Skip to content

Benchmark

BRIGHT

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

Models measured
8
Scores recorded
8
Sources
1
IQ weight
0.30

Score distribution

16.2%
Mean
16.8%
Median
1.8%
Std dev
14.6%
10th percentile
17.6%
90th percentile
13.6%
Min
13.6%19.5%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.30 for embedding models, measured over 8 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard