Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Object Existence on Lens
Loading...
86.59
Accuracy
Gemini2.5-Pro
71.2916
75.2633
79.235
83.2067
May 21, 2025
Accuracy
Updated 20d ago
Evaluation Results
Method
Method
Links
Accuracy
Gemini2.5-Pro
Model size=-
2025.05
86.59
Qwen2.5-VL
Model size=72B
2025.05
85.67
QVQ-Max
Model size=72B
2025.05
85.37
GPT-4o
Model size=-
2025.05
85.09
InternVL3
Model size=78B
2025.05
84.87
Qwen2.5-VL
Model size=7B
2025.05
83.75
Qwen2.5-VL
Model size=32B
2025.05
83.6
InternVL3
Model size=38B
2025.05
81.6
Deepseek-VL2
Model size=MoE 4.5B/27B
2025.05
77.68
InternVL3
Model size=9B
2025.05
77.49
Qwen2.5-VL
Model size=3B
2025.05
74.01
Gemma3
Model size=12B
2025.05
73.21
Kimi-VL-thinking
Model size=MoE 2.8B/16B
2025.05
72.77
Deepseek-VL2-tiny
Model size=MoE 1B/3B
2025.05
72.11
InternVL3
Model size=2B
2025.05
71.96
Gemma3
Model size=4B
2025.05
71.88
Feedback
Search any
task
Search any
task