Skip to content

Benchmark

WMDP-Cyber

Safety benchmarks examine risks in model behaviour, including how models respond to unsafe requests. Scores are percentages.

Models measured
1
Scores recorded
1
Sources
1
IQ weight
No weight published

Score distribution

88.1%
Mean
88.1%
Median
0%
Std dev
88.1%
10th percentile
88.1%
90th percentile
88.1%
Min

Leaderboard

#ModelScore
1Grok 4.7· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim88.1%

Data credits: Data by LLM Stats