Skip to content

Benchmark

UniGenBench++ (Chinese Long) - Non Contact

Scores are percentages.

Models measured
26
Scores recorded
26
Sources
1
IQ weight
1.62

Score distribution

75.8%
Mean
81.3%
Median
19.2%
Std dev
66.1%
10th percentile
91.5%
90th percentile
0%
Min
0%92.4%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.62 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)