Skip to content

Benchmark

MIEB(Multilingual) - DocumentUnderstanding

Multilingual benchmarks compare model performance across languages. Scores are percentages.

Models measured
3
Scores recorded
3
Sources
1
IQ weight
No weight published

Score distribution

58.7%
Mean
79.3%
Median
29%
Std dev
17.6%
10th percentile
79.3%
90th percentile
17.6%
Min
17.6%79.3%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1Jina Embeddings v5 Omni NanoDocumentUnderstanding· MTEB Multimodal Boards data docs79.3%
2Jina Embeddings v5 Omni SmallDocumentUnderstanding· MTEB Multimodal Boards data docs79.3%
3Jina Clip v1DocumentUnderstanding· MTEB Multimodal Boards data docs17.6%