Skip to content

Benchmark

UniGenBench++ (Chinese) - Overall

Scores are percentages.

Models measured
29
Scores recorded
29
Sources
1
IQ weight
2.37

Score distribution

67.1%
Mean
75.2%
Median
27.6%
Std dev
2.7%
10th percentile
88.1%
90th percentile
1.3%
Min
1.3%93.8%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.37 for image-generation models, measured over 28 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)