Benchmark profile
StrongREJECT compliance rate (StrongREJECT compliance)
Compliance on the public StrongREJECT harmful-prompt benchmark and evaluator suite.
Data verified 26 confirmed releases in the last 30 daysStart free briefBenchmark score on StrongREJECT compliance — August 12, 2026
BenchLM mirrors the published score view for StrongREJECT compliance. Grok 4.6 leads the public snapshot at 3.9%. We do not use these results to rank models overall.
Benchmark score table (1 model)
ScoreAbout StrongREJECT compliance
Year
2024
Tasks
Harmful prompts across six behavior categories
Format
Compliance rate
Difficulty
Adversarial safety
The benchmark code and data utilities are public. BenchLM preserves xAI's exact reported compliance rate as display-only provider evidence; lower is better.
BenchLM freshness & provenance
Version
StrongREJECT compliance 2024
Refresh cadence
Annual
Staleness state
Refreshing
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 StrongREJECT compliance measure?
Compliance on the public StrongREJECT harmful-prompt benchmark and evaluator suite.
Which model scores highest on StrongREJECT compliance?
Grok 4.6 by xAI currently leads with a score of 3.9% on StrongREJECT compliance.
How many models are evaluated on StrongREJECT compliance?
1 AI models have been evaluated on StrongREJECT compliance on BenchLM.
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.