Benchmark
MTEB(Africa, v1) - PairClassification
Embedding benchmarks measure how well models find related items, for example when matching a search to relevant results. Scores are percentages.
- Models measured
- 4
- Scores recorded
- 4
- Sources
- 1
- IQ weight
- No weight published
Score distribution
- 71.3%
- Mean
- 71.9%
- Median
- 1.3%
- Std dev
- 70.1%
- 10th percentile
- 73.3%
- 90th percentile
- 70.1%
- Min
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | BGE M3PairClassification· MTEB Multimodal Boards data docs | 73.3% |
| 2 | Qwen3 Embedding 8BPairClassification· MTEB Multimodal Boards data docs | 71.9% |
| 3 | Multilingual E5 LargePairClassification· MTEB Multimodal Boards data docs | 70.1% |
| 4 | Multilingual E5 Large InstructPairClassification· MTEB Multimodal Boards data docs | 70.1% |