Skip to content

Benchmark

NanoBEIR

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

Models measured
12
Scores recorded
12
Sources
1
IQ weight
0.46

Score distribution

66.6%
Mean
66.3%
Median
3.8%
Std dev
61.5%
10th percentile
71.6%
90th percentile
61%
Min
61%72%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.46 for embedding models, measured over 12 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard