Skip to content

Benchmark

UniGenBench++ (Chinese Long) - Overall

Scores are percentages.

Models measured
26
Scores recorded
26
Sources
1
IQ weight
2.23

Score distribution

79.2%
Mean
83.7%
Median
18%
Std dev
71.2%
10th percentile
90.5%
90th percentile
0.98%
Min
0.98%95.4%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.23 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)