language benchmark
MEGA UDPOS Leaderboard
MEGA UDPOS is a multilingual part-of-speech tagging benchmark based on Universal Dependencies treebanks across 38 languages.
Updated Sep 5, 2026
Models2
Model coverage2
MetricScore
EvidenceB
MEGA UDPOS Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelMI | Score60.40% | Percentile100.00% | Participants2 | EvidenceC | Evaluated |
| Rank02 | ModelMI | Score46.50% | Percentile0.00% | Participants2 | EvidenceC | Evaluated |
MEGA UDPOS Highlights
The leading models and scores on this benchmark.
MEGA UDPOS Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for MEGA UDPOS
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is MEGA UDPOS?
What MEGA UDPOS measures and how its scores work.
MEGA UDPOS is a dataset and benchmark for universal part-of-speech tagging, using the Universal POS tag set of 17 tags across 38 languages from different language families.
It measures multilingual part-of-speech tagging systems using the Score metric, reported as a ratio.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- MEGA UDPOS
- Modality
- text
- Primary category
- language
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- overall
LLM Stats. Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about MEGA UDPOS.
Which model scores highest on MEGA UDPOS?
Phi-3.5-MoE-instruct is currently ranked first with 60.40%.
What are the top three models on MEGA UDPOS?
The current leaders are Phi-3.5-MoE-instruct (60.40%) and Phi-3.5-mini-instruct (46.50%).
Which MEGA UDPOS model has the lowest official input price?
No matched official input price is currently available.
Which models are fastest among MEGA UDPOS results?
The fastest matched records are Phi-3.5-mini-instruct (23.00 tok/s via Azure).
Does the highest score result prove overall model quality?
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.