Skip to content

Benchmark

RISEBench - Causal

Scores are percentages.

Models measured
12
Scores recorded
14
Sources
1
IQ weight
0.71

Score distribution

29%
Mean
27.8%
Median
22.1%
Std dev
4.4%
10th percentile
63.3%
90th percentile
2.2%
Min
2.2%66.7%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.71 for image-generation models, measured over 10 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard