Skip to content

Benchmark

GEditBench v2 - Visual Quality

Models measured
12
Scores recorded
14
Sources
1
IQ weight
1.37

Score distribution

1,004
Mean
1,025
Median
111.7
Std dev
900
10th percentile
1,142
90th percentile
694
Min
6941,149
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.37 for image-generation models, measured over 12 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard