Skip to content

Benchmark

MTEB(fra, v1) - Mean (TaskType)

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

Models measured
17
Scores recorded
17
Sources
1
IQ weight
1.65

Score distribution

54.6%
Mean
53.1%
Median
5.2%
Std dev
49.8%
10th percentile
62.9%
90th percentile
48%
Min
48%65.2%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.65 for embedding models, measured over 17 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard