Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Forgery Detection on MedForge Real Forgery Cross-Model 90K
Loading...
92.86
Accuracy
MedForge-Reasoner
53.3816
63.6308
73.88
84.1292
Mar 19, 2026
Accuracy
F1 Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
F1 Score
MedForge-Reasoner
Category=Generic MLLMs
2026.03
92.86
92.07
AIGC-Holmes
Category=Specialized D...
2026.03
84.37
86.68
SIDA-13B
Category=Specialized D...
2026.03
84.25
80.58
FakeVLM
Category=Specialized D...
2026.03
76.94
76.29
SIDA-7B
Category=Specialized D...
2026.03
73.42
67.73
Gemini3-Flash
Category=Generic MLLMs
2026.03
72.57
34.78
Gemini3-Pro
Category=Generic MLLMs
2026.03
64.49
62.22
Qwen3VL-Plus
Category=Generic MLLMs
2026.03
55.1
46.18
Qwen3VL-Flash
Category=Generic MLLMs
2026.03
54.9
40.26
Feedback
Search any
task
Search any
task