Skip to content

Benchmark

MVEB(video, v1) - Mean (TaskType)

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

53.8%
Mean
59.7%
Median
11.1%
Std dev
36.6%
10th percentile
66.3%
90th percentile
36.6%
Min
36.6%66.3%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard