SpaceXAI 🇺🇸 · Grok 3

Grok 3 mini

A cost-efficient Grok 3 beta reasoning tier optimized for mathematics, coding and other STEM tasks through reinforcement-learned test-time compute.

DOOM SCORE69.7out 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 4

Why this model scores 69.7

The mini tier trails flagship world knowledge but demonstrates strong reasoning and coding with cost-efficient inference. Test-time reasoning raises autonomy, while early hosted rollout constrains deployment and control difficulty compared with open or fully general-availability systems.

Capability77
Autonomy64
Deployment78
Misuse potential70
Control difficulty58
MODEL-ATTRIBUTED EVIDENCE

News tied to Grok 3 mini

The model score of 69.7 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.

NET MODEL-ATTRIBUTED INDEX CONTRIBUTION+0.11

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.

AUDIT TRAIL

Model score history

  1. R4
    Doom Score 69.7

    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
  2. R3
    Doom Score 69.7

    Exact-version evidence chronology replayed after run doombench-hourly-news-20260812-142416 under temporal-monthly-pressure-v4.

    12 Aug 2026
  3. R2
    Doom Score 70.1

    Exact-version evidence chronology replayed after run doombench-hourly-news-20260812-132112 under fixed-sensitivity-v3.

    12 Aug 2026
  4. R1
    Doom Score 71.2

    Initial exact profile for the separately named February 2025 Grok 3 mini beta tier.

    12 Aug 2026
SHARE THE FINDINGS

Share this page

DoomBench social sharing card for Grok 3 mini.
  1. Grok 3 mini by SpaceXAI has a DoomBench model risk score of 69.7 out of 100, based on five transparent version-specific dimensions rather than the overall index.

  2. Grok 3 mini's highest current DoomBench dimension is deployment at 78.0 out of 100; the profile publishes every component score and its editorial rationale.

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

    https://www.doombench.com/models/spacexai-grok-3-mini