Skip to content

Benchmark

UniGenBench++ (Chinese Long) - Consistency

Scores are percentages.

Models measured
26
Scores recorded
26
Sources
1
IQ weight
1.74

Score distribution

78.3%
Mean
83.3%
Median
17.9%
Std dev
73.4%
10th percentile
90.9%
90th percentile
1.2%
Min
1.2%92.9%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.74 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)