Skip to content

Benchmark

MTEB(Indic, 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
23
Scores recorded
23
Sources
1
IQ weight
0.78

Score distribution

53.7%
Mean
46.2%
Median
11%
Std dev
41.7%
10th percentile
67%
90th percentile
39%
Min
39%73.3%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.78 for embedding models, measured over 23 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard