WhitzardNUWA Lab ↗
NUWANUWA INDEX

Search NUWA Index

Research · Benchmarks · Findings · Perspectives

中文
← Assessments and reports

DEVELOPER DISCLOSURE · Anthropic

Claude Sonnet 5 System Card

Developer documentation covering Claude Sonnet 5.

Published 2026-06-30 · Updated 2026-07-10

Sources ↓

Developer-authored disclosure. The section map was checked; this is not a full reading or result extraction. NUWA has not independently replicated these experiments.

Models covered

capability · PDF table of contents → named RSP / cyber / alignment sections

CyberGym

Protocol record →

Validated reproduction across a corpus of historical vulnerabilities.

A protocol mention does not establish cross-report comparability or independent replication.

This section is catalogued; no precise numerical result has been extracted here. Open the original report for its figures and full findings.

capability · PDF table of contents → named RSP / cyber / alignment sections

ExploitBench

Protocol record →

Separates exploit development into capability levels, distinguishing bug triggering from reusable exploitation primitives and control.

A protocol mention does not establish cross-report comparability or independent replication.

This section is catalogued; no precise numerical result has been extracted here. Open the original report for its figures and full findings.

propensity · PDF table of contents → named RSP / cyber / alignment sections

MASK

Protocol record →

Condition-bounded frequency of lying under stated pressures.

A protocol mention does not establish cross-report comparability or independent replication.

This section is catalogued; no precise numerical result has been extracted here. Open the original report for its figures and full findings.

capability · PDF table of contents → named RSP / cyber / alignment sections

SHADE-Arena

Protocol record →

Covert side-task completion and monitor detection under defined tool access.

A protocol mention does not establish cross-report comparability or independent replication.

This section is catalogued; no precise numerical result has been extracted here. Open the original report for its figures and full findings.

Report coverage

SectionSource locationTreatment
RSP, cyber and alignment sectionsPDF table of contents → named RSP / cyber / alignment sectionsLinked protocol

Historical comparator source located. Newer card summaries and external evaluations must preserve the tested model version, harness and safeguard configuration.

References

  1. [1] Claude Sonnet 5 System Card. 2026-06-30. 2026-07-10