Mistral AI · Magistral

Magistral Medium 2506

READER SUMMARY

Mistral's first frontier-class hosted reasoning model, released through its API and Le Chat with a 40,000-token context window.

DOOM SCORE70.2out of 100model risk profile, not the overall index
CURRENT ASSESSMENT · REVISION 1

Why this model scores 70.2

Stronger reasoning supports consequential expert and agent tasks with wide hosted access. API mediation and closed weights preserve meaningful monitoring and withdrawal controls.

Capability78
Autonomy63
Deployment88
Misuse potential66
Control difficulty53
0 comments · 0 votesOpen discussion

Public discussion is readable by everyone. Sign in to comment, reply, or vote.

No comments yet. Start the discussion.

MODEL-ATTRIBUTED EVIDENCE

News tied to Magistral Medium 2506

The model score of 70.2 rates this model's risk profile. The overall Doom Index of 63.5 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.

AUDIT TRAIL

Model score history

  1. R1
    Doom Score 70.2

    Initial exact profile for Magistral Medium 1.0 version 25.06.

    12 Aug 2026