Skip to content

Benchmark

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

Higher scores are better.

Models measured
15
Scores recorded
15
Sources
1
IQ weight
1.22

Score distribution

0.509
Mean
0.496
Median
0.066
Std dev
0.41
10th percentile
0.59
90th percentile
0.396
Min
0.3960.597
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.22 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.