Skip to content

Benchmark

UniGenBench++ (English Long) - Negation

Scores are percentages.

Models measured
32
Scores recorded
32
Sources
1
IQ weight
0.86

Score distribution

70.7%
Mean
67.3%
Median
11.2%
Std dev
57%
10th percentile
84.5%
90th percentile
48.9%
Min
48.9%95.7%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.86 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)