Skip to content

Benchmark

UniGenBench++ (English) - Expression

Scores are percentages.

Models measured
32
Scores recorded
32
Sources
1
IQ weight
1.17

Score distribution

70%
Mean
73.7%
Median
14.3%
Std dev
51.9%
10th percentile
85.5%
90th percentile
25%
Min
25%96%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.17 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)