Skip to content

Benchmark

UniGenBench++ (Chinese Long) - Attribute-Overall

Scores are percentages.

Models measured
26
Scores recorded
26
Sources
1
IQ weight
2.31

Score distribution

87.6%
Mean
93.8%
Median
18.6%
Std dev
83.9%
10th percentile
96.1%
90th percentile
0.69%
Min
0.69%97.1%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.31 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)