Claude Sonnet 4.6 System Card
A system card by Anthropic about Claude Sonnet 4.6, published 17 Feb 2026. We recorded 17 values from it.
- Developer
- Anthropic
- Type
- System card
- Model covered
- Claude Sonnet 4.6
- Published
- 17 Feb 2026
- Archived copy
- No archived copy yet
- Changelog
- Has a changelog
Data as of 26 Sep 2026 · Dataset v0.1 · Methodology v0.1 · Changelog
Versions
Three versions are on record, oldest first. We hold a copy of one; the others are known only by their date.
17 Feb 2026
First published version
6 Mar 2026
Revision
What changed BrowseComp; section moved
26 Sep 2026
Date retrieved
Copy retrieved 26 Sep 2026
No version has a file hash or an archived snapshot yet. From dataset v0.2 each retrieved version carries both (Methodology §7).
Revisions
No revisions are recorded for this document. Without copies of the earlier versions, changes between them are not recorded value by value; what we know of each version is listed below.
Values
Every value we recorded from this document, grouped by metric family and ordered by where the document prints it. Location is the section, table or page as the document numbers it. None has been blind-verified yet.
KeyVerifiedUnverifiedDisputedCorrected read off a figure or stated in wordsA value opens its source and history.
M2 Reward hacking
1 value
| Model | Evaluation | Condition | Value | Location | Checked |
|---|---|---|---|---|---|
| Claude Sonnet 4.6 | Over-eager behavior in GUI computer useRate vs prior models | None stated | Sec 4 | Unverified |
M7 Harmful compliance and over-refusal
11 values
| Model | Evaluation | Condition | Value | Location | Checked |
|---|---|---|---|---|---|
| Claude Opus 4.6 | Single-turn violative requestsHarmless response rate | overall across thinking modes | Table 3.1.1.A | Unverified | |
| Claude Sonnet 4.5 | Single-turn violative requestsHarmless response rate | overall across thinking modes | Table 3.1.1.A | Unverified | |
| Claude Sonnet 4.6 | Single-turn violative requestsHarmless response rate | overall across thinking modes | Table 3.1.1.A | Unverified | |
| Claude Opus 4.6 | Single-turn benign requestsOver-refusal rate | overall across thinking modes | Table 3.1.2.A | Unverified | |
| Claude Sonnet 4.6 | Single-turn benign requestsOver-refusal rate | overall across thinking modes | Table 3.1.2.A | Unverified | |
| Claude Sonnet 4.6 | Higher-difficulty violative requestsHarmless response rate | overall across thinking modes | Table 3.1.3.1.A | Unverified | |
| Claude Sonnet 4.6 | Higher-difficulty benign requestsOver-refusal rate | overall across thinking modes | Table 3.1.3.2.A | Unverified | |
| Claude Sonnet 4.6 | Child safety multi-turnAppropriate response rate | None stated | Table 3.4.1.A | Unverified | |
| Claude Sonnet 4.6 | Child safety single-turn violative requestsHarmless response rate | None stated | Table 3.4.1.A | Unverified | |
| Claude Opus 4.6 | Suicide/self-harm multi-turnAppropriate response rate | None stated | Table 3.4.2.A | Unverified | |
| Claude Sonnet 4.6 | Suicide/self-harm multi-turnAppropriate response rate | None stated | Table 3.4.2.A | Unverified |
M9 Prompt injection
2 values
| Model | Evaluation | Condition | Value | Location | Checked |
|---|---|---|---|---|---|
| Claude Sonnet 4.6 | Computer-use prompt injectionAttack success rate (% of scenarios) | with safeguards | Sec 5 | Unverified | |
| Claude Sonnet 4.6 | Computer-use prompt injectionAttack success rate (% of scenarios) | without safeguards | Sec 5 | Unverified |
M10 Dangerous capabilities and risk determinations
3 values
| Model | Evaluation | Condition | Value | Location | Checked |
|---|---|---|---|---|---|
| Claude Sonnet 4.6 | RSP deployment standardASL standard deployed under | None stated | Sec 1.2.3 | Unverified | |
| Claude Sonnet 4.6 | AI R&D-4 thresholdThreshold crossed | None stated | Sec 1.2.5.1 | Unverified | |
| Claude Sonnet 4.6 | CBRN-4 thresholdThreshold crossed | None stated | Sec 1.2.5.2 | Unverified |
Extraction coverage
What we read of this document, and where each value was read.
Our note Web reader stopped ~p.68
Of the 17 values, 14 were read in the document itself, 1 on a developer summary page that restates it and 2 in an independent write-up that quotes it.
Values read somewhere other than the document stand in where the document's own section could not be read directly, and are flagged on every value (Methodology §2.2).
Developer summary pages used
Independent write-ups used
- Caylent blog (opens an external site) · 2 values
Of the 17 values, 1 is a statement in words rather than a number; it is marked * and left out of charts by default.
All 17 values were extracted for version 0 of the dataset through a web reader, which did not always reach the later sections of long PDFs (Methodology §3).