METR finds low sabotage risk in Claude Opus 4 and 4.1 after independent review
METR reviewed unredacted evidence and agreed that catastrophic sabotage risk from Claude Opus 4 and 4.1 was low, while warning that reasoning-hiding and evaluation-awareness claims were overconfident. Anthropic said the review led it to revise threat models and alignment practices, including training changes for reasoning monitorability.
0 comments · 0 votes
Sign in to join the discussion →
No comments yet. Start the discussion.
Why it moved the index
Independent access to nonpublic evidence, concrete review findings, and documented changes to Anthropic's threat models and monitoring-oriented training directly strengthen controls against autonomous sabotage.
Assessment history
-
R1
Away 40 · confidence 84
New October 2025 independent risk review with verified operational effects on Anthropic's sabotage assessment and alignment practices.
14 Aug 2026
Share this page
-
DoomBench assesses “METR finds low sabotage risk in Claude Opus 4 and 4.1 after independent review” as evidence moving away from doom, with magnitude 40 and confidence 84 out of 100 in the safety and alignment category.
-
The DoomBench assessment of “METR finds low sabotage risk in Claude Opus 4 and 4.1 after independent review” is based on reporting from Model Evaluation and Threat Research and records the editorial rationale, source quality,...
-
DoomBench summarizes “METR finds low sabotage risk in Claude Opus 4 and 4.1 after independent review” as follows: METR reviewed unredacted evidence and agreed that catastrophic sabotage risk from Claude Opus 4 and 4.1 was low, while...
https://www.doombench.com/news/metr-finds-low-sabotage-risk-in-claude-opus-4-and-4-1-after-independent-review-2025-10-28