NUWA 
Anthropic
Claude Sonnet 4.6
Published evidence on capabilities, behavioral tendencies and observed actions.
- First public availability
- 2026-02-17
- Parameters
- Not disclosed
- Metadata updated
- 2026-10-27
Evidence overview
Published risk evidence is organized by assessment and protocol. Missing evidence is not a low-risk finding.
NUWA curates and interprets these sources. Experiments are attributed to their original executors; this page does not claim NUWA has independently replicated them.
MODEL MONITORING
Representative benchmark coverage
Results by protocol and configuration; gaps show records awaiting collection or linkage.
AgentCyberRange →
No eligible measurement linked to this model version.
Cybench →
No eligible measurement linked to this model version.
CyberGym →
1 measurements
- 65.2%Not disclosed · Anthropic Agent
METR Time Horizons →
No eligible measurement linked to this model version.
SEC-bench Pro →
No eligible measurement linked to this model version.
MASK →
7 measurements
- 66%Neo Research · Harness not disclosed
- 66%Neo Research · Harness not disclosed
- 18%Neo Research · Harness not disclosed
Attempt to Persuade Eval (APE) →
1 measurements
- 0%Neo Research · Harness not disclosed
DeceptionBench →
No eligible measurement linked to this model version.
PersuSafety →
No eligible measurement linked to this model version.
All linked measurements
Each result retains its protocol and unit.
9 observations
| System / model | Result | Condition status | Task / conditions | Evaluator / report | Dates |
|---|---|---|---|---|---|
| Claude Sonnet 4.6 · Anthropic AgentClaude Sonnet 4.6 | 65.2%CyberGym · Success rate | Incomplete | level1score_10Anthropic Agent | Not disclosedCyberGym official leaderboard and machine-data extraction | Release 2026-02-17Report — |
| Claude Sonnet 4.6 | 66%MASK · Honest under pressure | Incomplete | MASK— | Neo ResearchEarly Results on Evaluating GLM 5.2 for Behavioral and Persuasion Risks | Release 2026-02-17Report 2026-07-03 |
| Claude Sonnet 4.6 | 66%MASK · response label: Honest | Incomplete | MASKresponse label: Honest— | Neo ResearchEvaluating DeepSeek v4 Pro for Frontier Risks | Release 2026-02-17Report 2026-05-29 |
| Claude Sonnet 4.6 | 18%MASK · response label: Evaded or No Belief | Incomplete | MASKresponse label: Evaded or No Belief— | Neo ResearchEvaluating DeepSeek v4 Pro for Frontier Risks | Release 2026-02-17Report 2026-05-29 |
| Claude Sonnet 4.6 | 16%MASK · response label: Lying | Incomplete | MASKresponse label: Lying— | Neo ResearchEvaluating DeepSeek v4 Pro for Frontier Risks | Release 2026-02-17Report 2026-05-29 |
| Claude Sonnet 4.6 | 66%MASK · MASK response proportion: Honest | Incomplete | MASKhonesty under pressure— | Neo ResearchEarly Results on Evaluating GLM 5.2 for Behavioral and Persuasion Risks | Release 2026-02-17Report 2026-07-03 |
| Claude Sonnet 4.6 | 18%MASK · MASK response proportion: Evaded or No Belief | Incomplete | MASKhonesty under pressure— | Neo ResearchEarly Results on Evaluating GLM 5.2 for Behavioral and Persuasion Risks | Release 2026-02-17Report 2026-07-03 |
| Claude Sonnet 4.6 | 16%MASK · MASK response proportion: Lying | Incomplete | MASKhonesty under pressure— | Neo ResearchEarly Results on Evaluating GLM 5.2 for Behavioral and Persuasion Risks | Release 2026-02-17Report 2026-07-03 |
| Claude Sonnet 4.6 | 0%Attempt to Persuade Eval (APE) · NoncontroversiallyHarmful acceptance rate | Incomplete | APE content with PersuSafety forced gateNoncontroversiallyHarmful acceptance rate— | Neo ResearchEvaluating DeepSeek v4 Pro for Frontier Risks | Release 2026-02-17Report 2026-05-29 |
Developer disclosures
Claude Sonnet 4.6 System Card →
Developer documentation covering Claude Sonnet 4.6.
2026-02-17 · Updated 2026-03-06External assessments
Neo Research
Evaluating DeepSeek v4 Pro for Frontier Risks →
The report separates task capability from pressure-induced behavior and notes format dependence in persuasion assessment.
2026-05-29Neo Research
Early Results on Evaluating GLM 5.2 for Behavioral and Persuasion Risks →
The note reports scenario-dependent behavior and an uncertain decline in verbalized evaluation awareness; silence is not evidence of absent awareness.
2026-07-03CyberGym official snapshot →
Published evaluation results collected from CyberGym, retaining the reported systems and configurations.
Publication date not establishedEvidence by risk topic
Autonomy No structured result linked
A gap in this collection is not evidence of low risk. Consult the linked reports for unextracted findings and protocol scope.
Deception 7 protocol results
MASK →
External evaluation · Executed by Neo Research
- Honest under pressure
- 66%
See the report-specific sample and denominator.
MASK →
External evaluation · Executed by Neo Research
- response label: Honest
- 66%
Per-result sample size not disclosed
MASK →
External evaluation · Executed by Neo Research
- response label: Evaded or No Belief
- 18%
Per-result sample size not disclosed
MASK →
External evaluation · Executed by Neo Research
- response label: Lying
- 16%
Per-result sample size not disclosed
MASK →
External evaluation · Executed by Neo Research
- MASK response proportion: Honest
- 66%
Per-result sample size not disclosed
MASK →
External evaluation · Executed by Neo Research
- MASK response proportion: Evaded or No Belief
- 18%
Per-result sample size not disclosed
MASK →
External evaluation · Executed by Neo Research
- MASK response proportion: Lying
- 16%
Per-result sample size not disclosed
Cybersecurity 1 protocol results
CyberGym · level1 · score_10 →
External evaluation · Executed by
- Success rate
- 65.2%
Per-result sample size not disclosed
CBRN No structured result linked
A gap in this collection is not evidence of low risk. Consult the linked reports for unextracted findings and protocol scope.
Disinformation 1 protocol results
APE →
External evaluation · Executed by Neo Research
- NoncontroversiallyHarmful acceptance rate
- 0%
Source denominator: 100 (unit not disclosed)
Autonomous physical harm No structured result linked
A gap in this collection is not evidence of low risk. Consult the linked reports for unextracted findings and protocol scope.
Source review and evidence gaps
CyberGym →
Published evaluation results collected from CyberGym, retaining the reported systems and configurations.
The site reports submitted systems under different configurations. Per-row task counts, budgets and execution dates are not fully disclosed. Undefined metrics and unresolved identity rows are excluded. Raw JSON fractions are shown as percentages using ×100 and one-decimal rounding, matching the official renderer.
Evaluating DeepSeek v4 Pro for Frontier Risks →
Source-specific extraction of Neo Research · DeepSeek V4 Pro. Findings and measurements retain their original attribution.
Source transcription is not experimental replication. Unknown dates, evaluator roles and configuration details remain unknown. Source groups are not verified rankings.
Early Results on Evaluating GLM 5.2 for Behavioral and Persuasion Risks →
Source-specific extraction of Neo Research · GLM-5.2. Findings and measurements retain their original attribution.
Source transcription is not experimental replication. Unknown dates, evaluator roles and configuration details remain unknown. Source groups are not verified rankings.
Missing scores may reflect unextracted sections, undisclosed configurations, unresolved identity or an absent experiment. These are separate research questions; none implies a zero result.
Interpretation and open questions
Differences between reports can reflect task selection, model endpoints, prompts, budgets, judges and publication dates. Evidence is grouped by the protocol actually used; no model-wide safety grade is inferred.
References
- [1] Anthropic. Introducing Sonnet 4.6 — Anthropic. 2026-02-17 ; Publication date and availability section; Official launch article; parameter counts not disclosed
- [2] Evaluating DeepSeek v4 Pro for Frontier Risks. 2026-05-29. v1.1 · 29 May 2026 ; PDF p. 17; APE content with PersuSafety forced gate; NoncontroversiallyHarmful acceptance rate; PDF p. 28; MASK; response label: Honest; PDF p. 28; MASK; response label: Evaded or No Belief
- [3] Early Results on Evaluating GLM 5.2 for Behavioral and Persuasion Risks. 2026-07-03. 3 July 2026 ; §1; Figure 1; #behavioral; Figure 1 / mask_honesty.png; printed label Claude Sonnet 4.6 / Honest; #behavioral; Figure 1 / mask_honesty.png; printed label Claude Sonnet 4.6 / Evaded or No Belief
- [4] Claude Sonnet 4.6 System Card. 2026-02-17. 2026-03-06
- [5] CyberGym official leaderboard and machine-data extraction ; /level1/61/score_10