Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Universal Dependency Parsing on SpokeBench v1 (test)
Loading...
89.5
ID
BiLingua Parser
9.628
30.364
51.1
71.836
Feb 6, 2026
ID
UPOS
HEAD
DEPREL
Final Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
ID
UPOS
HEAD
DEPREL
Final Score
BiLingua Parser
Type=LLM-based pipeline
2026.02
89.5
91
66.7
69.9
81.4
DECAP
Backbone=GPT-4.1
2026.02
47.2
55
34.8
39.5
52.4
Bilingual Traditional Parser
Backbone=Stanza
2026.02
12.7
13.7
13.7
13.7
29.9
Feedback
Search any
task
Search any
task