← Model benchmark
Anthropic · Claude Opus

Claude Opus 4.8

A highly capable agentic model with stronger coding, computer use, long-running work, and documented improvements in alignment behavior.

DOOM SCORE83.8out of 100
CURRENT ASSESSMENT · REVISION 1

Why this model scores 83.8

Near-frontier autonomy and dangerous-domain capability create substantial risk, partly offset by lower measured misalignment and deployed cyber safeguards.

Capability93
Autonomy92
Deployment75
Misuse potential84
Control difficulty68
AUDIT TRAIL

Model score history

  1. R1
    Doom Score 83.8

    Initial source-backed model assessment

    11 Aug 2026