Benchmark
MVEB(text, video, v1) - VideoClustering
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
- 10%
- Mean
- 7.4%
- Median
- 7.2%
- Std dev
- 3.6%
- 10th percentile
- 22.2%
- 90th percentile
- 3.6%
- Min
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | Qwen3-VL Embedding 8BVideoClustering· MTEB Multimodal Boards data docs | 22.2% |
| 2 | Qwen2.5-Omni 7BVideoClustering· MTEB Multimodal Boards data docs | 7.4% |
| 3 | Jina Embeddings v5 Omni SmallVideoClustering· MTEB Multimodal Boards data docs | 7.1% |
| 4 | Jina Embeddings v5 Omni NanoVideoClustering· MTEB Multimodal Boards data docs | 3.6% |