Benchmark
MIEB(lite) - DocumentUnderstanding
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
- 57.6%
- Mean
- 74.2%
- Median
- 24.9%
- Std dev
- 14.8%
- 10th percentile
- 74.3%
- 90th percentile
- 14.8%
- Min
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | Jina Embeddings v5 Omni SmallDocumentUnderstanding· MTEB Multimodal Boards data docs | 74.3% |
| 2 | Jina Embeddings v5 Omni NanoDocumentUnderstanding· MTEB Multimodal Boards data docs | 74.2% |
| 3 | embeddinggemma-2DocumentUnderstanding· MTEB Multimodal Boards data docs | 67.1% |
| 4 | Jina Clip v1DocumentUnderstanding· MTEB Multimodal Boards data docs | 14.8% |