Spatial Reasoning on 3DSR-B SpatialScore-Hard
52.9AccuracyTVP (Generalize)
Evaluation results
| Method | Links | |
|---|---|---|
| TVP (Generalize)Model Category=Visual Programming, Zero-shot Evaluation=true2025.12 | 52.9 | |
| GPT-4oModel Category=Generic VLMs2025.12 | 52.1 | |
| Qwen2-VL-InstModel Category=Generic VLMs2025.12 | 49.6 | |
| Molmo-7B-DModel Category=Generic VLMs2025.12 | 41.3 | |
| SpaceMantisModel Category=Spatial-Finetuned VLMs2025.12 | 37.2 | |
| VADARModel Category=Visual Programming2025.12 | 24.8 | |
| SpatialBot-3BModel Category=Spatial-Finetuned VLMs2025.12 | 20.7 | |
| LLaVA-OV-7B-ChatModel Category=Generic VLMs2025.12 | 12.4 |