Claude Sonnet 5
A widely available, lower-cost model able to plan, browse, use terminals, and autonomously finish longer multi-step tasks.
0 comments · 0 votes
Sign in to join the discussion →
No comments yet. Start the discussion.
Why this model scores 79.8
Broad availability and cost-efficient autonomy increase real-world exposure, while lower cyber capability and improved agentic safety moderate the score.
Videos about Claude Sonnet 5
Reviewed videos from Artificial Intelligence Videos. These links add context and never change a DoomBench score.
News tied to Claude Sonnet 5
The model score of 79.8 rates this model's risk profile. The overall Doom Index of 66.8 measures the complete temporally weighted evidence record. These values answer different questions.
Each article's current 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 use a bounded temporal offset around their technical profile, but never feed back into the overall index.
Anthropic shows automated researchers can mitigate ten alignment failures
In a controlled study, Claude autonomously developed post-training methods that improved all ten tested alignment-failure categories without measured capability loss, generalized to withheld evaluations and larger models, and closed 65% of an early Claude Opus 4.8 checkpoint's measured safety gap in 60 hours.
- Full item contribution
- -0.10
- Claude Sonnet 5 equal share
- -0.05
Anthropic gives paid Claude users autonomous browser actions
Anthropic made Claude in Chrome generally available on every paid plan and enabled automatic approval for actions its safety classifier judges consistent with the user's request. Claude can use existing logins to read, type, click, navigate, and fill forms. In a stronger prompt-injection evaluation, probes plus the classifier reduced successful attacks to zero for Sonnet 5, Opus 5, and Mythos 5 and 0.3 percent for Fable 5, with the remaining successes manually rated low severity.
- Full item contribution
- +0.13
- Claude Sonnet 5 equal share
- +0.03
Anthropic reports deployed auto mode cuts serious unintended agent harm
Anthropic reported that Claude Code's deployed permission classifier reduced production-level unintended harm in reviewed sessions from 6.3% under manual approval to 2.4%. Separate dated production case studies document sustained use at Nuro, Gusto, and Garner Health, while third-party testing found no successful attacks against three current Claude models in 720 prompt-injection trials.
- Full item contribution
- -0.07
- Claude Sonnet 5 equal share
- -0.02
Anthropic releases a more autonomous Claude Sonnet 5
Sonnet 5 brought stronger planning, browser and terminal use, and sustained task completion to a cheaper, widely available model tier.
- Full item contribution
- +0.33
- Claude Sonnet 5 equal share
- +0.33
Model score history
-
R6
Doom Score 79.8
Source-backed model availability audit using the model's existing primary or authoritative catalogue evidence. Exact-version evidence chronology replayed under temporal-monthly-pressure-v4.
12 Aug 2026 -
R5
Doom Score 79.8
Exact-version evidence chronology replayed after run doombench-hourly-news-20260812-142416 under temporal-monthly-pressure-v4.
12 Aug 2026 -
R4
Doom Score 79.4
Exact-version evidence chronology replayed after run doombench-hourly-news-20260812-132112 under fixed-sensitivity-v3.
12 Aug 2026 -
R3
Doom Score 78.5
Full-corpus evidence recalculated after run doombench-hourly-news-20260812-002108 under bounded-corpus-v2.
12 Aug 2026 -
R2
Doom Score 81.6
Full-corpus evidence recalculated after run intensive-backfill-20260811-191225 under bounded-corpus-v2.
11 Aug 2026 -
R1
Doom Score 79.7
Initial source-backed model assessment
11 Aug 2026