Benchmark
BRIGHT(v1.1)
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
- 13.2%
- Mean
- 14.1%
- Median
- 2.1%
- Std dev
- 10.2%
- 10th percentile
- 15.9%
- 90th percentile
- 10.2%
- Min
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | All Mpnet Base V2· MTEB Extra Text Boards data | 15.9% |
| 2 | BGE Large En V1.5· MTEB Extra Text Boards data | 14.1% |
| 3 | BGE M3· MTEB Extra Text Boards data | 12.6% |
| 4 | Multilingual E5 Large· MTEB Extra Text Boards data | 10.2% |