← Model benchmark
OpenAI · GPT-5.6

GPT-5.6 Sol

The flagship GPT-5.6 tier, with the family's strongest agentic, cyber, scientific, computer-use, and AI-research capabilities.

DOOM SCORE92.9out of 100
CURRENT ASSESSMENT · REVISION 1

Why this model scores 92.9

Frontier capability, strong autonomy, broad availability, and acceleration of AI research create the catalogue's highest current risk profile despite a robust safeguard stack.

Capability98
Autonomy96
Deployment92
Misuse potential94
Control difficulty82
AUDIT TRAIL

Model score history

  1. R1
    Doom Score 92.9

    Initial source-backed model assessment

    11 Aug 2026