Benchmark
MVEB(text, video, v1) - VideoCentricQA
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
- 25.9%
- Mean
- 26.3%
- Median
- 0.953%
- Std dev
- 25%
- 10th percentile
- 27.3%
- 90th percentile
- 25%
- Min
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | Qwen3-VL Embedding 8BVideoCentricQA· MTEB Multimodal Boards data docs | 27.3% |
| 2 | Jina Embeddings v5 Omni SmallVideoCentricQA· MTEB Multimodal Boards data docs | 26.3% |
| 3 | Qwen2.5-Omni 7BVideoCentricQA· MTEB Multimodal Boards data docs | 25.2% |
| 4 | Jina Embeddings v5 Omni NanoVideoCentricQA· MTEB Multimodal Boards data docs | 25% |