Skip to content

Benchmark

UniGenBench++ (English Long) - Shape

Scores are percentages.

Models measured
32
Scores recorded
32
Sources
1
IQ weight
1.37

Score distribution

83.1%
Mean
86.7%
Median
10.1%
Std dev
73.6%
10th percentile
92.5%
90th percentile
43%
Min
43%96.5%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.37 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)