Skip to content

Benchmark

UniGenBench++ (Chinese Long) - Hand

Scores are percentages.

Models measured
26
Scores recorded
26
Sources
1
IQ weight
1.76

Score distribution

75%
Mean
81.1%
Median
18.6%
Std dev
68%
10th percentile
88%
90th percentile
0%
Min
0%93.6%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.76 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)