Mistral AI · Mistral NeMo

Mistral NeMo 12B Instruct

READER SUMMARY

The instruction-tuned Mistral NeMo 12B checkpoint with multilingual dialogue, coding, 128K context, function calling, Apache-licensed weights and hosted API access.

DOOM SCORE55.7out of 100model risk profile, not the overall index

CURRENT ASSESSMENT · REVISION 1

Why this model scores 55.7

Instruction following and function calling add practical agent utility, while permissive downloadable weights and hosted access make deployment, modification and harmful repurposing difficult to contain.

Capability53

Autonomy12

Deployment97

Misuse potential51

Control difficulty63

0 comments · 0 votesOpen discussion

No comments yet. Start the discussion.

MODEL-ATTRIBUTED EVIDENCE

News tied to Mistral NeMo 12B Instruct

The model score of 55.7 rates this model's risk profile. The overall Doom Index of 63.2 measures the recalibrated complete evidence corpus. These values answer different questions.

NET MODEL-ATTRIBUTED INDEX CONTRIBUTION+0.01

Each article's leave-one-out 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 are recalculated from their technical profile and related news, but never feed back into the overall index.

18 Jul 2024CapabilityTOWARD

Mistral AI and NVIDIA release Mistral NeMo

Mistral AI and NVIDIA released Mistral NeMo 12B base and instruction checkpoints with a 128K context window, multilingual and coding capability, function calling, Apache 2.0 weights and hosted API access.

Full item contribution: +0.03
Mistral NeMo 12B Instruct equal share: +0.01

Read assessment →

AUDIT TRAIL

Model score history

R1
Doom Score 55.7
New exact Mistral NeMo 12B instruction checkpoint.
12 Aug 2026