Skip to content

Benchmark

MTEB(cmn, 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
7
Scores recorded
7
Sources
1
IQ weight
1.24

Score distribution

65.6%
Mean
64.2%
Median
6.2%
Std dev
60.5%
10th percentile
73.5%
90th percentile
57.9%
Min
57.9%75%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.24 for embedding models, measured over 7 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard