Skip to content

Benchmark

MIEB(lite)

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

53.9%
Mean
61.1%
Median
8.9%
Std dev
41.6%
10th percentile
63.5%
90th percentile
41.6%
Min
41.6%63.5%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard