Benchmark
MIEB(lite) - VisualSTS(multi)
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
- 65.1%
- Median
- 15.5%
- Std dev
- 34.6%
- 10th percentile
- 76.8%
- 90th percentile
- 34.6%
- Min
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | embeddinggemma-2VisualSTS(multi)· MTEB Multimodal Boards data docs | 76.8% |
| 2 | Jina Embeddings v5 Omni SmallVisualSTS(multi)· MTEB Multimodal Boards data docs | 65.1% |
| 3 | Jina Embeddings v5 Omni NanoVisualSTS(multi)· MTEB Multimodal Boards data docs | 54% |
| 4 | Jina Clip v1VisualSTS(multi)· MTEB Multimodal Boards data docs | 34.6% |