Skip to content

Benchmark

llm-stats Image Generation Arena

Scores are percentages. Higher is better.

Models measured
22
Scores recorded
22
Sources
1
IQ weight
1.67

Score distribution

0.332%
Mean
0.439%
Median
1.9%
Std dev
-2%
10th percentile
2.6%
90th percentile
-2.7%
Min
-2.7%5.1%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.67 for image-generation models, measured over 22 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard