Benchmark
MVEB(video, v1) - VideoPairClassification
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
- 66.4%
- Mean
- 73.2%
- Median
- 8.2%
- Std dev
- 54.3%
- 10th percentile
- 74.6%
- 90th percentile
- 54.3%
- Min
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | Qwen3-VL Embedding 8BVideoPairClassification· MTEB Multimodal Boards data docs | 74.6% |
| 2 | Jina Embeddings v5 Omni SmallVideoPairClassification· MTEB Multimodal Boards data docs | 73.2% |
| 3 | Jina Embeddings v5 Omni NanoVideoPairClassification· MTEB Multimodal Boards data docs | 63.3% |
| 4 | Qwen2.5-Omni 7BVideoPairClassification· MTEB Multimodal Boards data docs | 54.3% |