Skip to content

Benchmark

UniGenBench++ (English Long) - Feature matching

Scores are percentages.

Models measured
32
Scores recorded
32
Sources
1
IQ weight
1.43

Score distribution

77.1%
Mean
82.2%
Median
15%
Std dev
62.6%
10th percentile
90.7%
90th percentile
18.9%
Min
18.9%93.1%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.43 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)