3D Question Answering on SQA3D
61.3EMCog3DMap-8B
Evaluation Results
| Method | Links | |
|---|---|---|
| Cog3DMap-8BModel Category=3D Large Multi-modal Models2026.03 | 61.3 | |
| 3DRSModel Category=3D-based models2025.09 | 60.6 | |
| 3DRS-7BModel Category=3D Large Multi-modal Models2026.03 | 60.6 | |
| 3DRSModel category=Generalists, 3D geometric inputs=Yes2026.03 | 60.6 | |
| LLaVA-3DModel Category=3D-based models2025.09 | 60.1 | |
| LLaVA-3DCategory=Fully Supervised (In-domain training)2025.10 | 60.1 | |
| Concerto2026.03 | 60 | |
| Utonia2026.03 | 59.9 | |
| Sonata2026.03 | 59.7 | |
| 3D-IDEModel category=Generalists, 3D geometric inputs=No2026.03 | 59.2 | |
| Video-3D LLM (Uniform)3D Generalist=true, sampling strategy=uniform sampling2024.11 | 58.6 | |
| Video-3D LLMModel Category=3D-based models2025.09 | 58.6 | |
| Baseline2026.03 | 58.6 | |
| Video-3D LLM3D=true2025.08 | 58.6 | |
| Video-3D LLMModel Category=3D Large Multi-modal Models2026.03 | 58.6 | |
| Video-3D LLMModel category=Generalists, 3D geometric inputs=Yes2026.03 | 58.6 | |
| Video-3D LLM*Model category=Generalists, 3D geometric inputs=No2026.03 | 58.6 | |
| Video-3D-LLMCategory=Fully Supervised (In-domain training)2025.10 | 58.5 | |
| VG LLM-8BModel category=Generalists, 3D geometric inputs=No2026.03 | 57.9 | |
| Video-3D LLM (MC)3D Generalist=true, sampling strategy=maximum coverage2024.11 | 57.7 | |
| Vid-LLMModel Category=Video-based models2025.09 | 57.3 | |
| VID-LLMModel category=Generalists, 3D geometric inputs=No2026.03 | 57.3 | |
| VG LLM-4BModel category=Generalists, 3D geometric inputs=No2026.03 | 57 | |
| Spatial-MLLM-4BModel Category=3D Large Multi-modal Models2026.03 | 55.9 | |
| LLaVA-3D3D Generalist=true2024.11 | 55.6 | |
| LLaVA-3D3D=true2025.08 | 55.6 | |
| LLaVA-3DModel Category=3D Large Multi-modal Models2026.03 | 55.6 | |
| LLaVA-3DModel category=Generalists, 3D geometric inputs=Yes2026.03 | 55.6 | |
| Chat-3D v23D Generalist=true2024.11 | 54.7 | |
| Chat-3D v23D=true2025.08 | 54.7 | |
| Chat-3D v2Model category=Generalists, 3D geometric inputs=Yes2026.03 | 54.7 | |
| ChatScene3D Generalist=true2024.11 | 54.6 | |
| ChatSceneModel Category=3D-based models2025.09 | 54.6 | |
| ChatSceneModel Category=3D Large Multi-modal Models2026.03 | 54.6 | |
| ChatSceneModel category=Generalists, 3D geometric inputs=Yes2026.03 | 54.6 | |
| 3DRSModel Category=Video-based models, Geometry Source=VGGT-generated 3D geometry2025.09 | 54.5 | |
| 3D-LLaVAModel category=Generalists, 3D geometric inputs=Yes2026.03 | 54.5 | |
| Scene-LLMModel Category=3D-based models2025.09 | 54.2 | |
| Scene-LLM3D=true2025.08 | 54.2 | |
| Scene-LLMModel Category=3D Large Multi-modal Models2026.03 | 54.2 | |
| SceneLLM3D Generalist=true2024.11 | 53.6 | |
| SceneLLMModel category=Generalists, 3D geometric inputs=Yes2026.03 | 53.6 | |
| ChatSceneModel Category=Video-based models, Evaluation Mode=Video Mode2025.09 | 52.9 | |
| UniUGG3D=false2025.08 | 51.3 | |
| LEO3D Generalist=true2024.11 | 50 | |
| LEOModel Category=3D-based models2025.09 | 50 | |
| LEO3D=true2025.08 | 50 | |
| LEOModel category=Generalists, 3D geometric inputs=Yes2026.03 | 50 | |
| 3D-VisTA3D Generalist=false2024.11 | 48.5 | |
| LLaVA-Video-7B3D Generalist=false, zero-shot=true2024.11 | 48.5 | |
| 3D-VisTAModel Category=3D-based models2025.09 | 48.5 | |
| LLaVA-Video-7BModel Category=Video-based models2025.09 | 48.5 | |
| 3D-VisTAModel category=Specialists2026.03 | 48.5 | |
| LLaVA-OV-7BModel Category=Video-based models2025.09 | 47.6 | |
| ScanQA3D Generalist=false2024.11 | 47.2 | |
| ScanQAModel Category=3D-based models2025.09 | 47.2 | |
| ScanQAModel category=Specialists2026.03 | 47.2 | |
| PQ3D3D Generalist=true2024.11 | 47.1 | |
| PQ3DModel category=Generalists, 3D geometric inputs=Yes2026.03 | 47.1 | |
| IXC-2.5-7BModel Category=Video-based models2025.09 | 41.5 | |
| Scan2CapModel Category=3D-based models2025.09 | 41 | |
| VILA-40BModel Category=Video-based models2025.09 | 37.2 | |
| Gemini-1.5-FlashCategory=2-Shot (Generalist VLMs)2025.10 | 32.28 | |
| MSSRCategory=2-Shot (Generalist VLMs)2025.10 | 27.4 | |
| GPT-4oCategory=2-Shot (Generalist VLMs)2025.10 | 24.21 | |
| Gemini-1.5-ProCategory=2-Shot (Generalist VLMs)2025.10 | 22.35 | |
| GPT-o3Category=2-Shot (Generalist VLMs)2025.10 | 21.93 | |
| Qwen2.5-VL-72BCategory=2-Shot (Generalist VLMs)2025.10 | 13.11 | |
| Qwen2.5-VL-7BCategory=2-Shot (Generalist VLMs)2025.10 | 9.45 |