Skip to content

Benchmark

UniGenBench++ (English) - Compound-Overall

Scores are percentages.

Models measured
32
Scores recorded
32
Sources
1
IQ weight
1.26

Score distribution

72.2%
Mean
72.8%
Median
15%
Std dev
54.4%
10th percentile
90.9%
90th percentile
26.7%
Min
26.7%92.9%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.26 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)