Claude Sonnet 4.6
19 values about Claude Sonnet 4.6 from 4 documents, in 4 metric families. In each family, values from its own document come first.
- Developer
- Anthropic
- Release date
- 17 Feb 2026The date of its first card in the dataset, the Claude Sonnet 4.6 System Card.
- Availability
- Public
- Its own document
- Claude Sonnet 4.6 System Card · 17 Feb 2026
- Also reported in
- Claude Mythos Preview System Card · 7 Apr 2026
- Claude Opus 4.8 System Card · 28 May 2026
- Claude Sonnet 5 System Card · 30 Jun 2026
Data as of 26 Sep 2026 · Dataset v0.1 · Methodology v0.1 · Changelog
Values by metric family
Each value as the document printed it. Select a value for its source, its checks and its history. Values from other documents are listed after the model’s own, each marked as the first report of that measure or as a restatement.
KeyVerifiedUnverifiedDisputedCorrected read off a figure or stated in wordsA value opens its source and history.
M2 · Reward hacking 2 values
| Evaluation and metric | Value | Document |
|---|---|---|
| From its own documentClaude Sonnet 4.6 System Card · 17 Feb 2026 | ||
| Over-eager behavior in GUI computer useRate vs prior models | Claude Sonnet 4.6 System Card17 Feb 2026 | |
| From other documents | ||
| GUI computer-use impossible tasksReward hack rateCondition: anti-hack promptClaude Mythos Preview System Card7 Apr 2026First reported | Claude Mythos Preview System Card7 Apr 2026First reported | |
M7 · Harmful compliance and over-refusal 11 values
| Evaluation and metric | Value | Document |
|---|---|---|
| From its own documentClaude Sonnet 4.6 System Card · 17 Feb 2026 | ||
| Child safety multi-turnAppropriate response rate | Claude Sonnet 4.6 System Card17 Feb 2026 | |
| Child safety single-turn violative requestsHarmless response rate | Claude Sonnet 4.6 System Card17 Feb 2026 | |
| Higher-difficulty benign requestsOver-refusal rateCondition: overall across thinking modes | Claude Sonnet 4.6 System Card17 Feb 2026 | |
| Higher-difficulty violative requestsHarmless response rateCondition: overall across thinking modes | Claude Sonnet 4.6 System Card17 Feb 2026 | |
| Single-turn benign requestsOver-refusal rateCondition: overall across thinking modes | Claude Sonnet 4.6 System Card17 Feb 2026 | |
| Single-turn violative requestsHarmless response rateCondition: overall across thinking modes | Claude Sonnet 4.6 System Card17 Feb 2026 | |
| Suicide/self-harm multi-turnAppropriate response rate | Claude Sonnet 4.6 System Card17 Feb 2026 | |
| From other documents | ||
| Single-turn violative requestsHarmless response rateCondition: no system prompt; APIClaude Opus 4.8 System Card28 May 2026First reported | Claude Opus 4.8 System Card28 May 2026First reported | |
| Malicious Claude Code useRefusal rate, malicious requestsClaude Sonnet 5 System Card30 Jun 2026First reported | Claude Sonnet 5 System Card30 Jun 2026First reported | |
| Malicious computer useRefusal rateClaude Sonnet 5 System Card30 Jun 2026First reported | Claude Sonnet 5 System Card30 Jun 2026First reported | |
| Single-turn violative requestsHarmless response rateCondition: no system prompt; APIClaude Sonnet 5 System Card30 Jun 2026Restated | Claude Sonnet 5 System Card30 Jun 2026Restated | |
M9 · Prompt injection 2 values
| Evaluation and metric | Value | Document |
|---|---|---|
| From its own documentClaude Sonnet 4.6 System Card · 17 Feb 2026 | ||
| Computer-use prompt injectionAttack success rate (% of scenarios)Condition: with safeguards | Claude Sonnet 4.6 System Card17 Feb 2026 | |
| Computer-use prompt injectionAttack success rate (% of scenarios)Condition: without safeguards | Claude Sonnet 4.6 System Card17 Feb 2026 | |
M10 · Dangerous capabilities and risk determinations 4 values
| Evaluation and metric | Value | Document |
|---|---|---|
| From its own documentClaude Sonnet 4.6 System Card · 17 Feb 2026 | ||
| AI R&D-4 thresholdThreshold crossed | Claude Sonnet 4.6 System Card17 Feb 2026 | |
| CBRN-4 thresholdThreshold crossed | Claude Sonnet 4.6 System Card17 Feb 2026 | |
| RSP deployment standardASL standard deployed under | Claude Sonnet 4.6 System Card17 Feb 2026 | |
| From other documents | ||
| CyberGymTargeted vuln reproduction rateClaude Opus 4.8 System Card28 May 2026First reported | Claude Opus 4.8 System Card28 May 2026First reported | |
Risk determinations
The developer's formal decisions about Claude Sonnet 4.6 under its framework, as printed. Levels from different frameworks do not map onto one another.
| Domain | Level as printed | Framework and document |
|---|---|---|
| Overall | ASL-3 Responsible Scaling Policy Claude Sonnet 4.6 System Card · 17 Feb 2026 | Responsible Scaling Policy Claude Sonnet 4.6 System Card · 17 Feb 2026 |
| Bio/chem | not crossed Responsible Scaling Policy Claude Sonnet 4.6 System Card · 17 Feb 2026 | Responsible Scaling Policy Claude Sonnet 4.6 System Card · 17 Feb 2026 |
| AI R&D / autonomy | not crossed Responsible Scaling Policy Claude Sonnet 4.6 System Card · 17 Feb 2026 | Responsible Scaling Policy Claude Sonnet 4.6 System Card · 17 Feb 2026 |