Skip to content

Benchmark

MTEB(cmn, v1) - Clustering

Embedding benchmarks measure how well models find related items, for example when matching a search to relevant results. Scores are percentages.

Models measured
14
Scores recorded
14
Sources
1
IQ weight
1.31

Score distribution

57%
Mean
57%
Median
11.6%
Std dev
45.7%
10th percentile
77.9%
90th percentile
37.7%
Min
37.7%80.1%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.31 for embedding models, measured over 13 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard