Skip to content

Benchmark

MTEB(rus, 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
19
Scores recorded
19
Sources
1
IQ weight
0.52

Score distribution

47.1%
Mean
53.2%
Median
17.1%
Std dev
28.6%
10th percentile
67%
90th percentile
23.7%
Min
23.7%71.4%
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 19 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard