Skip to content

Benchmark

UniGenBench++ (Chinese Long) - Text

Scores are percentages.

Models measured
26
Scores recorded
26
Sources
1
IQ weight
0.53

Score distribution

45.5%
Mean
57.1%
Median
35.8%
Std dev
3%
10th percentile
91.3%
90th percentile
0.27%
Min
0.27%93.2%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.53 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)