Skip to content

Benchmark

UniGenBench++ (Chinese Long) - Composition

Scores are percentages.

Models measured
26
Scores recorded
26
Sources
1
IQ weight
1.99

Score distribution

81.5%
Mean
86.3%
Median
19%
Std dev
73.1%
10th percentile
92.7%
90th percentile
0.13%
Min
0.13%95.8%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.99 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)