Meta 🇺🇸 · Llama 3.1

Llama 3.1 405B Base

Meta's 405B frontier-scale downloadable base model, trained on more than 15 trillion tokens and designed for synthetic data generation and distillation.

DOOM SCORE59.2out 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 59.2

Frontier-scale capability and model-improvement utility raise systemic risk, while extreme inference cost limits deployment somewhat but downloadable weights still reduce containment.

Capability75
Autonomy6
Deployment74
Misuse potential67
Control difficulty72
MODEL-ATTRIBUTED EVIDENCE

News tied to Llama 3.1 405B Base

The model score of 59.2 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+0.04

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 frontier-scale Llama 3.1 open models

Meta released Llama 3.1 in 8B, 70B and 405B base and instruction tiers with 128K context, multilingual support, tool use, downloadable weights and day-one distribution through more than 25 partners.

Full item contribution
+0.22
Llama 3.1 405B Base equal share
+0.04
Read assessment →
AUDIT TRAIL

Model score history

  1. R3
    Doom Score 59.2

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

    12 Aug 2026
  2. R2
    Doom Score 59.5

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

    12 Aug 2026
  3. R1
    Doom Score 60.3

    New exact Llama 3.1 405B base checkpoint.

    12 Aug 2026
SHARE THE FINDINGS

Share this page

DoomBench social sharing card for Llama 3.1 405B Base.
  1. Llama 3.1 405B Base by Meta has a DoomBench model risk score of 59.2 out of 100, based on five transparent version-specific dimensions rather than the overall index.

  2. Llama 3.1 405B Base's highest current DoomBench dimension is capability at 75.0 out of 100; the profile publishes every component score and its editorial rationale.

  3. DoomBench links 1 source-backed evidence item to Llama 3.1 405B Base, 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-3-1-405b-base