List your company
ResearchFormerly WizWand

3D Question Answering on SQA3D

61.3EMCog3DMap-8B
7.37621.375535.37549.3745Nov 30, 2024Feb 18, 2025May 10, 2025Jul 29, 2025Oct 18, 2025Jan 6, 2026Mar 28, 2026
Updated 6mo ago

Evaluation results

MethodLinks
Cog3DMap-8BModel Category=3D Large Multi-modal Models2026.0361.3
3DRSModel Category=3D-based models2025.0960.6
3DRS-7BModel Category=3D Large Multi-modal Models2026.0360.6
3DRSModel category=Generalists, 3D geometric inputs=Yes2026.0360.6
LLaVA-3DModel Category=3D-based models2025.0960.1
LLaVA-3DCategory=Fully Supervised (In-domain training)2025.1060.1
Concerto2026.0360
Utonia2026.0359.9
Sonata2026.0359.7
3D-IDEModel category=Generalists, 3D geometric inputs=No2026.0359.2
Video-3D LLM (Uniform)3D Generalist=true, sampling strategy=uniform sampling2024.1158.6
Video-3D LLMModel Category=3D-based models2025.0958.6
Baseline2026.0358.6
Video-3D LLM3D=true2025.0858.6
Video-3D LLMModel Category=3D Large Multi-modal Models2026.0358.6
Video-3D LLMModel category=Generalists, 3D geometric inputs=Yes2026.0358.6
Video-3D LLM*Model category=Generalists, 3D geometric inputs=No2026.0358.6
Video-3D-LLMCategory=Fully Supervised (In-domain training)2025.1058.5
VG LLM-8BModel category=Generalists, 3D geometric inputs=No2026.0357.9
Video-3D LLM (MC)3D Generalist=true, sampling strategy=maximum coverage2024.1157.7
Vid-LLMModel Category=Video-based models2025.0957.3
VID-LLMModel category=Generalists, 3D geometric inputs=No2026.0357.3
VG LLM-4BModel category=Generalists, 3D geometric inputs=No2026.0357
Spatial-MLLM-4BModel Category=3D Large Multi-modal Models2026.0355.9
LLaVA-3D3D Generalist=true2024.1155.6
LLaVA-3D3D=true2025.0855.6
LLaVA-3DModel Category=3D Large Multi-modal Models2026.0355.6
LLaVA-3DModel category=Generalists, 3D geometric inputs=Yes2026.0355.6
Chat-3D v23D Generalist=true2024.1154.7
Chat-3D v23D=true2025.0854.7
Chat-3D v2Model category=Generalists, 3D geometric inputs=Yes2026.0354.7
ChatScene3D Generalist=true2024.1154.6
ChatSceneModel Category=3D-based models2025.0954.6
ChatSceneModel Category=3D Large Multi-modal Models2026.0354.6
ChatSceneModel category=Generalists, 3D geometric inputs=Yes2026.0354.6
3DRSModel Category=Video-based models, Geometry Source=VGGT-generated 3D geometry2025.0954.5
3D-LLaVAModel category=Generalists, 3D geometric inputs=Yes2026.0354.5
Scene-LLMModel Category=3D-based models2025.0954.2
Scene-LLM3D=true2025.0854.2
Scene-LLMModel Category=3D Large Multi-modal Models2026.0354.2
SceneLLM3D Generalist=true2024.1153.6
SceneLLMModel category=Generalists, 3D geometric inputs=Yes2026.0353.6
ChatSceneModel Category=Video-based models, Evaluation Mode=Video Mode2025.0952.9
UniUGG3D=false2025.0851.3
LEO3D Generalist=true2024.1150
LEOModel Category=3D-based models2025.0950
LEO3D=true2025.0850
LEOModel category=Generalists, 3D geometric inputs=Yes2026.0350
3D-VisTA3D Generalist=false2024.1148.5
LLaVA-Video-7B3D Generalist=false, zero-shot=true2024.1148.5
3D-VisTAModel Category=3D-based models2025.0948.5
LLaVA-Video-7BModel Category=Video-based models2025.0948.5
3D-VisTAModel category=Specialists2026.0348.5
LLaVA-OV-7BModel Category=Video-based models2025.0947.6
ScanQA3D Generalist=false2024.1147.2
ScanQAModel Category=3D-based models2025.0947.2
ScanQAModel category=Specialists2026.0347.2
PQ3D3D Generalist=true2024.1147.1
PQ3DModel category=Generalists, 3D geometric inputs=Yes2026.0347.1
IXC-2.5-7BModel Category=Video-based models2025.0941.5
Scan2CapModel Category=3D-based models2025.0941
VILA-40BModel Category=Video-based models2025.0937.2
Gemini-1.5-FlashCategory=2-Shot (Generalist VLMs)2025.1032.28
MSSRCategory=2-Shot (Generalist VLMs)2025.1027.4
GPT-4oCategory=2-Shot (Generalist VLMs)2025.1024.21
Gemini-1.5-ProCategory=2-Shot (Generalist VLMs)2025.1022.35
GPT-o3Category=2-Shot (Generalist VLMs)2025.1021.93
Qwen2.5-VL-72BCategory=2-Shot (Generalist VLMs)2025.1013.11
Qwen2.5-VL-7BCategory=2-Shot (Generalist VLMs)2025.109.45