Skip to content

Benchmark

UniGenBench++ (English) - Non Contact

Scores are percentages.

Models measured
32
Scores recorded
32
Sources
1
IQ weight
1.37

Score distribution

74%
Mean
76%
Median
12%
Std dev
61.2%
10th percentile
85.2%
90th percentile
26.7%
Min
26.7%92%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.37 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)