Skip to content

Benchmark

INCLUDE-base-44 0-shot croatian (Speakleash)

Higher scores are better.

Models measured
15
Scores recorded
15
Sources
1
IQ weight
1.32

Score distribution

0.664
Mean
0.658
Median
0.083
Std dev
0.544
10th percentile
0.756
90th percentile
0.475
Min
0.4750.769
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.32 for chat models, measured over 15 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

Data credits: Speakleash community evaluation of INCLUDE-base-44 (Romanou et al., arXiv:2411.19799). Public results.csv; no results licence stated.