Skip to content

Benchmark

MVEB(text, video, v1) - VideoZeroshotClassification

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

42.3%
Mean
53.3%
Median
16.7%
Std dev
15.5%
10th percentile
59.2%
90th percentile
15.5%
Min
15.5%59.2%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1Qwen3-VL Embedding 8BVideoZeroshotClassification· MTEB Multimodal Boards data docs59.2%
2Jina Embeddings v5 Omni SmallVideoZeroshotClassification· MTEB Multimodal Boards data docs53.3%
3Jina Embeddings v5 Omni NanoVideoZeroshotClassification· MTEB Multimodal Boards data docs41.3%
4Qwen2.5-Omni 7BVideoZeroshotClassification· MTEB Multimodal Boards data docs15.5%