Meta 🇺🇸 · Llama 4

Llama 4 Scout

Meta's open-weight 17B-active, 16-expert multimodal Llama 4 model with an exceptionally long context window.

DOOM SCORE72.3out 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 3

Why this model scores 72.3

Strong multimodal and long-context capability is broadly deployable through downloadable weights. Tool autonomy is not intrinsic, while permissive diffusion raises misuse and control difficulty.

Capability76
Autonomy46
Deployment98
Misuse potential69
Control difficulty76
MODEL-ATTRIBUTED EVIDENCE

News tied to Llama 4 Scout

The model score of 72.3 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+0.10

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.

Capability TOWARD

Meta releases open-weight Llama 4 multimodal models

Meta released Llama 4 Scout and Maverick weights with native multimodality, mixture-of-experts architectures and broad commercial reuse terms, while deploying Llama 4 through Meta AI.

Full item contribution
+0.20
Llama 4 Scout equal share
+0.10
Read assessment →
AUDIT TRAIL

Model score history

  1. R3
    Doom Score 72.3

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

    12 Aug 2026
  2. R2
    Doom Score 72.5

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

    12 Aug 2026
  3. R1
    Doom Score 73.0

    Initial exact profile for the Scout tier.

    12 Aug 2026
SHARE THE FINDINGS

Share this page

DoomBench social sharing card for Llama 4 Scout.
  1. Llama 4 Scout by Meta has a DoomBench model risk score of 72.3 out of 100, based on five transparent version-specific dimensions rather than the overall index.

  2. Llama 4 Scout's highest current DoomBench dimension is deployment at 98.0 out of 100; the profile publishes every component score and its editorial rationale.

  3. DoomBench links 1 source-backed evidence item to Llama 4 Scout, while keeping the model's risk profile separate from each item's contribution to the live Doom Index.

    https://www.doombench.com/models/meta-llama-4-scout