Skip to content

Benchmark

MIEB(lite) - Compositionality

Vision benchmarks measure how well models understand images. Scores are percentages.

Models measured
4
Scores recorded
4
Sources
1
IQ weight
No weight published

Score distribution

36.9%
Mean
39%
Median
4.3%
Std dev
29.6%
10th percentile
40.5%
90th percentile
29.6%
Min
29.6%40.5%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard