Benchmark
MIEB(Img) - VisualSTS(eng)
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
- 72.3%
- Mean
- 74.8%
- Median
- 7.7%
- Std dev
- 61.8%
- 10th percentile
- 80.3%
- 90th percentile
- 61.8%
- Min
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | Jina Embeddings v5 Omni SmallVisualSTS(eng)· MTEB Multimodal Boards data docs | 80.3% |
| 2 | Jina Embeddings v5 Omni NanoVisualSTS(eng)· MTEB Multimodal Boards data docs | 74.8% |
| 3 | Jina Clip v1VisualSTS(eng)· MTEB Multimodal Boards data docs | 61.8% |