Skip to content

Benchmark

GenExam Strict - Geo

Scores are percentages.

Models measured
27
Scores recorded
29
Sources
1
IQ weight
1.86

Score distribution

26.9%
Mean
9.1%
Median
32%
Std dev
0%
10th percentile
75.8%
90th percentile
0%
Min
0%86.4%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.86 for image-generation models, measured over 26 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: GenExam (OpenGVLab), MIT (licence)