Skip to content

Benchmark

MIEB(Multilingual) - Compositionality

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

41.6%
Mean
45.1%
Median
5.7%
Std dev
33.6%
10th percentile
46.1%
90th percentile
33.6%
Min
33.6%46.1%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard