Skip to content

Benchmark

UniGenBench++ (English Long) - Animal

Scores are percentages.

Models measured
32
Scores recorded
32
Sources
1
IQ weight
1.48

Score distribution

75.9%
Mean
78.7%
Median
11.6%
Std dev
65.6%
10th percentile
88.7%
90th percentile
29.4%
Min
29.4%90.9%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.48 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)