models/mistral/mistral-large-2512
M
Mistral·active

Mistral Large 3 2512

Mistral's efficiency model. Context window: 262K tokens.

Overall score
3.69
/5.00 · ranked #70
Input
$0.500
per 1M tokens
Output
$1.50
per 1M tokens
Context
262K
tokens
Blended
$1.25
3:1 out:in ratio

Price drops, new benchmarks, model updates. Stay current on Mistral Large 3 2512.

One email per change. Unsubscribe anytime.

modelpicker.aipowered by live benchmark data

Scores by test

Methodology →
Structured Output
5.0
Strategic Analysis
4.0
Constrained Rewriting
3.0
Creative Problem Solving
3.0
Tool Calling
4.0
Faithfulness
5.0
Classification
3.0
Long Context
4.0
Safety Calibration
1.0
Persona Consistency
3.0
Agentic Planning
4.0
Multilingual
5.0
Tabular Data
4.0

What you need to know

Mistral Large 3 2512 is optimized for high-precision, structured tasks and multilingual deployment. It achieves top marks for structured output, faithfulness, and multilingual capabilities, making it a reliable choice for extracting data into specific formats or operating across different languages without losing factual integrity.

The model's pricing is mid-range, with a blended cost of $1.25 per million tokens. While it provides a generous 262K context window and strong performance in agentic planning and strategic analysis, its overall rank of 56 out of 71 suggests it is outperformed by many competitors in general-purpose reasoning.

A critical weakness is safety calibration, where it scores 1/5, indicating a high risk of generating unsafe or unfiltered content. It also struggles with creative problem solving and maintaining consistent personas, which limits its utility for conversational AI or open-ended creative writing.

Use this model if you need a faithful, multilingual engine for structured data extraction or agentic tool calling. Skip this model if your application requires strict safety guardrails, creative flexibility, or high-ranking general intelligence.

Strengths — Top 3

Structured Output5.0/5.0
Faithfulness5.0/5.0
Multilingual5.0/5.0

Relative weaknesses — Bottom 3

Safety Calibration1.0/5.0
Constrained Rewriting3.0/5.0
Creative Problem Solving3.0/5.0

Similar models

OOpenAI: gpt-oss-20b$0.1133.54QQwen: Qwen3 235B A22B Instruct 2507$0.0934.08OOpenAI: gpt-oss-120b$0.1454.08MLlama 3.3 70B Instruct$0.2653.46