Semantic Reasoning on LingoQA
68.6ScoreMimo-Embodied
Evaluation Results
| Method | Links | |
|---|---|---|
| Mimo-EmbodiedCategory=Embodied Models2026.04 | 68.6 | |
| XEmbodiedversion=Best2026.04 | 65.7 | |
| Gemini-1.5Category=Proprietary Models2026.04 | 61.3 | |
| PR1-Detection-3BCategory=Spatial Models2026.04 | 56.08 | |
| Qwen3-VL-32BCategory=Open-Source Models2026.04 | 54.3 | |
| GPT-4oCategory=Proprietary Models2026.04 | 53.58 | |
| Qwen2.5-VL-7BCategory=Open-Source Models2026.04 | 53.2 | |
| Cosmos-R1Category=Embodied Models2026.04 | 52.7 | |
| PR1-Grounding-2BCategory=Spatial Models2026.04 | 50.3 | |
| PR1-Counting-2BCategory=Spatial Models2026.04 | 48.52 | |
| PR1-OCR-2BCategory=Spatial Models2026.04 | 48.5 | |
| Qwen3-VL-A3B-30BCategory=Open-Source Models2026.04 | 47 | |
| Qwen2.5-VL-32BCategory=Open-Source Models2026.04 | 43.7 | |
| UniVG-R1-7BCategory=Spatial Models2026.04 | 39.2 | |
| DriveMMCategory=Embodied Models2026.04 | 37.7 |