Skip to content

Benchmark

UniGenBench++ (English Long) - Size

Scores are percentages.

Models measured
32
Scores recorded
32
Sources
1
IQ weight
1.54

Score distribution

88.5%
Mean
89.5%
Median
6.8%
Std dev
84.5%
10th percentile
94.7%
90th percentile
58.1%
Min
58.1%97%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.54 for image-generation models, measured over 31 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: UniGenBench++ (CodeGoat24), MIT (licence)