Skip to content

Benchmark

Vals HLAB-Vals-1.1

Scores are percentages.

Models measured
40
Scores recorded
40
Sources
1
IQ weight
0.79

Score distribution

12.2%
Mean
12.1%
Median
6.9%
Std dev
4.2%
10th percentile
23.3%
90th percentile
1.7%
Min
1.7%27.1%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.79 for chat models, measured over 40 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard