Skip to content

Benchmark

MTEB(rus, v1.1) - Retrieval

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
0.60

Score distribution

40.2%
Mean
40.7%
Median
28.4%
Std dev
9.2%
10th percentile
75.2%
90th percentile
1.5%
Min
1.5%78.2%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.60 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