Skip to content

Benchmark

UniGenBench++ (English Long) - Logical Reasoning

Scores are percentages.

Models measured
32
Scores recorded
32
Sources
1
IQ weight
1.36

Score distribution

67.3%
Mean
68.2%
Median
14.4%
Std dev
51.5%
10th percentile
83%
90th percentile
19.4%
Min
19.4%91%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.36 for image-generation models, measured over 31 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: UniGenBench++ (CodeGoat24), MIT (licence)