Skip to content

Benchmark

UniGenBench++ (English Long) - Grammar-Overall

Scores are percentages.

Models measured
32
Scores recorded
32
Sources
1
IQ weight
1.12

Score distribution

78.7%
Mean
77.7%
Median
9.5%
Std dev
70.2%
10th percentile
89.3%
90th percentile
46.8%
Min
46.8%94.5%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.12 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)