Skip to content

Benchmark

UniGenBench++ (English) - Logical Reasoning

Scores are percentages.

Models measured
32
Scores recorded
32
Sources
1
IQ weight
1.20

Score distribution

52.5%
Mean
51.8%
Median
17.3%
Std dev
31.6%
10th percentile
74.8%
90th percentile
10.3%
Min
10.3%83.8%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.20 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)