Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Comprehensive Document Safety Analysis on RealText proposed (test)
Loading...
68.9
M-F1 Score
DocShield
13.26
27.705
42.15
56.595
Apr 3, 2026
M-F1 Score
Updated 13d ago
Evaluation Results
Method
Method
Links
M-F1 Score
DocShield
2026.04
68.9
gpt-4o-o3-0416
2026.04
55.8
Gemini-2.5-Pro
2026.04
53.9
qwen3-vl-8B
2026.04
49.7
InternVL-3.5-8B
2026.04
48.8
FakeShield
2026.04
40.6
Qwen2.5-VL-7B
2026.04
36.3
DeepSeekVL-7B
2026.04
15.4
Feedback
Search any
task
Search any
task