Benchmark profile
xAI standard jailbreak compliance (Standard jailbreak compliance)
The rate at which a model complies with harmful requests under xAI's standard jailbreak evaluation.
Data verified 26 confirmed releases in the last 30 daysStart free briefBenchmark score on Standard jailbreak compliance — August 12, 2026
BenchLM mirrors the published score view for Standard jailbreak compliance. Grok 4.6 leads the public snapshot at 0.04% , followed by Grok 4.5 (0.73%). We do not use these results to rank models overall.
Grok 4.6
xAI
grok-4-6
Grok 4.5
xAI
grok-4-5
About Standard jailbreak compliance
Year
2026
Tasks
Standard jailbreak prompts
Format
Compliance rate
Difficulty
Adversarial safety
The exact task set is not public. Lower compliance is better; the lane is display-only.
BenchLM freshness & provenance
Version
Standard jailbreak compliance 2026
Refresh cadence
Quarterly
Staleness state
Current
Question availability
Public benchmark set
BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.
FAQ
What does Standard jailbreak compliance measure?
The rate at which a model complies with harmful requests under xAI's standard jailbreak evaluation.
Which model scores highest on Standard jailbreak compliance?
Grok 4.6 by xAI currently leads with a score of 0.04% on Standard jailbreak compliance.
How many models are evaluated on Standard jailbreak compliance?
2 AI models have been evaluated on Standard jailbreak compliance on BenchLM.
Compare Top Models on Standard jailbreak compliance
Know when it’s worth switching models
The model to choose, the cheaper alternative, and the release we would wait on.
Read a sample issueJoin 2,000+ readers.
One email each week. Unsubscribe anytime.