Skip to content

Benchmark

UniGenBench++ (English) - Contact

Scores are percentages.

Models measured
32
Scores recorded
32
Sources
1
IQ weight
1.14

Score distribution

70.6%
Mean
72%
Median
13.4%
Std dev
56.6%
10th percentile
84.5%
90th percentile
24.3%
Min
24.3%94.1%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.14 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)