Skip to content

Benchmark

VN-MTEB (vie, v1) - Mean (TaskType)

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

52.9%
Mean
62.5%
Median
10.2%
Std dev
41.3%
10th percentile
63.5%
90th percentile
41.3%
Min
41.3%63.5%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1BGE M3Mean (TaskType)· MTEB Extra Text Boards data63.5%
2Multilingual E5 LargeMean (TaskType)· MTEB Extra Text Boards data62.5%
3All MiniLM L12 V2Mean (TaskType)· MTEB Extra Text Boards data44.3%
4All MiniLM L6 V2Mean (TaskType)· MTEB Extra Text Boards data41.3%