Benchmark
BEIR-NL
Embedding benchmarks measure how well models find related items, for example when matching a search to relevant results. Scores are percentages.
- Models measured
- 5
- Scores recorded
- 5
- Sources
- 1
- IQ weight
- 1.63
Score distribution
- 47%
- Mean
- 45.6%
- Median
- 3.8%
- Std dev
- 44.4%
- 10th percentile
- 54.5%
- 90th percentile
- 44.4%
- Min
This benchmark has a weight of 1.63 for embedding models, measured over 5 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | INF Retriever v1· MTEB Extra Text Boards data | 54.5% |
| 2 | Multilingual E5 Large· MTEB Extra Text Boards data | 45.9% |
| 3 | Jina Embeddings v3· MTEB Extra Text Boards data | 45.6% |
| 4 | BGE M3· MTEB Extra Text Boards data | 44.7% |
| 5 | Multilingual E5 Large Instruct· MTEB Extra Text Boards data | 44.4% |