Skip to content

Benchmark

UniGenBench++ (Chinese) - State

Scores are percentages.

Models measured
29
Scores recorded
29
Sources
1
IQ weight
2.15

Score distribution

73.2%
Mean
83.5%
Median
30%
Std dev
2.4%
10th percentile
92.9%
90th percentile
0%
Min
0%96.7%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.15 for image-generation models, measured over 28 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)