Skip to content

Benchmark

UniGenBench++ (Chinese Long) - Contact

Scores are percentages.

Models measured
26
Scores recorded
26
Sources
1
IQ weight
2.11

Score distribution

73.2%
Mean
79%
Median
18.6%
Std dev
62.6%
10th percentile
87.1%
90th percentile
0%
Min
0%92%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.11 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)