Benchmark
MVEB(v1) - VideoClassification
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
- 39.3%
- Mean
- 45.3%
- Median
- 13.8%
- Std dev
- 20.2%
- 10th percentile
- 52.4%
- 90th percentile
- 20.2%
- Min
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | Jina Embeddings v5 Omni SmallVideoClassification· MTEB Multimodal Boards data docs | 52.4% |
| 2 | Jina Embeddings v5 Omni NanoVideoClassification· MTEB Multimodal Boards data docs | 45.3% |
| 3 | Qwen2.5-Omni 7BVideoClassification· MTEB Multimodal Boards data docs | 20.2% |