Skip to content

Benchmark

Vals SAGE

Scores are percentages.

Models measured
29
Scores recorded
29
Sources
1
IQ weight
2.24

Score distribution

84.5%
Mean
85.5%
Median
6.4%
Std dev
79.5%
10th percentile
89.5%
90th percentile
59.2%
Min
59.2%91.3%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.24 for chat models, measured over 29 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard