Spatial Reasoning on SpatialSense SpatialScore-Hard
62AccuracySpatialBot-3B
Evaluation Results
| Method | Links | |
|---|---|---|
| SpatialBot-3BModel Category=Spatial-Finetuned VLMs2025.12 | 62 | |
| TVP (Generalize)Model Category=Visual Programming, Zero-shot Evaluation=true2025.12 | 59.2 | |
| Molmo-7B-DModel Category=Generic VLMs2025.12 | 54.9 | |
| TVP (Generalize)Model Category=Visual Programming, Zero-shot Evaluation=true2025.12 | 52.3 | |
| GPT-4oModel Category=Generic VLMs2025.12 | 46.5 | |
| GPT-4oModel Category=Generic VLMs2025.12 | 42.6 | |
| VADARModel Category=Visual Programming2025.12 | 40.8 | |
| Molmo-7B-DModel Category=Generic VLMs2025.12 | 37.9 | |
| Qwen2-VL-InstModel Category=Generic VLMs2025.12 | 34.4 | |
| VADARModel Category=Visual Programming2025.12 | 32.8 | |
| Qwen2-VL-InstModel Category=Generic VLMs2025.12 | 32.4 | |
| SpatialBot-3BModel Category=Spatial-Finetuned VLMs2025.12 | 28.5 | |
| SpaceMantisModel Category=Spatial-Finetuned VLMs2025.12 | 25 | |
| SpaceMantisModel Category=Spatial-Finetuned VLMs2025.12 | 19.7 | |
| LLaVA-OV-7B-ChatModel Category=Generic VLMs2025.12 | 10.9 | |
| LLaVA-OV-7B-ChatModel Category=Generic VLMs2025.12 | 9.9 |