Skip to content

Benchmark

UniGenBench++ (Chinese Long) - Action-Overall

Scores are percentages.

Models measured
26
Scores recorded
26
Sources
1
IQ weight
1.93

Score distribution

77.8%
Mean
83.2%
Median
18%
Std dev
70.6%
10th percentile
89.3%
90th percentile
0.6%
Min
0.6%93%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.93 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)