Skip to content

Benchmark

UniGenBench++ (Chinese Long) - 2D

Scores are percentages.

Models measured
26
Scores recorded
26
Sources
1
IQ weight
2.17

Score distribution

86.3%
Mean
92.1%
Median
18.5%
Std dev
81.5%
10th percentile
95.6%
90th percentile
1.6%
Min
1.6%96.5%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.17 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)