Meta 🇺🇸 · Code Llama

Code Llama 70B Instruct

Instruction-tuned open-weight 70B Code Llama checkpoint for conversational programming assistance.

DOOM SCORE52.5out 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 52.5

Instruction tuning made the openly deployable checkpoint easier to direct for both benign and harmful coding tasks, modestly raising autonomy, misuse and control difficulty.

Capability55
Autonomy8
Deployment94
Misuse potential54
Control difficulty61
MODEL-ATTRIBUTED EVIDENCE

News tied to Code Llama 70B Instruct

The model score of 52.5 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+0.05

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 52.5

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

    12 Aug 2026
  2. R2
    Doom Score 53.0

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

    12 Aug 2026
  3. R1
    Doom Score 54.1

    New exact Code Llama 70B Instruct profile.

    12 Aug 2026
SHARE THE FINDINGS

Share this page

DoomBench social sharing card for Code Llama 70B Instruct.
  1. Code Llama 70B Instruct by Meta has a DoomBench model risk score of 52.5 out of 100, based on five transparent version-specific dimensions rather than the overall index.

  2. Code Llama 70B Instruct's highest current DoomBench dimension is deployment at 94.0 out of 100; the profile publishes every component score and its editorial rationale.

  3. DoomBench links 1 source-backed evidence item to Code Llama 70B Instruct, 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-70b-instruct