Skip to content

Benchmark

UniGenBench++ (Chinese Long) - State

Scores are percentages.

Models measured
26
Scores recorded
26
Sources
1
IQ weight
2.02

Score distribution

80%
Mean
85.2%
Median
17.3%
Std dev
74.2%
10th percentile
89.5%
90th percentile
1.4%
Min
1.4%92.3%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.02 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)