List your company

Physical Commonsense Reasoning on PIQA (ACC)

81.3ACCQwen2.5-VL
65.325669.472873.6277.7672Jul 2, 2026Jul 3, 2026Jul 4, 2026Jul 5, 2026Jul 6, 2026Jul 7, 2026

Evaluation results

MethodLinks
Qwen2.5-VLModel Category=General VLMs2026.0781.3
ELSA3DModel Category=Unified 3D Models2026.0780.6
LLaMA3.2-VisionModel Category=General VLMs2026.0780.1
LLaMA-MeshModel Category=Mesh LLM2026.0779.8
CoRe3DModel Category=Unified 3D Models2026.0779.4
ShapeLLM-OmniModel Category=Unified 3D Models2026.0778.9
ADAMWBackbone=Llama-500M, Evaluation Protocol=Zero-shot, Communication Strategy=DENSE all-reduce2026.0767.3
ADAMWSynchronization=DENSE all-reduce, Backbone=Llama-500M, Evaluation Protocol=Zero-shot2026.0767.3
SCAPEBackbone=Llama-500M, Evaluation Protocol=Zero-shot, Sparsity (d)=0.12026.0766.76
SCAPESparsity (d)=0.1, Backbone=Llama-500M, Evaluation Protocol=Zero-shot2026.0766.76
SCAPEBackbone=Llama-500M, Evaluation Protocol=Zero-shot, Sparsity (d)=0.012026.0766.32
SCAPESparsity (d)=0.01, Backbone=Llama-500M, Evaluation Protocol=Zero-shot2026.0766.32
ADAMSBackbone=Llama-500M, Evaluation Protocol=Zero-shot, Communication Strategy=DENSE all-reduce2026.0765.94
ADAMSSynchronization=DENSE all-reduce, Backbone=Llama-500M, Evaluation Protocol=Zero-shot2026.0765.94