Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Visual Understanding on VisPuzzle
Loading...
79
Accuracy
ThinkMorph
28.56
41.655
54.75
67.845
Oct 30, 2025
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
ThinkMorph
Size=7B, think mode=true
2025.10
79
GPT-5
Size=-
2025.10
78
Gemini 2.5 Flash
Size=-
2025.10
47
GPT-4o
Size=-
2025.10
43.75
Qwen2.5-VL
Size=72B
2025.10
40
InternVL3.5
Size=38B
2025.10
36.5
Bagel
Size=7B, think mode=false
2025.10
35
InternVL3.5
Size=8B
2025.10
34.75
Qwen2.5-VL
Size=7B
2025.10
34.75
Janus-pro
Size=7B
2025.10
33.5
Chameleon
Size=7B
2025.10
30.5
Feedback
Search any
task
Search any
task