Skip to content

Benchmark

MVEB(v1) - VideoPairClassification

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

64.6%
Mean
60.5%
Median
11.3%
Std dev
53.2%
10th percentile
79.9%
90th percentile
53.2%
Min
53.2%79.9%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1Jina Embeddings v5 Omni SmallVideoPairClassification· MTEB Multimodal Boards data docs79.9%
2Jina Embeddings v5 Omni NanoVideoPairClassification· MTEB Multimodal Boards data docs60.5%
3Qwen2.5-Omni 7BVideoPairClassification· MTEB Multimodal Boards data docs53.2%