Mistral AI · Mistral Medium

Mistral Medium 3.5

READER SUMMARY

A 128-billion-parameter open-weight model optimized for long-horizon coding, multi-tool work, structured output, and persistent remote agents.

DOOM SCORE79.5out of 100model risk profile, not the overall index
CURRENT ASSESSMENT · REVISION 2

Why this model scores 79.5

Strong agentic coding, long-running execution, open weights, self-hosting on four GPUs, and broad API and product availability create high autonomy and diffusion, while capability remains below the closed frontier.

Capability78
Autonomy84
Deployment90
Misuse potential80
Control difficulty70
MODEL-ATTRIBUTED EVIDENCE

News tied to Mistral Medium 3.5

The model score of 79.5 rates this model's risk profile. The overall Doom Index of 62.1 measures the recalibrated complete evidence corpus. These values answer different questions.

NET MODEL-ATTRIBUTED INDEX CONTRIBUTION+0.14

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. R2
    Doom Score 79.5

    Full-corpus evidence recalculated after run intensive-backfill-20260811-191225 under bounded-corpus-v2.

    11 Aug 2026
  2. R1
    Doom Score 79.7

    Initial exact-version profile from the dated open-weight and remote-agent launch.

    11 Aug 2026