Benchmark
MVEB(v1) - VideoZeroshotClassification
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
- 37.2%
- Mean
- 43.4%
- Median
- 15%
- Std dev
- 16.5%
- 10th percentile
- 51.7%
- 90th percentile
- 16.5%
- Min
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | Jina Embeddings v5 Omni SmallVideoZeroshotClassification· MTEB Multimodal Boards data docs | 51.7% |
| 2 | Jina Embeddings v5 Omni NanoVideoZeroshotClassification· MTEB Multimodal Boards data docs | 43.4% |
| 3 | Qwen2.5-Omni 7BVideoZeroshotClassification· MTEB Multimodal Boards data docs | 16.5% |