Skip to content

Benchmark

MTEB(eng, v1)

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

Models measured
25
Scores recorded
25
Sources
1
IQ weight
0.99

Score distribution

62.8%
Mean
62.1%
Median
4.9%
Std dev
56.1%
10th percentile
71.5%
90th percentile
53.9%
Min
53.9%72.2%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.99 for embedding models, measured over 25 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard