Skip to content

Benchmark

MIEB(lite) - ImageClustering

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

69.9%
Mean
78.7%
Median
11.3%
Std dev
57.1%
10th percentile
83.2%
90th percentile
57.1%
Min
57.1%83.2%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard