Mistral AI 🇫🇷 · Mistral OCR

Mistral OCR 2503

Mistral's March 2025 document-understanding model for extracting structured text and images through hosted APIs and Le Chat.

DOOM SCORE43.5out of 100model risk profile, not the overall index
0 comments · 0 votesOpen discussion

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

No comments yet. Start the discussion.

CURRENT ASSESSMENT · REVISION 4

Why this model scores 43.5

Strong specialized document extraction improves automation and agent inputs, with broad hosted availability. Narrow scope and provider controls constrain autonomy, misuse and control difficulty.

Capability52
Autonomy15
Deployment84
Misuse potential35
Control difficulty35
MODEL-ATTRIBUTED EVIDENCE

News tied to Mistral OCR 2503

The model score of 43.5 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.

NET MODEL-ATTRIBUTED INDEX CONTRIBUTION+0.08

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.

AUDIT TRAIL

Model score history

  1. R4
    Doom Score 43.5

    Source-backed model availability audit using the model's existing primary or authoritative catalogue evidence. Exact-version evidence chronology replayed under temporal-monthly-pressure-v4.

    12 Aug 2026
  2. R3
    Doom Score 43.5

    Exact-version evidence chronology replayed after run doombench-hourly-news-20260812-142416 under temporal-monthly-pressure-v4.

    12 Aug 2026
  3. R2
    Doom Score 44.9

    Exact-version evidence chronology replayed after run doombench-hourly-news-20260812-132112 under fixed-sensitivity-v3.

    12 Aug 2026
  4. R1
    Doom Score 48.2

    Initial exact profile for the immutable March 2025 OCR checkpoint.

    12 Aug 2026
SHARE THE FINDINGS

Share this page

DoomBench social sharing card for Mistral OCR 2503.
  1. Mistral OCR 2503 by Mistral AI has a DoomBench model risk score of 43.5 out of 100, based on five transparent version-specific dimensions rather than the overall index.

  2. Mistral OCR 2503's highest current DoomBench dimension is deployment at 84.0 out of 100; the profile publishes every component score and its editorial rationale.

  3. DoomBench links 1 source-backed evidence item to Mistral OCR 2503, while keeping the model's risk profile separate from each item's contribution to the live Doom Index.

    https://www.doombench.com/models/mistral-ai-mistral-ocr-2503