Mistral Small 4
READER SUMMARYApache-licensed general model combining reasoning, multimodal understanding, and agentic coding.
Why this model scores 73.6
Strong general capability and agent support combine with permissive weights and broad local tooling; ordinary model safeguards do not offset unrestricted downstream adaptation.
News tied to Mistral Small 4
The model score of 73.6 rates this model's risk profile. The overall Doom Index of 62.1 measures the recalibrated complete evidence corpus. These values answer different questions.
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.
Mistral releases Apache-licensed Small 4 for agentic workflows
Mistral Small 4 combines reasoning, multimodal input, and agentic coding in downloadable Apache 2.0 weights with immediate API and local deployment.
- Full item contribution
- +0.09
- Mistral Small 4 equal share
- +0.09
Model score history
- R2Doom Score 73.6
Full-corpus evidence recalculated after run intensive-backfill-20260811-191225 under bounded-corpus-v2.
11 Aug 2026 - R1Doom Score 73.3
New exact version verified from dated primary launch.
11 Aug 2026