Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Physical Commonsense Reasoning on PIQA (ACC)
Loading...
81.3
ACC
Qwen2.5-VL
65.3256
69.4728
73.62
77.7672
Jul 2, 2026
Jul 3, 2026
Jul 4, 2026
Jul 5, 2026
Jul 6, 2026
Jul 7, 2026
ACC
Updated 17d ago
Evaluation Results
Method
Method
Links
ACC
Qwen2.5-VL
Model Category=General...
2026.07
81.3
ELSA3D
Model Category=Unified...
2026.07
80.6
LLaMA3.2-Vision
Model Category=General...
2026.07
80.1
LLaMA-Mesh
Model Category=Mesh LLM
2026.07
79.8
CoRe3D
Model Category=Unified...
2026.07
79.4
ShapeLLM-Omni
Model Category=Unified...
2026.07
78.9
ADAMW
Backbone=Llama-500M, E...
2026.07
67.3
ADAMW
Synchronization=DENSE...
2026.07
67.3
SCAPE
Backbone=Llama-500M, E...
2026.07
66.76
SCAPE
Sparsity (d)=0.1, Back...
2026.07
66.76
SCAPE
Backbone=Llama-500M, E...
2026.07
66.32
SCAPE
Sparsity (d)=0.01, Bac...
2026.07
66.32
ADAMS
Backbone=Llama-500M, E...
2026.07
65.94
ADAMS
Synchronization=DENSE...
2026.07
65.94
Feedback
Search any
task
Search any
task