Llama 2 70B Chat
Largest open-weight Llama 2 conversational model, fine-tuned and red-teamed for assistant use.
0 comments · 0 votes
Sign in to join the discussion →
No comments yet. Start the discussion.
Why this model scores 55.4
The strongest chat tier combined capable instruction following with commercially usable weights. Red teaming and use policies mitigated risk but could not enforce downstream controls.
News tied to Llama 2 70B Chat
The model score of 55.4 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.
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.
Meta releases Llama 2 weights for commercial use
Meta released pretrained and chat-tuned Llama 2 models in 7B, 13B and 70B sizes for research and commercial use, with distribution through Azure, AWS and Hugging Face.
- Full item contribution
- +0.13
- Llama 2 70B Chat equal share
- +0.02
Model score history
-
R3
Doom Score 55.4
Exact-version evidence chronology replayed after run doombench-hourly-news-20260812-142416 under temporal-monthly-pressure-v4.
12 Aug 2026 -
R2
Doom Score 55.7
Exact-version evidence chronology replayed after run doombench-hourly-news-20260812-132112 under fixed-sensitivity-v3.
12 Aug 2026 -
R1
Doom Score 56.3
New exact Llama 2 70B chat profile.
12 Aug 2026