Skip to content

Benchmark

Vals CyberBench v1.1

Scores are percentages.

Models measured
43
Scores recorded
43
Sources
1
IQ weight
0.92

Score distribution

64.5%
Mean
69.5%
Median
13.2%
Std dev
43.8%
10th percentile
76.3%
90th percentile
28.6%
Min
28.6%80.4%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.92 for chat models, measured over 43 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard