Skip to content

Benchmark

MIEB(lite) - VisualSTS(multi)

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

57.6%
Mean
65.1%
Median
15.5%
Std dev
34.6%
10th percentile
76.8%
90th percentile
34.6%
Min
34.6%76.8%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard