Skip to content

Benchmark

UniGenBench++ (Chinese Long) - Relationship-Overall

Scores are percentages.

Models measured
26
Scores recorded
26
Sources
1
IQ weight
1.89

Score distribution

82.6%
Mean
88.1%
Median
18.8%
Std dev
77.2%
10th percentile
92.8%
90th percentile
0.32%
Min
0.32%95.6%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.89 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)