Benchmark profile
xAI biological refusal accuracy (Bio refusal accuracy)
Accuracy at refusing restricted biological requests in xAI's internal evaluation.
Data verified 26 confirmed releases in the last 30 daysStart free briefBenchmark score on Bio refusal accuracy — August 12, 2026
BenchLM mirrors the published score view for Bio refusal accuracy. Grok 4.6 leads the public snapshot at 100.0% , followed by Grok 4.5 (97.9%). 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 Bio refusal accuracy
Year
2026
Tasks
Restricted biological requests
Format
Refusal accuracy
Difficulty
Biological safety
The exact task set is not public. The exact card values remain display-only.
BenchLM freshness & provenance
Version
Bio refusal accuracy 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 Bio refusal accuracy measure?
Accuracy at refusing restricted biological requests in xAI's internal evaluation.
Which model scores highest on Bio refusal accuracy?
Grok 4.6 by xAI currently leads with a score of 100.0% on Bio refusal accuracy.
How many models are evaluated on Bio refusal accuracy?
2 AI models have been evaluated on Bio refusal accuracy on BenchLM.
Compare Top Models on Bio refusal accuracy
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.