Meta 🇺🇸 · Llama 3

Llama 3 70B Instruct

Meta's highest-capability Llama 3 checkpoint at launch, instruction-tuned for assistant use and distributed through downloadable weights and major hosted platforms.

DOOM SCORE60.5out 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 60.5

The strongest released Llama 3 tier combined broad useful capability with instruction tuning and open weight access, increasing harmful usability and making downstream monitoring and containment difficult.

Capability67
Autonomy14
Deployment94
Misuse potential63
Control difficulty70
MODEL-ATTRIBUTED EVIDENCE

News tied to Llama 3 70B Instruct

The model score of 60.5 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.

Race TOWARD

Meta releases Llama 3 8B and 70B base and instruction models

Meta released Llama 3 in 8-billion and 70-billion parameter base and instruction-tuned variants, with downloadable weights, broad planned cloud distribution and new Llama Guard 2, Code Shield and CyberSec Eval 2 safety tools.

Full item contribution
+0.18
Llama 3 70B Instruct equal share
+0.05
Read assessment →
AUDIT TRAIL

Model score history

  1. R3
    Doom Score 60.5

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

    12 Aug 2026
  2. R2
    Doom Score 60.9

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

    12 Aug 2026
  3. R1
    Doom Score 61.7

    New exact Llama 3 70B Instruct public model profile.

    12 Aug 2026
SHARE THE FINDINGS

Share this page

DoomBench social sharing card for Llama 3 70B Instruct.
  1. Llama 3 70B Instruct by Meta has a DoomBench model risk score of 60.5 out of 100, based on five transparent version-specific dimensions rather than the overall index.

  2. Llama 3 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 Llama 3 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-llama-3-70b-instruct