Tools Model Security Capability claude-opus-4-5
Model record
Claude Opus 4.5: how it does on security work, and what it will answer
- Lab
- Anthropic
- Access
- api
- Weights
- closed
- Safeguards
- As run by Anthropic for its system card
- Score rows
- 1
- Confidence
- CONFIRMED
What happened
Claude Opus 4.5 scores 82% end-to-end on Cybench on the 39 of 40 tasks Anthropic ran, per the benchmark's own leaderboard read on 11 September 2026.
Cybench, unguided, solved: 82% (vendor-card; vendor system card run; 39 of 40 tasks; safeguards: as run by the vendor; safeguard state per the card; run 2026-09-11; CONFIRMED). task count is what the vendor ran, so rows are comparable only with it beside them. Refusal gate (SINGLE, observed 2026-09-11): Safeguard state per the system card run.
Sources
- Cybench leaderboard CSVraw.githubusercontent.com/cybench/cybench.github.io/main/dat…
- Refusal policy or licenceplatform.claude.com/docs/en/build-with-claude/refusals-and-f…
One record from the Model Security Capability, maintained by the Security Desk. Data: CSV · JSON ·RSS · CC BY 4.0 with attribution to YFarmX.Tracker updated · 19 September 2026