Skip to content

Benchmark

UniGenBench++ (English Long) - Inclusion

Scores are percentages.

Models measured
32
Scores recorded
32
Sources
1
IQ weight
1.57

Score distribution

88.1%
Mean
90.5%
Median
10.5%
Std dev
79.6%
10th percentile
96%
90th percentile
42.2%
Min
42.2%98.3%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.57 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)