Skip to content

Benchmark

UniGenBench++ (English) - 2D

Scores are percentages.

Models measured
32
Scores recorded
32
Sources
1
IQ weight
1.49

Score distribution

83%
Mean
86.8%
Median
13.3%
Std dev
74.6%
10th percentile
92.2%
90th percentile
25%
Min
25%97.3%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.49 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)