Skip to content

Benchmark

HUME(v1) - Classification

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

Models measured
5
Scores recorded
5
Sources
1
IQ weight
0.53

Score distribution

62.7%
Mean
62.1%
Median
6.1%
Std dev
56.1%
10th percentile
72.1%
90th percentile
56.1%
Min
56.1%72.1%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.53 for embedding models, measured over 5 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard