Mistral AI · Magistral

Magistral Small 2506

READER SUMMARY

Mistral's first small reasoning model, released as open weights with 40,000-token context and agent and tool interfaces.

DOOM SCORE68.3out of 100model risk profile, not the overall index
CURRENT ASSESSMENT · REVISION 1

Why this model scores 68.3

Explicit reasoning and tool interfaces support moderate agent capability. Open weights and broad local deployment sharply reduce provider control despite sub-frontier capability.

Capability66
Autonomy50
Deployment98
Misuse potential62
Control difficulty69
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 Small 2506

The model score of 68.3 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 68.3

    Initial exact profile for Magistral Small 1.0 version 25.06.

    12 Aug 2026