Skip to content

Benchmark

UniGenBench++ (Chinese Long) - Color

Scores are percentages.

Models measured
26
Scores recorded
26
Sources
1
IQ weight
2.51

Score distribution

91.9%
Mean
97.7%
Median
18.9%
Std dev
90%
10th percentile
99%
90th percentile
1.4%
Min
1.4%99.2%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.51 for image-generation models, measured over 25 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)