Dynamic Spatial Reasoning on DSR-Bench 1.0 (test)
87Abs DistanceGSM (Ours)
Evaluation Results
| Method | Links | ||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| GSM (Ours)Base Model=Qwen2.5-VL-7B, Learnable Queries (N)=32, Batch size=322025.12 | 87 | 73.8 | 84.1 | 73.8 | 72 | 35.5 | 75.8 | 76.1 | 77.7 | 60.6 | 37.1 | 35.1 | 46.4 | 58.9 | |
| VG-LLMModel Category=Spatial Reasoning Models2025.12 | 55.2 | 32.3 | 58.5 | 57.1 | 51.6 | 32.2 | 56 | 36.3 | 32 | 30.3 | 32.1 | 29.1 | 27.9 | 38.4 | |
| Qwen2.5-VL-32BModel Category=General-Purpose Models2025.12 | 31.7 | 21.5 | 23.1 | 44 | 36.5 | 25.4 | 27.5 | 23.8 | 37 | 27.2 | 29.2 | 21.4 | 36.2 | 29.9 | |
| VLM-3RModel Category=Spatial Reasoning Models2025.12 | 28.2 | 27.6 | 31.7 | 42.8 | 38.7 | 33 | 34.4 | 23.8 | 30.8 | 22.2 | 26.4 | 29.1 | 35 | 31.4 | |
| Qwen3-VL-30B-A3B-InstructModel Category=General-Purpose Models2025.12 | 25.8 | 27.6 | 46.3 | 30.9 | 31.1 | 34.7 | 20.6 | 29.5 | 37 | 28.2 | 24.2 | 31.5 | 35.4 | 31.1 | |
| InternVL3.5-38BModel Category=General-Purpose Models2025.12 | 25.8 | 27.8 | 29.2 | 34.2 | 24.7 | 28.5 | 26.7 | 16.3 | 23.4 | 29.2 | 32.1 | 15.4 | 31.3 | 26.7 | |
| VideoReferModel Category=Video Understanding Models2025.12 | 23.5 | 18.4 | 25.6 | 33.5 | 45.4 | 27.1 | 25 | 16.1 | 18.5 | 20.2 | 26.4 | 22.6 | 34.7 | 26.9 | |
| Qwen3-VL-8B-InstructModel Category=General-Purpose Models2025.12 | 23.5 | 24.6 | 42.6 | 29.7 | 27.9 | 33.8 | 18.1 | 28.4 | 34.5 | 24.2 | 22.1 | 27.9 | 33.5 | 28.7 | |
| InternVL3.5-8BModel Category=General-Purpose Models2025.12 | 23.5 | 27.6 | 28 | 34.5 | 24.7 | 27.9 | 22.4 | 17 | 19.7 | 28.2 | 30 | 14.2 | 30.1 | 25.4 | |
| LLaVA-Video-7BModel Category=Video Understanding Models2025.12 | 22.3 | 16.9 | 25.6 | 33.3 | 45.1 | 24.5 | 24.1 | 15.9 | 17.2 | 19.1 | 24.2 | 21.4 | 33.9 | 25.9 | |
| GPT-5Model Category=Propriety Models2025.12 | 21.1 | 41.5 | 48.7 | 34.5 | 33.3 | 34.7 | 17.2 | 44.3 | 41.9 | 21.2 | 25 | 30.9 | 26.7 | 30.8 | |
| Gemini-2.5-ProModel Category=Propriety Models2025.12 | 20 | 44.6 | 53.6 | 27.3 | 38.7 | 30.5 | 23.2 | 32.9 | 43.2 | 17.1 | 28.5 | 27.9 | 34.3 | 31.7 | |
| LongVILA-R1Model Category=Video Understanding Models2025.12 | 20 | 21.5 | 23.1 | 21.4 | 37.6 | 22.8 | 24.1 | 26.1 | 28.3 | 22.2 | 17.8 | 20.8 | 33.9 | 25.3 | |
| GPT-4oModel Category=Propriety Models2025.12 | 18.8 | 29.2 | 26.8 | 29.7 | 21.5 | 26.2 | 24.1 | 23.8 | 17.2 | 32.3 | 22.8 | 24.4 | 34.7 | 26.4 | |
| Gemini-2.5-FlashModel Category=Propriety Models2025.12 | 18.8 | 27.6 | 19.5 | 25 | 23.6 | 22 | 11.2 | 28.4 | 30.8 | 23.2 | 17.1 | 22.6 | 38.8 | 24.9 | |
| Qwen2.5-VL-7BModel Category=General-Purpose Models2025.12 | 18.8 | 15.3 | 14.6 | 42.8 | 29 | 19.4 | 31.8 | 19.3 | 11.1 | 22.2 | 19.2 | 20.2 | 30.1 | 23.5 |