Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Visual Reasoning on OpenWorld
Loading...
93.6
Direct Accuracy
Qwen2.5-VL 72B
78.832
82.666
86.5
90.334
Jul 10, 2025
Direct Accuracy
CoT Accuracy
LSC Accuracy
Final Linear Separability Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Direct Accuracy
CoT Accuracy
LSC Accuracy
Final Linear Separability Accuracy
Qwen2.5-VL 72B
Model size=72B
2025.07
93.6
93.2
86.8
74.8
Human
2025.07
91
-
-
-
Pixtral 12B
Model size=12B
2025.07
79.4
84.2
76
88
Feedback
Search any
task
Search any
task