MEGA UDPOS

Multilingual
text
+
+
+
+
About

MEGA-UDPOS is a multilingual part-of-speech tagging component of the MEGA benchmark that evaluates AI models' syntactic understanding across multiple languages. This benchmark tests models' ability to correctly identify grammatical categories in diverse languages, measuring cross-lingual syntactic analysis capabilities and understanding of universal dependencies across different linguistic structures.

+
+
+
+
Evaluation Stats
Total Models2
Organizations1
Verified Results0
Self-Reported2
+
+
+
+
Benchmark Details
Max Score1
Language
en
+
+
+
+
Performance Overview
Score distribution and top performers

Score Distribution

2 models
Top Score
60.4%
Average Score
53.4%
High Performers (80%+)
0

Top Organizations

#1Microsoft
2 models
53.4%
+
+
+
+
Leaderboard
2 models ranked by performance on MEGA UDPOS
LicenseLinks
Aug 23, 2024
MIT
60.4%
Aug 23, 2024
MIT
46.5%
+
+
+
+
Resources