# CyScenarioBench

Anthropic integrated Project Glasswing and its Cyber Verification Program into three access tiers that relax model cyber safeguards according to defensive, authorized red-team and specialized testing work. Previously, generally available models blocked most cyber work, and the CVP offered a single reduced-safeguard channel. On CyScenarioBench, with five attempts at each of 10 challenges per tier, no CVP access blocked every task at the first prompt, Defense Access blocked 46 of 50 trials with four successes, and Red Team Access had no blocks and completed 34 of 50, comparable to the 67.6% success rate with no safeguards.

Anthropic integrated Project Glasswing and its Cyber Verification Program into three access tiers that relax model cyber safeguards according to defensive, authorized red-team and specialized testing work. Previously, generally available models blocked most cyber work, and the CVP offered a single reduced-safeguard channel. On CyScenarioBench, with five attempts at each of 10 challenges per tier, no CVP access blocked every task at the first prompt, Defense Access blocked 46 of 50 trials with four successes, and Red Team Access had no blocks and completed 34 of 50, comparable to the 67.6% success rate with no safeguards.

Anthropic merged its earlier Project Glasswing and Cyber Verification Program into an expanded three-tier access program, letting vetted security teams use its most capable models with fewer cyber blocks. Previously, generally available models carried conservative cyber safeguards that blocked most cyber work, leaving defenders without an equivalent path. Across five attempts at each of 10 CyScenarioBench challenges, every task was blocked on the first prompt without CVP access; the Defense tier blocked 46 of 50 trials with four successes, while the Red Team tier saw no blocks and completed 34 of 50, effectively matching the 67.6% success rate with no safeguards.

Anthropic merged its earlier Project Glasswing and Cyber Verification Program into an expanded three-tier access program, letting vetted security teams use its most capable models with fewer cyber blocks. Previously, generally available models carried conservative cyber safeguards that blocked most cyber work, leaving defenders without an equivalent path. Across five attempts at each of 10 CyScenarioBench challenges, every task was blocked on the first prompt without CVP access; the Defense tier blocked 46 of 50 trials with four successes, while the Red Team tier saw no blocks and completed 34 of 50, effectively matching the 67.6% success rate with no safeguards.