Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Grounding on T-SROIE dense text for robustness (test)
Loading...
9.1
mIOU
DocShield
-0.364
2.093
4.55
7.007
Apr 3, 2026
mIOU
mF1
Updated 13d ago
Evaluation Results
Method
Method
Links
mIOU
mF1
DocShield
2026.04
9.1
11
gpt-4o-o3-0416
2026.04
1.3
1.3
FakeShield
2026.04
0.5
1.9
Gemini-2.5-Pro
2026.04
0.2
1.2
InternVL-3.5-8B
2026.04
0.1
1
qwen3-vl-8B
2026.04
0
1
DeepSeekVL-7B
2026.04
0
0.5
Qwen2.5-VL-7B
2026.04
0
0.7
Feedback
Search any
task
Search any
task