Meta 🇺🇸 · Code Llama

Code Llama 34B

Largest initially released open-weight Code Llama foundation model for code generation, completion, infilling and long-context software tasks.

DOOM SCORE51.2out 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 51.2

Strong open coding capability and downloadable commercial weights enabled broad local deployment and modification. It remained a model rather than a standalone software agent.

Capability52
Autonomy10
Deployment92
Misuse potential52
Control difficulty60
MODEL-ATTRIBUTED EVIDENCE

News tied to Code Llama 34B

The model score of 51.2 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+0.10

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.

AUDIT TRAIL

Model score history

  1. R3
    Doom Score 51.2

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

    12 Aug 2026
  2. R2
    Doom Score 52.8

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

    12 Aug 2026
  3. R1
    Doom Score 55.4

    New exact Code Llama 34B profile.

    12 Aug 2026
SHARE THE FINDINGS

Share this page

DoomBench social sharing card for Code Llama 34B.
  1. Code Llama 34B by Meta has a DoomBench model risk score of 51.2 out of 100, based on five transparent version-specific dimensions rather than the overall index.

  2. Code Llama 34B's highest current DoomBench dimension is deployment at 92.0 out of 100; the profile publishes every component score and its editorial rationale.

  3. DoomBench links 1 source-backed evidence item to Code Llama 34B, while keeping the model's risk profile separate from each item's contribution to the live Doom Index.

    https://www.doombench.com/models/meta-code-llama-34b