Mistral Large

Mistral Large

mistralai · Released Feb 26, 2024 Professional
Intelligence #14 / 590
82.0 Our Score
AA Index #325 / 385
4.4 Artificial Analysis
Input #494 / 592
$2.00 per 1M tokens
Output #480 / 592
$6.00 per 1M tokens
Context #340 / 592
128,000 tokens

Analysis Summary

Mistral Large is a 2024 flagship from Mistral AI, supporting tool use, function calling, and file input with a 128K context window. Its benchmark scores place it in the lower tier of the current field, with modest reasoning and coding performance relative to models available today.

For businesses, it can handle general-purpose text tasks, structured output generation, and basic tool-use workflows. The file input modality adds some utility for document-based tasks. However, at $2 input and $6 output per million tokens, the price-to-performance ratio is unfavourable compared to newer alternatives that offer stronger benchmarks at similar or lower cost.

Teams already using Mistral's infrastructure may find it a reasonable fit for mid-complexity tasks, but for new deployments, more capable models are available at comparable or lower cost. It is best treated as a legacy option within the Mistral family rather than a primary choice.

Assessed June 30, 2026

Editorial notes

Mistral Large offers tool use and function calling with a 128K context window, but its benchmark performance is limited by current standards and pricing is relatively high for what it delivers.

Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?

Performance Profile

Intelligence1.4Technical0Value6.8Content0
Intelligence 1.4/10
Technical 0/10
Content 0/10
Value 6.8/10

How Mistral Large compares

Mistral Large ranks #325 of 385 AI models we track for overall intelligence. Its 128K-token context window is larger than 43% of the models we list. At $2.00 per million input tokens it is cheaper than 17% of comparable models.

About Mistral Large

This is Mistral AI's flagship model, Mistral Large 2 (version mistral-large-2407). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more...

Capabilities

Tool Use Function Calling

Performance Indices

Source: Artificial Analysis

4.4 Intelligence Index

Benchmark Scores

Intelligence

GPQA Diamond 35.1% Graduate-level scientific reasoning
HLE 3.4% Humanity's Last Exam
MMLU Pro 51.5% Multi-task language understanding
MATH 500 52.7% Mathematical problem-solving
SciCode 20.8% Scientific computing

Technical

LiveCodeBench 17.8% Live coding evaluation

Benchmark data from Artificial Analysis and Hugging Face

How does Mistral Large stack up?

Compare side-by-side with other professional models.

Compare Models

Model Information

OpenRouter ID mistralai/mistral-large
Providermistralai
Model FamilyMistral
Release Date February 26, 2024
Context Length128,000 tokens
Status Active

Pricing

Token Type Cost per 1M tokens Cost per 1K tokens
Input $2.00 $0.002000
Output $6.00 $0.006000

Live Performance

Live endpoint metrics, refreshed every 30 minutes.

99.8%
Avg Uptime
1,188ms
Best Latency (TTFT)
31 tok/s
Best Throughput
1/1
Active Endpoints
Available via: Mistral

Leaderboard Categories

Frequently asked questions about Mistral Large

How much does Mistral Large cost?

Mistral Large costs $2.00 per million input tokens and $6.00 per million output tokens.

What is the context window of Mistral Large?

Mistral Large has a context window of 128,000 tokens (128K).

What can Mistral Large do?

Mistral Large supports tool use and function calling.

Who created Mistral Large?

Mistral Large is developed by Mistral AI and was released on February 26, 2024.