Skip to content

Benchmark

UniGenBench++ (Chinese Long) - Negation

Scores are percentages.

Models measured
26
Scores recorded
26
Sources
1
IQ weight
1.31

Score distribution

71.3%
Mean
75.4%
Median
16%
Std dev
59.5%
10th percentile
85.7%
90th percentile
9.5%
Min
9.5%93.2%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.31 for image-generation models, measured over 25 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)