpatialHome benchmark and leaderboard.