Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Explanation on T-SROIE dense text for robustness (test)
Loading...
84.9
CSS
DocShield
50.372
59.336
68.3
77.264
Apr 3, 2026
CSS
BS (F1)
Updated 13d ago
Evaluation Results
Method
Method
Links
CSS
BS (F1)
DocShield
2026.04
84.9
77
Gemini-2.5-Pro
2026.04
79.8
69.8
qwen3-vl-8B
2026.04
75.9
66
InternVL-3.5-8B
2026.04
74.7
67.5
gpt-4o-o3-0416
2026.04
73.3
65.5
Qwen2.5-VL-7B
2026.04
65.4
66.3
DeepSeekVL-7B
2026.04
60.6
53.7
FakeShield
2026.04
51.7
52.9
Feedback
Search any
task
Search any
task