Spatial & 3D Understanding on SURDS
83.83SURDS Spatial & 3D ScoreXEmbodied (Best)
Evaluation Results
| Method | Links | |
|---|---|---|
| XEmbodied (Best)Model Category=Our Model2026.04 | 83.83 | |
| Qwen3-VL-32BModel Category=Open-Source Models2026.04 | 41.53 | |
| Qwen2.5-VL-32BModel Category=Open-Source Models2026.04 | 38.82 | |
| Qwen3-VL-A3B-30BModel Category=Open-Source Models2026.04 | 38.69 | |
| PR1-Detection-3BModel Category=Spatial Models2026.04 | 33.84 | |
| Gemini-1.5Model Category=Proprietary Models2026.04 | 32.77 | |
| Mimo-EmbodiedModel Category=Embodied Models2026.04 | 24.04 | |
| PR1-Grounding-2BModel Category=Spatial Models2026.04 | 13.96 | |
| PR1-OCR-2BModel Category=Spatial Models2026.04 | 13.81 | |
| PR1-Counting-2BModel Category=Spatial Models2026.04 | 13.69 | |
| GPT-4oModel Category=Proprietary Models2026.04 | 13.31 | |
| Qwen2.5-VL-7BModel Category=Open-Source Models2026.04 | 12.61 | |
| Cosmos-R1Model Category=Embodied Models2026.04 | 10.05 | |
| DriveMMModel Category=Embodied Models2026.04 | 8.73 | |
| UniVG-R1-7BModel Category=Spatial Models2026.04 | 1.96 |