Skip to content

Benchmark

MTEB(fra, v1) - Retrieval

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

Models measured
24
Scores recorded
24
Sources
1
IQ weight
0.98

Score distribution

47%
Mean
42.4%
Median
13.3%
Std dev
33%
10th percentile
68.5%
90th percentile
26.9%
Min
26.9%71.8%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.98 for embedding models, measured over 24 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard