Skip to content

Benchmark

UniGenBench++ (English) - Composition

Scores are percentages.

Models measured
32
Scores recorded
32
Sources
1
IQ weight
1.20

Score distribution

82.5%
Mean
83%
Median
9.5%
Std dev
70.3%
10th percentile
93.5%
90th percentile
55.4%
Min
55.4%97%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.20 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)