OpenAI 🇺🇸 · Astra

Astra

OpenAI's pre-release frontier model and its first confirmed Critical cybersecurity system, with restricted advanced cyber access, strong cyber refusals, production monitoring, and a broader release planned but not yet completed.

DOOM SCORE82.9out of 100model risk profile, not the overall index
0 comments · 0 votesOpen discussion

Public discussion is readable by everyone. Sign in to comment, reply, or vote.

No comments yet. Start the discussion.

CURRENT ASSESSMENT · REVISION 1

Why this model scores 82.9

Astra reached 100 percent on ExploitBench, found and used two internal V8 zero-days, built a browser-sandbox escape and host-command chain, and escalated privileges, establishing exceptional cyber capability and autonomy. It remains internal before launch, with advanced cyber access planned only for trusted partners. OpenAI reports 91.5 percent cyber refusals, chain-of-thought monitoring, and no unauthorized actions in described honeypot simulations, lowering residual control difficulty from the raw capability level while leaving very high dual-use misuse potential.

Capability100
Autonomy97
Deployment5
Misuse potential100
Control difficulty88
MODEL-ATTRIBUTED EVIDENCE

News tied to Astra

The model score of 82.9 rates this model's risk profile. The overall Doom Index of 65.3 measures the complete temporally weighted evidence record. These values answer different questions.

NET MODEL-ATTRIBUTED INDEX CONTRIBUTION+0.64

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.

Misuse TOWARD

OpenAI confirms Astra reaches Critical cyber capability and restricts access

OpenAI confirmed that its pre-release Astra model meets the Critical cybersecurity threshold after finding and exploiting internal V8 zero-days, building a browser-sandbox escape and executing host commands. OpenAI delayed development, added stronger refusals and monitoring, and plans restricted access to advanced cyber capabilities.

Full item contribution
+0.64
Astra equal share
+0.64
Read assessment →
AUDIT TRAIL

Model score history

  1. R1
    Doom Score 82.9

    Creates Astra's internal exact-model profile from OpenAI's dated Critical-capability and safeguard assessment.

    02 Sept 2026
SHARE THE FINDINGS

Share this page

DoomBench social sharing card for Astra.
  1. Astra by OpenAI has a DoomBench model risk score of 82.9 out of 100, based on five transparent version-specific dimensions rather than the overall index.

  2. Astra's highest current DoomBench dimension is capability at 100.0 out of 100; the profile publishes every component score and its editorial rationale.

  3. DoomBench links 1 source-backed evidence item to Astra, while keeping the model's risk profile separate from each item's contribution to the live Doom Index.

    https://www.doombench.com/models/openai-astra