Skip to content

Benchmark

MVEB(v1) - VideoCentricQA

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

35%
Mean
45.2%
Median
15.4%
Std dev
13.2%
10th percentile
46.6%
90th percentile
13.2%
Min
13.2%46.6%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard