Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Vision-Language Compositional Reasoning on Winoground standard (test)
Loading...
75.5
Text Score
GPT-4o
58.6
62.9875
67.375
71.7625
Jan 23, 2025
Text Score
Image Score
Group Score
Updated 4d ago
Evaluation Results
Method
Method
Links
Text Score
Image Score
Group Score
GPT-4o
Paradigm=Componential...
2025.01
75.5
58.5
52
Gemini 2.0
Paradigm=Componential...
2025.01
71
48.75
42
Llama3.3-70B
Paradigm=Componential...
2025.01
68.25
49.25
41.75
Qwen2.5-32B
Paradigm=Componential...
2025.01
67
46.25
40
Phi-4-14B
Paradigm=Componential...
2025.01
65.25
46
37.75
MMICL + CoCoT
2025.01
64.25
52.5
50.75
Qwen2.5-14B
Paradigm=Componential...
2025.01
59.25
34.5
27.25
Feedback
Search any
task
Search any
task