Skip to content

Benchmark

Design Arena Elo (models/image)

People compare model answers and choose which they prefer. Higher scores are better.

Models measured
58
Scores recorded
59
Sources
1
IQ weight
0.98

Score distribution

1,159.6
Mean
1,159
Median
95.2
Std dev
1,038
10th percentile
1,283
90th percentile
986
Min
9861,383
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.98 for image-generation models, measured over 55 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

Showing 51–59 of 59 results.