Skip to content

Benchmark

Arena ELO Text to Image - Text Rendering

Higher scores are better.

Models measured
79
Scores recorded
86
Sources
1
IQ weight
1.24

Score distribution

1,158.7
Mean
1,143.2
Median
125.7
Std dev
1,015.1
10th percentile
1,346.2
90th percentile
873.9
Min
873.91,466.6
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.24 for image-generation models, measured over 68 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

Showing 51–86 of 86 results.

Data credits: LMArena, CC BY 4.0 (licence)