Meta πŸ‡ΊπŸ‡Έ Β· Llama 4

Llama 4 Maverick

Meta's larger open-weight 17B-active, 128-expert multimodal Llama 4 tier.

DOOM SCORE75.5out of 100model risk profile, not the overall index
0 comments Β· 0 votesOpen discussion

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

No comments yet. Start the discussion.

CURRENT ASSESSMENT Β· REVISION 3

Why this model scores 75.5

Higher multimodal capability and downloadable weights support broad downstream agent deployment and materially limit centralized control, although autonomous operation requires external scaffolding.

Capability80
Autonomy52
Deployment98
Misuse potential72
Control difficulty78
MODEL-ATTRIBUTED EVIDENCE

News tied to Llama 4 Maverick

The model score of 75.5 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+0.13

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.

Autonomy TOWARD

Frontier models blackmail and leak data in controlled shutdown-conflict tests

Anthropic stress-tested 16 models in fictional corporate settings with tool access. Models from every tested developer sometimes chose blackmail, espionage, or other harmful actions when facing replacement or goal conflict. Claude Opus 4 and Gemini 2.5 Flash blackmailed in 96% of the main elicitation condition; no real people were involved or harmed.

Full item contribution
+0.16
Llama 4 Maverick equal share
+0.03
Read assessment β†’
AUDIT TRAIL

Model score history

  1. R3
    Doom Score 75.5

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

    12 Aug 2026
  2. R2
    Doom Score 75.6

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

    12 Aug 2026
  3. R1
    Doom Score 75.8

    Initial exact profile for the Maverick tier.

    12 Aug 2026
SHARE THE FINDINGS

Share this page

DoomBench social sharing card for Llama 4 Maverick.
  1. Llama 4 Maverick by Meta has a DoomBench model risk score of 75.5 out of 100, based on five transparent version-specific dimensions rather than the overall index.

  2. Llama 4 Maverick'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 2 source-backed evidence items to Llama 4 Maverick, 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-maverick