Anthropic · Claude 3

Claude 3 Sonnet

READER SUMMARY

Anthropic's balanced Claude 3 tier at launch, deployed through free chat, API, Amazon Bedrock and Google Cloud preview for large-scale enterprise workloads.

DOOM SCORE52.1out of 100model risk profile, not the overall index

CURRENT ASSESSMENT · REVISION 2

Why this model scores 52.1

Strong reasoning and vision with lower cost, high endurance and broad managed-cloud availability made Sonnet highly deployable, while its lower frontier capability and controlled interfaces constrained misuse and control difficulty.

Capability63

Autonomy30

Deployment90

Misuse potential47

Control difficulty39

0 comments · 0 votesOpen discussion

No comments yet. Start the discussion.

MODEL-ATTRIBUTED EVIDENCE

News tied to Claude 3 Sonnet

The model score of 52.1 rates this model's risk profile. The overall Doom Index of 63.2 measures the recalibrated complete evidence corpus. These values answer different questions.

NET MODEL-ATTRIBUTED INDEX CONTRIBUTION-0.03

Each article's leave-one-out Doom Index contribution is divided equally among the exact models named on that article. This prevents multi-model evidence from being claimed in full on several model pages. Model risk scores are recalculated from their technical profile and related news, but never feed back into the overall index.

21 May 2024SafetyAWAY

Anthropic maps and steers safety-relevant features in Claude 3 Sonnet

Anthropic scaled sparse feature extraction to the publicly deployed Claude 3 Sonnet, identified internal representations tied to unsafe code, bias, deception and manipulation, and demonstrated that activating or suppressing features could causally change model behavior.

Full item contribution: -0.05
Claude 3 Sonnet equal share: -0.05

Read assessment →

04 Mar 2024CapabilityTOWARD

Anthropic releases Claude 3 Opus and Sonnet

Anthropic released Claude 3 Opus and Sonnet through Claude, its generally available API and selected cloud platforms, adding stronger reasoning, vision, long-context processing and support for complex automated work.

Full item contribution: +0.03
Claude 3 Sonnet equal share: +0.02

Read assessment →

AUDIT TRAIL

Model score history

R2
Doom Score 52.1
Full-corpus evidence recalculated after run intensive-backfill-20260812-034452-may-2024-incremental under bounded-corpus-v2.
12 Aug 2026
R1
Doom Score 56.1
New exact Claude 3 Sonnet public model profile.
12 Aug 2026