Skip to content

Benchmark

UniGenBench++ (English) - Material

Scores are percentages.

Models measured
32
Scores recorded
32
Sources
1
IQ weight
1.07

Score distribution

83.9%
Mean
87.7%
Median
11.5%
Std dev
66.5%
10th percentile
97.2%
90th percentile
54.9%
Min
54.9%97.6%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.07 for image-generation models, measured over 31 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)