Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Section Hierarchy Parsing on DocHieNet (test)
Loading...
62.91
F1 Score
DSHP-LLM
24.0868
34.1659
44.245
54.3241
Apr 14, 2026
F1 Score
TEDS Score
Updated 4d ago
Evaluation Results
Method
Method
Links
F1 Score
TEDS Score
DSHP-LLM
base_model=Mistral-8B
2026.04
62.91
82.3
DSHP-LLM
base_model=Qwen-2.5-7B
2026.04
55.65
81.04
Qwen-2.5-7B
2026.04
52.3
73.56
GPT-4
2026.04
51.39
69.61
DSHP-LLM
base_model=Llama-3.2-3B
2026.04
48.94
75.49
DSHP-LLM
base_model=Qwen-2.5-3B
2026.04
48.08
69.57
Qwen-2.5-3B
2026.04
41.22
69.95
Mistral-8B
2026.04
39.07
65.59
Llama-3.2-3B
2026.04
25.58
54.64
Feedback
Search any
task
Search any
task