Skip to content

Benchmark

UniGenBench++ (English Long) - Non Contact

Scores are percentages.

Models measured
32
Scores recorded
32
Sources
1
IQ weight
1.33

Score distribution

72.3%
Mean
74.1%
Median
14.1%
Std dev
58.5%
10th percentile
87.9%
90th percentile
17.4%
Min
17.4%89.3%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.33 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)