Skip to content

Benchmark

BuiltBench(eng) - Retrieval

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

Models measured
16
Scores recorded
16
Sources
1
IQ weight
0.71

Score distribution

63.6%
Mean
64.6%
Median
3.4%
Std dev
58.8%
10th percentile
67.3%
90th percentile
57.3%
Min
57.3%71%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.71 for embedding models, measured over 16 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard