Skip to content

Benchmark

MTEB(Multilingual, 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
20
Scores recorded
20
Sources
1
IQ weight
0.52

Score distribution

48.6%
Mean
50.8%
Median
9.1%
Std dev
37.9%
10th percentile
59.6%
90th percentile
35.2%
Min
35.2%61.8%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.52 for embedding models, measured over 20 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard