Skip to content

Benchmark

MTEB(kor, v2) - STS

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

Models measured
23
Scores recorded
23
Sources
1
IQ weight
1.19

Score distribution

65.6%
Mean
80.1%
Median
22.3%
Std dev
36%
10th percentile
87.5%
90th percentile
33.7%
Min
33.7%89.9%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.19 for embedding models, measured over 23 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard