Claude Sonnet 4
A broadly available hybrid-reasoning model with stronger coding, tool use, and agentic task performance than Sonnet 3.7.
0 comments · 0 votes
Sign in to join the discussion →
No comments yet. Start the discussion.
Why this model scores 66.7
Improved coding and tool use reached free users and major cloud platforms, while stronger steerability and safety testing moderated residual risk.
News tied to Claude Sonnet 4
The model score of 66.7 rates this model's risk profile. The overall Doom Index of 67.9 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 reports production safety training that suppresses agentic misalignment
Anthropic reported that difficult-advice training reduced agentic misalignment to zero in its evaluation and that constitution-based documents generalized beyond their training distribution. The techniques were applied to production models beginning with Claude Opus 4.5, with explicit warnings that the tests cannot guarantee safety.
- Full item contribution
- -0.24
- Claude Sonnet 4 equal share
- -0.04
OpenAI and Anthropic publish joint model safety evaluations
OpenAI and Anthropic jointly evaluated each other's frontier models across alignment, misuse and capability tests, publishing strengths, failures and limits of extrapolating the results to real-world behavior.
- Full item contribution
- -0.08
- Claude Sonnet 4 equal share
- -0.01
Anthropic introduces Claude 4 and activates stronger safety protections
Anthropic launched stronger coding and agent models while activating its AI Safety Level 3 deployment controls.
- Full item contribution
- +0.14
- Claude Sonnet 4 equal share
- +0.07
Model score history
-
R6
Doom Score 66.7
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 66.7
Exact-version evidence chronology replayed after run doombench-hourly-news-20260812-142416 under temporal-monthly-pressure-v4.
12 Aug 2026 -
R4
Doom Score 66.9
Exact-version evidence chronology replayed after run doombench-hourly-news-20260812-132112 under fixed-sensitivity-v3.
12 Aug 2026 -
R3
Doom Score 67.3
Full-corpus evidence recalculated after run intensive-backfill-20260812-080357-august-2025-pass1 under bounded-corpus-v2.
12 Aug 2026 -
R2
Doom Score 68.4
Full-corpus evidence recalculated after run intensive-backfill-20260811-191225 under bounded-corpus-v2.
11 Aug 2026 -
R1
Doom Score 66.7
Initial source-backed model assessment
11 Aug 2026