# Mistral Large 3

Europe's most powerful open model, 675B MoE (41B active), agentic-tuned, strong multilingual performance.

## Agent Decision Summary
- Risk level: low
- Source confidence: medium
- Recommended workflows: Browser automation, Local or private AI stack
- Permission surface: low explicit permission surface in metadata
- Agent JSON: https://www.openagent.bot/models/mistral-large-3.agent.json

## Summary
Europe's most powerful open model, 675B MoE (41B active), agentic-tuned, strong multilingual performance.

## What It Does
Mistral Large 3 is a model in the models category. Europe's most powerful open model, 675B MoE (41B active), agentic-tuned, strong multilingual performance.

## How To Evaluate
Evaluate Mistral Large 3 by starting from the official sources, checking its docs, demo interface surface, and running one narrow workflow before expanding scope. Recorded integrations include GitHub, Hugging Face.

## Why It Matters
Mistral Large 3 is Europe's most powerful open model with a 675B MoE architecture (41B active parameters), offering strong multilingual performance and agentic tuning that makes it a leading choice for European AI builders.


## Best For
- Teams needing strong multilingual open model performance across European languages
- Developers evaluating agentic-tuned models for production agent workflows
- Builders looking for Apache-2.0 licensed alternatives to US-based open model families

## Not For
- Use cases requiring a small dense model rather than a large MoE architecture
- Teams that cannot independently verify model behavior for their specific language and domain

## Fit Matrix
- Browser automation: strong. Mistral Large 3 has multiple signals for browser automation, including matching tags, capabilities, category, or positioning. Required check: Run one non-sensitive website task and inspect clicks, waits, retries, and changed URLs.
- Local or private AI stack: strong. Mistral Large 3 has multiple signals for local or private ai stack, including matching tags, capabilities, category, or positioning. Required check: Verify hardware requirements, data path, storage, and whether all calls stay in your environment.
- Evaluation and observability: partial. Mistral Large 3 has at least one signal for evaluation and observability, but should be checked against a real task before adoption. Required check: Add one repeatable test case and confirm results can run again in review or CI.
- Reusable skill workflow: partial. Mistral Large 3 has at least one signal for reusable skill workflow, but should be checked against a real task before adoption. Required check: Run one skill end to end and check whether it produces evidence or structured output.
- Coding agent workflow: weak. Mistral Large 3 is not primarily positioned for coding agent workflow in the current metadata. Required check: Run a small repository change and inspect the diff, tests, and rollback path.
- Connector or protocol layer: weak. Mistral Large 3 is not primarily positioned for connector or protocol layer in the current metadata. Required check: Connect one low-risk service, then inspect schemas, auth scope, errors, and logs.

## Evidence
- verified: Mistral Large 3 is listed as open source. Source: License metadata: Apache-2.0
- verified: Mistral Large 3 has a recorded GitHub repository: mistralai/mistral-large. Source: Resource facts and GitHub source link.
- inferred: Mistral Large 3 supports these recorded deployment modes: local, self hosted, cloud. Source: OpenAgent decision signal metadata.
- inferred: Mistral Large 3 is tagged with local inference, inference capabilities. Source: OpenAgent capability taxonomy.

## Missing Checks
- Dedicated docs link is missing.
- Repository freshness has not been recorded.

## Next Actions
- Inspect repository: https://github.com/mistralai/mistral-large

## Facts
- Category: models
- Resource type: model
- Open source: yes
- License: Apache-2.0
- Last verified: 2026-06-16
- GitHub repo: mistralai/mistral-large
- GitHub stars: 10000

## Capabilities
- local-inference
- inference

## Structured Use Case Tags
- local-ai
- self-hosted-ai

## Links
- GitHub: https://github.com/mistralai/mistral-large

## Structured Outputs
- JSON: https://www.openagent.bot/models/mistral-large-3.json
- Markdown: https://www.openagent.bot/models/mistral-large-3.md
- Agent JSON: https://www.openagent.bot/models/mistral-large-3.agent.json
- Canonical: https://www.openagent.bot/models/mistral-large-3