Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Harmful Meme Detection on MAMI (test)
Loading...
81
Accuracy
GPT-4o
51.776
59.363
66.95
74.537
Jul 9, 2025
Accuracy
Macro-F1
Updated 4d ago
Evaluation Results
Method
Method
Links
Accuracy
Macro-F1
GPT-4o
Setting=Zero-shot, Pro...
2025.07
81
81
Gemini 1.5 Flash
Setting=Zero-shot, Pro...
2025.07
76.4
74.29
LLaVA-1.6-34B
Setting=Zero-shot, Pro...
2025.07
71.3
71.28
MIND
Backbone=LLaVA-1.5-13B...
2025.07
68.9
68.84
LLaVA-1.5-13B
Setting=Zero-shot, Pro...
2025.07
60.1
55.52
InstructBLIP-13B
Setting=Zero-shot, Pro...
2025.07
60
57.97
MiniGPT-v2-7B
Setting=Zero-shot, Pro...
2025.07
57.4
52.22
OpenFlamingo-9B
Setting=Zero-shot, Pro...
2025.07
54.7
49.88
InstructBLIP-7B
Setting=Zero-shot, Pro...
2025.07
53.1
46.93
LLaVA-1.5-7B
Setting=Zero-shot, Pro...
2025.07
52.9
41.53
Feedback
Search any
task
Search any
task