RoboSpatial — Spatial-reasoning-for-robotics benchmark, Home-domain subset.
| # | Model | Vendor | Best score | Runs | Last seen |
|---|---|---|---|---|---|
| 1 | Qwen3 VL 4B (Reasoning) | Alibaba | 63.2 | 1 | 2026-06-15 |
| 2 | MiMo Embodied 7B | Xiaomi | 61.8 | 1 | 2026-06-15 |
| 3 | HY-Embodied 0.5 MoT-2B | Tencent | 55.7 | 1 | 2026-06-15 |
| 4 | Qwen3 VL 2B | Alibaba | 45.3 | 1 | 2026-06-15 |
| 5 | Qwen3 VL 235B A22B Reasoning | Alibaba | 0.7 | 1 | 2026-08-23 |
Best tracked score per model (default configuration; source-attributed and verification-tiered). Open a model for its full benchmark surface, provenance and pricing.