Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Skill Knowledge on Lens
Loading...
59.31
Accuracy
Gemini2.5-Pro
35.5252
41.7001
47.875
54.0499
May 21, 2025
Accuracy
Updated 20d ago
Evaluation Results
Method
Method
Links
Accuracy
Gemini2.5-Pro
Model size=-
2025.05
59.31
QVQ-Max
Model size=72B
2025.05
58.86
GPT-4o
Model size=-
2025.05
55.2
InternVL3
Model size=78B
2025.05
55.17
Qwen2.5-VL
Model size=72B
2025.05
54.79
InternVL3
Model size=38B
2025.05
51.85
Qwen2.5-VL
Model size=32B
2025.05
51.54
InternVL3
Model size=9B
2025.05
51.32
Deepseek-VL2
Model size=MoE 4.5B/27B
2025.05
49.5
Qwen2.5-VL
Model size=7B
2025.05
48.87
InternVL3
Model size=2B
2025.05
48.59
Gemma3
Model size=12B
2025.05
48.56
Qwen2.5-VL
Model size=3B
2025.05
46.5
Gemma3
Model size=4B
2025.05
45.18
Deepseek-VL2-tiny
Model size=MoE 1B/3B
2025.05
45.12
Kimi-VL-thinking
Model size=MoE 2.8B/16B
2025.05
36.44
Feedback
Search any
task
Search any
task