Skip to content

Benchmark

MVEB(v1) - Any2AnyRetrieval

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

Models measured
3
Scores recorded
3
Sources
1
IQ weight
No weight published

Score distribution

22.2%
Mean
27.7%
Median
16%
Std dev
0.5%
10th percentile
38.5%
90th percentile
0.5%
Min
0.5%38.5%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard