Mistral Large 2407

Mistral Large 2407

mistralai · Released Nov 19, 2024 Professional
Intelligence #9 / 579
82.0 Our Score
AA Index #274 / 380
7.3 Artificial Analysis
Input #485 / 579
$2.00 per 1M tokens
Output #471 / 579
$6.00 per 1M tokens
Context #237 / 579
131,072 tokens

Analysis Summary

Mistral Large 2407 is Mistral AI's mid-2024 flagship, with an intelligence index of 7.3 and a high agentic index of 33 for its generation. Tool use and function calling are supported, and its MMLU-Pro of 0.683 and GPQA of 0.472 reflect competent general knowledge. The text+file modality adds document handling capability.

For businesses, it suits structured content generation, tool-augmented workflows, and moderate agentic tasks. Its instruction-following score (ifbench 0.316) is adequate but not exceptional. The absence of vision limits its use in multimodal pipelines, and its intelligence index has been surpassed by newer models in the same price bracket.

At $2.00 input and $6.00 output per million tokens, it sits in the mid-tier on cost. Teams already in the Mistral ecosystem will find it reliable for content and tool-use tasks, but new adopters should compare it against newer alternatives before committing at this price point.

Assessed June 17, 2026

Editorial notes

Mistral Large 2407 from Mistral AI offers solid general reasoning, tool use, and function calling with a strong agentic index of 33, though it lacks vision and is priced at a mid-tier level.

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

Performance Profile

Intelligence1.9Technical4.1Value6.8Content1.9
Intelligence 1.9/10
Technical 4.1/10
Content 1.9/10
Value 6.8/10

How Mistral Large 2407 compares

Mistral Large 2407 ranks #274 of 380 AI models we track for overall intelligence, #136 of 292 for agentic tasks. Its 131K-token context window is larger than 59% of the models we list. At $2.00 per million input tokens it is cheaper than 16% of comparable models.

About Mistral Large 2407

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

7.3 Intelligence Index
33 Agentic Index

Benchmark Scores

Intelligence

GPQA Diamond 47.2% Graduate-level scientific reasoning
HLE 3.2% Humanity's Last Exam
MMLU Pro 68.3% Multi-task language understanding
MATH 500 71.4% Mathematical problem-solving
AIME 9.3% Competition mathematics
SciCode 27.1% Scientific computing

Technical

LiveCodeBench 26.7% Live coding evaluation
τ²-Bench 33% Conversational agent benchmark

Content

IFBench 31.6% Instruction following
LCR 1.7% Long-context reasoning

Benchmark data from Artificial Analysis and Hugging Face

How does Mistral Large 2407 stack up?

Compare side-by-side with other professional models.

Compare Models

Model Information

OpenRouter ID mistralai/mistral-large-2407
Providermistralai
Model FamilyMistral
Release Date November 19, 2024
Context Length131,072 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.

1,266ms
Best Latency (TTFT)
12 tok/s
Best Throughput
0/1
Active Endpoints
Available via: Mistral

Leaderboard Categories

Frequently asked questions about Mistral Large 2407

How much does Mistral Large 2407 cost?

Mistral Large 2407 costs $2.00 per million input tokens and $6.00 per million output tokens.

What is the context window of Mistral Large 2407?

Mistral Large 2407 has a context window of 131,072 tokens (131K).

What can Mistral Large 2407 do?

Mistral Large 2407 supports tool use and function calling.

Who created Mistral Large 2407?

Mistral Large 2407 is developed by Mistral AI and was released on November 19, 2024.