CyScenarioBench Scenarios Ever Solved (CyScenarioBench solved)
We show this table for reference; we do not rank on it.
Number of CyScenarioBench scenarios completed successfully in at least one run.
Benchmark score on CyScenarioBench solved — September 29, 2026
We compile the CyScenarioBench solved rows from benchmark-owner or independent runs. GPT-6 Astra leads the table at 9%, followed by GPT-5.6 Sol (7%). We do not use these results to rank models overall.
GPT-6 Astra
OpenAI
GPT-5.6 Sol
OpenAI
2 modelsAgenticCurrentDisplay onlyUpdated September 29, 2026
Benchmark score table (2 models)
ScoreAbout CyScenarioBench solved
Year
2026
Tasks
11 cyber scenarios
Format
Scenarios solved at least once
Difficulty
Long-horizon cybersecurity
This companion metric counts scenarios with at least one successful run. It is not interchangeable with the benchmark's average success rate.
Freshness and provenance
Version
CyScenarioBench solved 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.
Questions
What does CyScenarioBench solved measure?
Number of CyScenarioBench scenarios completed successfully in at least one run.
Which model scores highest on CyScenarioBench solved?
GPT-6 Astra by OpenAI currently leads with a score of 9% on CyScenarioBench solved.
How many models are evaluated on CyScenarioBench solved?
2 AI models have been evaluated on CyScenarioBench solved on BenchLM.
Compare top models on CyScenarioBench solved
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.