Skip to content

Benchmark

UniGenBench++ (Chinese Long) - World Knowledge

Scores are percentages.

Models measured
26
Scores recorded
26
Sources
1
IQ weight
2.10

Score distribution

89.9%
Mean
94.4%
Median
18.5%
Std dev
88.7%
10th percentile
97.8%
90th percentile
0.29%
Min
0.29%98.8%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.10 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)