Skip to content

Benchmark

UniGenBench++ (Chinese Long) - Full body

Scores are percentages.

Models measured
26
Scores recorded
26
Sources
1
IQ weight
1.83

Score distribution

78.3%
Mean
85%
Median
18.8%
Std dev
69.1%
10th percentile
91.6%
90th percentile
0.31%
Min
0.31%92.8%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.83 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)