Skip to content

Benchmark

UniGenBench++ (English) - Inclusion

Scores are percentages.

Models measured
32
Scores recorded
32
Sources
1
IQ weight
1.23

Score distribution

83.8%
Mean
85.5%
Median
11.5%
Std dev
70.1%
10th percentile
94.9%
90th percentile
38.8%
Min
38.8%96.1%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.23 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)