Skip to content

Benchmark

UniGenBench++ (English) - State

Scores are percentages.

Models measured
32
Scores recorded
32
Sources
1
IQ weight
1.25

Score distribution

81.1%
Mean
82.6%
Median
10.4%
Std dev
66.8%
10th percentile
93.9%
90th percentile
52.4%
Min
52.4%95.3%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.25 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)