Panoramic Spatial Reasoning on PanoSpace-Bench
56.5Overall AccuracyPanoWorld
Evaluation Results
| Method | Links | |||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| PanoWorld2026.05 | 56.5 | 93.7 | 73.3 | 42.6 | 52.4 | 47.2 | 47.4 | 59.6 | 40.6 | 49.8 | 65.5 | |
| Mimo-v2.52026.05 | 37.2 | 26.8 | 0.7 | 42 | 42.8 | 42 | 42.2 | 51.6 | 23.6 | 37.6 | 45.6 | |
| Qwen3.5-9Bprompting=visual prompt2026.05 | 36.4 | 55.2 | 4.9 | 34 | 36.4 | 28.8 | 33.1 | 46 | 26.2 | 36.1 | 46.5 | |
| Qwen3-VL-32B2026.05 | 34.8 | 32 | 2.5 | 36.4 | 27.2 | 34.8 | 32.8 | 54.8 | 28.8 | 41.8 | 43.6 | |
| GPT-4o2026.05 | 31.8 | 37.2 | 17.7 | 34.8 | 28.4 | 24.8 | 29.3 | 45.6 | 27.2 | 36.4 | 37.6 | |
| Qwen3.5-9B2026.05 | 30.8 | 25.2 | 1.4 | 32.2 | 22.6 | 26.3 | 26.1 | 48.6 | 24.5 | 36.9 | 41.2 | |
| InternVL3.5-14B2026.05 | 30.4 | 23.6 | 2.8 | 35.6 | 30.8 | 38.4 | 34.9 | 56.8 | 20.8 | 38.8 | 28.8 | |
| Qwen2.5-VL-3B2026.05 | 30.1 | 20.4 | 2.7 | 30.8 | 29.6 | 34.8 | 31.7 | 43.6 | 35.2 | 39.4 | 46.4 | |
| Qwen2.5-VL-7B2026.05 | 29.9 | 34 | 3.1 | 30.8 | 23.6 | 30.4 | 28.2 | 48.8 | 29.6 | 39.2 | 32 | |
| Qwen3-VL-8B2026.05 | 29.6 | 47.6 | 2.2 | 28.4 | 21.2 | 27.2 | 25.6 | 45.6 | 23.6 | 34.6 | 34.4 | |
| InternVL3.5-8B2026.05 | 28.3 | 24.8 | 2.9 | 28.8 | 26.4 | 25.2 | 26.8 | 52.4 | 26.8 | 39.6 | 25.6 | |
| Ministral-8B2026.05 | 25.5 | 22.4 | 2.1 | 22 | 20.4 | 20 | 20.8 | 47.6 | 29.6 | 38.6 | 28.4 | |
| Ministral-14B2026.05 | 23.6 | 35.6 | 2.3 | 20 | 14.4 | 12.8 | 15.7 | 49.6 | 31.6 | 40.6 | 21.6 |